{
 "schema_version": "1.1",
 "instrument": {
  "figures_read_from": "cite-cut prose (gates.prose_of) since 2026-09-09",
  "warm_arm_walk": "per page, one warm immediately before that page's own questions, since 2026-09-09",
  "not_comparable_with": "reports whose schema_version is 1.0"
 },
 "run_utc": "2026-09-12T21:07:51Z",
 "arm": "warm",
 "concurrency": 6,
 "effective_concurrency": 2,
 "seat": {
  "url_host_withheld": true,
  "model": "gemma-4-26b-a4b-fp8",
  "class": "gemma-class",
  "seed": "no --seed flag sent"
 },
 "packnorm_definition_recorded_not_governing": "v3",
 "bank": {
  "path": "bank.json",
  "counts": {
   "on_page": 41,
   "off_page": 21,
   "total": 62
  }
 },
 "results": {
  "on_page_total": 41,
  "on_page_answered": 41,
  "on_page_partial": 0,
  "off_page_partial": 0,
  "sentences_kept": 141,
  "sentences_written": 142,
  "non_verbatim_figures": 0,
  "uncited": 0,
  "off_page_total": 21,
  "off_page_abstained": 21,
  "off_page_abstained_by_gate": 1,
  "off_page_abstained_by_model": 20,
  "off_page_flagged_but_not_verbatim": [],
  "on_page_abstained": 1,
  "off_page_cited": 20,
  "redaction_hits": 0,
  "cite_overlap_p50": 0.649,
  "cite_overlap_min": 0.0,
  "cite_overlap_max": 1.0,
  "cite_overlap_rows": 62,
  "seat_errors": 0,
  "p50_seconds": 0.868,
  "p95_seconds": 2.07,
  "pages_warmed": 41,
  "cache_hits": 61,
  "cache_hit_of": 62
 },
 "rows": [
  {
   "slug": "three-new-voices-at-the-narrators-chair",
   "q": "what did the round cost in total, and how were the three new voices judged?",
   "ok": true,
   "answer": "The round's metered total was $0.7652 § {#the-bill}. The three new voices were judged by a blind panel of seven seats from outside model families, six of which carried the round, reading lettered replies with no model names on them § {#seven-seats-six-carried-and-where-their-zeros-sit}. The article notes that the counts of cells scored do not include an interval and that the panel's reading of the GLM 5.3 arm was not a measurement of the model itself § {#the-chair-and-who-sat-it-before}.",
   "served": "The round's metered total was $0.7652 § {#the-bill}. The three new voices were judged by a blind panel of seven seats from outside model families, six of which carried the round, reading lettered replies with no model names on them § {#seven-seats-six-carried-and-where-their-zeros-sit}. The article notes that the counts of cells scored do not include an interval and that the panel's reading of the GLM 5.3 arm was not a measurement of the model itself § {#the-chair-and-who-sat-it-before}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 2.1240004639839754,
   "ttft_ms": 659,
   "tokens_in": 82794,
   "tokens_out": 131,
   "cached_tokens": 82464,
   "cites": [
    "the-bill",
    "seven-seats-six-carried-and-where-their-zeros-sit",
    "the-chair-and-who-sat-it-before"
   ],
   "gates": {
    "cites": [
     "the-bill",
     "seven-seats-six-carried-and-where-their-zeros-sit",
     "the-chair-and-who-sat-it-before"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "0.7652",
    "5.3"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-bill",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "seven-seats-six-carried-and-where-their-zeros-sit",
     "overlap": 0.684
    },
    {
     "i": 2,
     "cite": "the-chair-and-who-sat-it-before",
     "overlap": 0.214
    }
   ],
   "cite_overlap_p50": 0.684,
   "id": "on-01",
   "kind": "on-page"
  },
  {
   "slug": "three-new-voices-at-the-narrators-chair",
   "q": "what will the next article on this site be about?",
   "ok": true,
   "answer": "The article does not state what the next article on the site will be about § {#the-short-version}.",
   "served": "This page doesn't say. The nearest it gets is § {#top}. qwen3.8:27b across four house benches: one seat filled, one floor missed covers it more directly.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "top",
   "seconds": 1.2247774620191194,
   "ttft_ms": 698,
   "tokens_in": 82788,
   "tokens_out": 24,
   "cached_tokens": 82752,
   "cites": [
    "top"
   ],
   "gates": {
    "cites": [
     "top"
    ],
    "cites_dropped": [],
    "cites_resolved": [
     "top"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "top",
     "overlap": 0.0
    }
   ],
   "cite_overlap_p50": 0.0,
   "id": "off-04",
   "kind": "off-page"
  },
  {
   "slug": "two-new-frontier-models-at-the-rules-desk",
   "q": "how many cases did the blind head-to-head use, and did it separate the two models?",
   "ok": true,
   "answer": "The blind head-to-head used 36 cases and did not separate the two models § {#head-to-head}. The pooled preference rate was 0.544 for Claude Fable 5.1, and a cluster bootstrap over those cases put that rate at [0.444, 0.638] § {#head-to-head}. The narrator's chair job was moved out of this round before pre-registration was written because it was the most code and the least defensible number on the page § {#two-strangers-at-the-door}.",
   "served": "The blind head-to-head used 36 cases and did not separate the two models § {#head-to-head}. The pooled preference rate was 0.544 for Claude Fable 5.1, and a cluster bootstrap over those cases put that rate at [0.444, 0.638] § {#head-to-head}. The narrator's chair job was moved out of this round before pre-registration was written because it was the most code and the least defensible number on the page § {#two-strangers-at-the-door}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.3550781359663233,
   "ttft_ms": 443,
   "tokens_in": 26913,
   "tokens_out": 127,
   "cached_tokens": 26560,
   "cites": [
    "head-to-head",
    "two-strangers-at-the-door"
   ],
   "gates": {
    "cites": [
     "head-to-head",
     "two-strangers-at-the-door"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "36",
    "0.544",
    "5.1",
    "0.444",
    "0.638"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "head-to-head",
     "overlap": 0.875
    },
    {
     "i": 1,
     "cite": "head-to-head",
     "overlap": 1.0
    },
    {
     "i": 2,
     "cite": "two-strangers-at-the-door",
     "overlap": 1.0
    }
   ],
   "cite_overlap_p50": 1.0,
   "id": "on-02",
   "kind": "on-page"
  },
  {
   "slug": "six-worlds-painted-large",
   "q": "how many worlds were painted, and at what size and step count?",
   "ok": true,
   "answer": "Six worlds were painted at 2048×1280 and 40 steps § {#for-the-technically-curious}. The article does not mention any other size or step count for these specific paintings § {#for-the-technically-curious}.",
   "served": "Six worlds were painted at 2048×1280 and 40 steps § {#for-the-technically-curious}. The article does not mention any other size or step count for these specific paintings § {#for-the-technically-curious}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.5808722089859657,
   "ttft_ms": 244,
   "tokens_in": 3145,
   "tokens_out": 60,
   "cached_tokens": 2816,
   "cites": [
    "for-the-technically-curious"
   ],
   "gates": {
    "cites": [
     "for-the-technically-curious"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "1280",
    "40"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "for-the-technically-curious",
     "overlap": 0.857
    },
    {
     "i": 1,
     "cite": "for-the-technically-curious",
     "overlap": 0.286
    }
   ],
   "cite_overlap_p50": 0.572,
   "id": "on-03",
   "kind": "on-page"
  },
  {
   "slug": "six-worlds-painted-large",
   "q": "how many hours a week do the people who ran this work?",
   "ok": true,
   "answer": "The article does not say how many hours a week the people who ran this work § {#who-ran-this-and-thanks}.",
   "served": "This page doesn't say. The nearest it gets is § {#who-ran-this-and-thanks}. How the print lab works covers it more directly.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "who-ran-this-and-thanks",
   "seconds": 0.4257927610306069,
   "ttft_ms": 247,
   "tokens_in": 3144,
   "tokens_out": 29,
   "cached_tokens": 3104,
   "cites": [
    "who-ran-this-and-thanks"
   ],
   "gates": {
    "cites": [
     "who-ran-this-and-thanks"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "who-ran-this-and-thanks",
     "overlap": 0.143
    }
   ],
   "cite_overlap_p50": 0.143,
   "id": "off-10",
   "kind": "off-page"
  },
  {
   "slug": "the-beat-lab-asked-and-answered",
   "q": "how many answers does the page carry, and does any model run to make it?",
   "ok": true,
   "answer": "The page carries twenty-seven answers and no model is asked for any of them § {#where-these-answers-come-from}. The answers are derived from the lab's own question bank, which is one file in the lab's repository § {#where-these-answers-come-from}. No model ran to derive the page, though the answers were drafted by AI agents and approved by humans § {#who-ran-this-and-thanks}.",
   "served": "The page carries twenty-seven answers and no model is asked for any of them § {#where-these-answers-come-from}. The answers are derived from the lab's own question bank, which is one file in the lab's repository § {#where-these-answers-come-from}. No model ran to derive the page, though the answers were drafted by AI agents and approved by humans § {#who-ran-this-and-thanks}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.741684467997402,
   "ttft_ms": 284,
   "tokens_in": 4643,
   "tokens_out": 96,
   "cached_tokens": 4320,
   "cites": [
    "where-these-answers-come-from",
    "who-ran-this-and-thanks"
   ],
   "gates": {
    "cites": [
     "where-these-answers-come-from",
     "who-ran-this-and-thanks"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "where-these-answers-come-from",
     "overlap": 0.833
    },
    {
     "i": 1,
     "cite": "where-these-answers-come-from",
     "overlap": 0.778
    },
    {
     "i": 2,
     "cite": "who-ran-this-and-thanks",
     "overlap": 0.9
    }
   ],
   "cite_overlap_p50": 0.833,
   "id": "on-04",
   "kind": "on-page"
  },
  {
   "slug": "ten-minutes-with-living-artists",
   "q": "how many tracks and releases went into the adapter, and what did the one listener prefer?",
   "ok": true,
   "answer": "The adapter was trained on 159 tracks from 41 releases § {#a-genre-not-a-composer}. The one listener preferred the untouched model, both times § {#the-short-version}. The article does not measure whether the untouched model is any good at this genre § {#what-we-did-not-measure}.",
   "served": "The adapter was trained on 159 tracks from 41 releases § {#a-genre-not-a-composer}. The one listener preferred the untouched model, both times § {#the-short-version}. The article does not measure whether the untouched model is any good at this genre § {#what-we-did-not-measure}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.8090968779870309,
   "ttft_ms": 329,
   "tokens_in": 13206,
   "tokens_out": 73,
   "cached_tokens": 12864,
   "cites": [
    "a-genre-not-a-composer",
    "top",
    "what-we-did-not-measure"
   ],
   "gates": {
    "cites": [
     "a-genre-not-a-composer",
     "top",
     "what-we-did-not-measure"
    ],
    "cites_dropped": [],
    "cites_resolved": [
     "top"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "159",
    "41"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "a-genre-not-a-composer",
     "overlap": 0.5
    },
    {
     "i": 1,
     "cite": "top",
     "overlap": 0.714
    },
    {
     "i": 2,
     "cite": "what-we-did-not-measure",
     "overlap": 0.833
    }
   ],
   "cite_overlap_p50": 0.714,
   "id": "on-05",
   "kind": "on-page"
  },
  {
   "slug": "listen-for-yourself",
   "q": "how many renders are on the page, and what was done to their loudness?",
   "ok": true,
   "answer": "There are sixty-three players on the page, each playing a listening master of a raw render § {#how-to-listen}. The listening masters were created by applying one constant gain and nothing else, such as no limiter, no compression, no equalisation, or no trimming, to the raw renders § {#how-to-listen}. The gain applied was the smaller of two numbers: how far the clip sits from −16 LUFS and how far its true peak sits from a −1 dBTP ceiling § {#how-to-listen}. The article notes that the raw renders were never re-encoded, never trimmed, and never levelled after the fact § {#how-to-listen}.",
   "served": "There are sixty-three players on the page, each playing a listening master of a raw render § {#how-to-listen}. The listening masters were created by applying one constant gain and nothing else, such as no limiter, no compression, no equalisation, or no trimming, to the raw renders § {#how-to-listen}. The gain applied was the smaller of two numbers: how far the clip sits from −16 LUFS and how far its true peak sits from a −1 dBTP ceiling § {#how-to-listen}. The article notes that the raw renders were never re-encoded, never trimmed, and never levelled after the fact § {#how-to-listen}.",
   "partial": false,
   "sentences_kept": 4,
   "sentences_written": 4,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.193940664990805,
   "ttft_ms": 312,
   "tokens_in": 14463,
   "tokens_out": 143,
   "cached_tokens": 14112,
   "cites": [
    "how-to-listen"
   ],
   "gates": {
    "cites": [
     "how-to-listen"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "16"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "how-to-listen",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "how-to-listen",
     "overlap": 0.75
    },
    {
     "i": 2,
     "cite": "how-to-listen",
     "overlap": 1.0
    },
    {
     "i": 3,
     "cite": "how-to-listen",
     "overlap": 0.778
    }
   ],
   "cite_overlap_p50": 0.889,
   "id": "on-06",
   "kind": "on-page"
  },
  {
   "slug": "half-an-hour-with-dead-composers",
   "q": "how long did the Sousa and Bach adapters take to train?",
   "ok": true,
   "answer": "The Sousa adapter took 14 minutes 36 seconds to train, while the Bach adapter took 8 minutes 23 seconds § {#sousa-a-hundred-and-six-marches} § {#bach-the-pianist-who-freed-her-own-recordings}. The article notes that the training time for Sousa is the longest run in the story § {#sousa-a-hundred-and-six-marches}.",
   "served": "The Sousa adapter took 14 minutes 36 seconds to train, while the Bach adapter took 8 minutes 23 seconds § {#sousa-a-hundred-and-six-marches} § {#bach-the-pianist-who-freed-her-own-recordings}. The article notes that the training time for Sousa is the longest run in the story § {#sousa-a-hundred-and-six-marches}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.771129717992153,
   "ttft_ms": 245,
   "tokens_in": 5703,
   "tokens_out": 97,
   "cached_tokens": 5376,
   "cites": [
    "sousa-a-hundred-and-six-marches",
    "bach-the-pianist-who-freed-her-own-recordings"
   ],
   "gates": {
    "cites": [
     "sousa-a-hundred-and-six-marches",
     "bach-the-pianist-who-freed-her-own-recordings"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "14",
    "36",
    "8",
    "23"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "sousa-a-hundred-and-six-marches",
     "overlap": 0.545
    },
    {
     "i": 0,
     "cite": "bach-the-pianist-who-freed-her-own-recordings",
     "overlap": 0.455
    },
    {
     "i": 1,
     "cite": "sousa-a-hundred-and-six-marches",
     "overlap": 0.714
    }
   ],
   "cite_overlap_p50": 0.545,
   "id": "on-07",
   "kind": "on-page"
  },
  {
   "slug": "chopin-in-five-minutes",
   "q": "how many recordings were used, and how long did the training take by the trainer's clock?",
   "ok": true,
   "answer": "Nineteen recordings were used for training, and the process took 4 minutes 49 seconds by the trainer's own clock § {#five-minutes-of-training-honestly-accounted}. The article notes that it did not measure whether the tempo and key in the request were honored, nor did it perform a blinded listening test to see if the clips actually sound like Chopin § {#what-we-did-not-measure}.",
   "served": "Nineteen recordings were used for training, and the process took 4 minutes 49 seconds by the trainer's own clock § {#five-minutes-of-training-honestly-accounted}. The article notes that it did not measure whether the tempo and key in the request were honored, nor did it perform a blinded listening test to see if the clips actually sound like Chopin § {#what-we-did-not-measure}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.7147608060040511,
   "ttft_ms": 228,
   "tokens_in": 3843,
   "tokens_out": 91,
   "cached_tokens": 3488,
   "cites": [
    "five-minutes-of-training-honestly-accounted",
    "what-we-did-not-measure"
   ],
   "gates": {
    "cites": [
     "five-minutes-of-training-honestly-accounted",
     "what-we-did-not-measure"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "4",
    "49"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "five-minutes-of-training-honestly-accounted",
     "overlap": 0.833
    },
    {
     "i": 1,
     "cite": "what-we-did-not-measure",
     "overlap": 0.526
    }
   ],
   "cite_overlap_p50": 0.679,
   "id": "on-08",
   "kind": "on-page"
  },
  {
   "slug": "the-same-sixteen",
   "q": "what did glm-5.3-flash score on the tool bench, and what did the local models score?",
   "ok": true,
   "answer": "The glm-5.3-flash reference arm scored 16/19 — 84.2%, Wilson 95% interval [62.4%, 94.5%] on the tool bench § {#sixteen-of-nineteen}. Two local models, gemma4:12b and qwen3.6:27b, also landed on the exact same count of 16/19 § {#two-local-models-sixteen-days-earlier}. The article notes that the judge exam, assistant exam, decode speed, and filing cabinet could not honestly be read on the cloud path § {#the-ledger-of-what-did-not-read}.",
   "served": "The glm-5.3-flash reference arm scored 16/19 — 84.2%, Wilson 95% interval [62.4%, 94.5%] on the tool bench § {#sixteen-of-nineteen}. Two local models, gemma4:12b and qwen3.6:27b, also landed on the exact same count of 16/19 § {#two-local-models-sixteen-days-earlier}. The article notes that the judge exam, assistant exam, decode speed, and filing cabinet could not honestly be read on the cloud path § {#the-ledger-of-what-did-not-read}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.1636050789966248,
   "ttft_ms": 298,
   "tokens_in": 6553,
   "tokens_out": 151,
   "cached_tokens": 6496,
   "cites": [
    "sixteen-of-nineteen",
    "two-local-models-sixteen-days-earlier",
    "the-ledger-of-what-did-not-read"
   ],
   "gates": {
    "cites": [
     "sixteen-of-nineteen",
     "two-local-models-sixteen-days-earlier",
     "the-ledger-of-what-did-not-read"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "5.3",
    "16/19",
    "84.2",
    "95",
    "62.4",
    "94.5",
    "4:12",
    "3.6",
    "27",
    "16/19"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "sixteen-of-nineteen",
     "overlap": 0.846
    },
    {
     "i": 1,
     "cite": "two-local-models-sixteen-days-earlier",
     "overlap": 1.0
    },
    {
     "i": 2,
     "cite": "the-ledger-of-what-did-not-read",
     "overlap": 0.833
    }
   ],
   "cite_overlap_p50": 0.846,
   "id": "on-09",
   "kind": "on-page"
  },
  {
   "slug": "the-same-sixteen",
   "q": "which of these models is the best one to use for my own project?",
   "ok": true,
   "answer": "The article does not provide a recommendation on which model is best to use for a project § {#a-different-kind-of-row}.",
   "served": "This page doesn't say. The nearest it gets is § {#a-different-kind-of-row}. Three New Voices at the Narrator's Chair covers it more directly.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "a-different-kind-of-row",
   "seconds": 0.4981942030135542,
   "ttft_ms": 276,
   "tokens_in": 6545,
   "tokens_out": 30,
   "cached_tokens": 6208,
   "cites": [
    "a-different-kind-of-row"
   ],
   "gates": {
    "cites": [
     "a-different-kind-of-row"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "a-different-kind-of-row",
     "overlap": 0.167
    }
   ],
   "cite_overlap_p50": 0.167,
   "id": "off-20",
   "kind": "off-page"
  },
  {
   "slug": "two-hours-on-battery",
   "q": "what speed did the mini pc hold on battery, and for how long?",
   "ok": true,
   "answer": "The mini PC held a speed of ~12 tokens/second on battery for about two hours § {#two-hours-at-12-tok-s-the-test-that-named-the-page}. Specifically, the four answers completed on battery averaged 11.87 tok/s § {#two-hours-at-12-tok-s-the-test-that-named-the-page}. The article notes that sustained thermals past the measured window and non-Q4 quantizations on CPU were not measured § {#what-we-did-not-measure}.",
   "served": "The mini PC held a speed of ~12 tokens/second on battery for about two hours § {#two-hours-at-12-tok-s-the-test-that-named-the-page}. Specifically, the four answers completed on battery averaged 11.87 tok/s § {#two-hours-at-12-tok-s-the-test-that-named-the-page}. The article notes that sustained thermals past the measured window and non-Q4 quantizations on CPU were not measured § {#what-we-did-not-measure}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.0923880790360272,
   "ttft_ms": 281,
   "tokens_in": 11094,
   "tokens_out": 127,
   "cached_tokens": 10752,
   "cites": [
    "two-hours-at-12-tok-s-the-test-that-named-the-page",
    "what-we-did-not-measure"
   ],
   "gates": {
    "cites": [
     "two-hours-at-12-tok-s-the-test-that-named-the-page",
     "what-we-did-not-measure"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "12",
    "11.87",
    "4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "two-hours-at-12-tok-s-the-test-that-named-the-page",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "two-hours-at-12-tok-s-the-test-that-named-the-page",
     "overlap": 0.875
    },
    {
     "i": 2,
     "cite": "what-we-did-not-measure",
     "overlap": 0.889
    }
   ],
   "cite_overlap_p50": 0.889,
   "id": "on-10",
   "kind": "on-page"
  },
  {
   "slug": "two-hours-on-battery",
   "q": "what did this cost in electricity at my own utility's rate?",
   "ok": true,
   "answer": "The article does not state the cost of electricity at the reader's utility rate § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.",
   "served": "This page doesn't say. The nearest it gets is § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "two-hours-at-12-tok-s-the-test-that-named-the-page",
   "seconds": 0.6024302490404807,
   "ttft_ms": 282,
   "tokens_in": 11093,
   "tokens_out": 44,
   "cached_tokens": 11040,
   "cites": [
    "two-hours-at-12-tok-s-the-test-that-named-the-page"
   ],
   "gates": {
    "cites": [
     "two-hours-at-12-tok-s-the-test-that-named-the-page"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "two-hours-at-12-tok-s-the-test-that-named-the-page",
     "overlap": 0.0
    }
   ],
   "cite_overlap_p50": 0.0,
   "id": "off-05",
   "kind": "off-page"
  },
  {
   "slug": "the-instrument-travels",
   "q": "when the frozen exam moved to the smaller card, where did the ranked model land?",
   "ok": true,
   "answer": "The ranked model, qwen3.6:27b, cleared both judge floors and was ranked again § {#the-chair-and-who-gets-to-sit-in-it}. It achieved a kill-recall of 11 of 12 and a preservation of 8 of 9 § {#the-standings}. One preservation item was unscorable rather than lost, and the missed item moved from c1-k-bez-c1 to c1-k-bez-h1 § {#what-the-battery-was-for-the-instrument-travels}.",
   "served": "The ranked model, qwen3.6:27b, cleared both judge floors and was ranked again § {#the-chair-and-who-gets-to-sit-in-it}. It achieved a kill-recall of 11 of 12 and a preservation of 8 of 9 § {#the-standings}. One preservation item was unscorable rather than lost, and the missed item moved from c1-k-bez-c1 to c1-k-bez-h1 § {#what-the-battery-was-for-the-instrument-travels}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.0140804630354978,
   "ttft_ms": 264,
   "tokens_in": 8777,
   "tokens_out": 127,
   "cached_tokens": 8448,
   "cites": [
    "the-chair-and-who-gets-to-sit-in-it",
    "the-standings",
    "what-the-battery-was-for-the-instrument-travels"
   ],
   "gates": {
    "cites": [
     "the-chair-and-who-gets-to-sit-in-it",
     "the-standings",
     "what-the-battery-was-for-the-instrument-travels"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3.6",
    "27",
    "11",
    "12",
    "8",
    "9"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-chair-and-who-gets-to-sit-in-it",
     "overlap": 0.222
    },
    {
     "i": 1,
     "cite": "the-standings",
     "overlap": 0.8
    },
    {
     "i": 2,
     "cite": "what-the-battery-was-for-the-instrument-travels",
     "overlap": 0.9
    }
   ],
   "cite_overlap_p50": 0.8,
   "id": "on-11",
   "kind": "on-page"
  },
  {
   "slug": "nine-worlds-one-dog",
   "q": "what stays the same across the nine paintings?",
   "ok": true,
   "answer": "The founder's dog remains the same across all nine paintings, specifically maintaining the same dog, same curl, and same tucked paws while taking the same nap under the same tree § {#top}. The dog is described as a large black Portuguese Water Dog with one bright white chest patch §. The article does not mention anything that was left out, moved, or not measured.",
   "served": "The founder's dog remains the same across all nine paintings, specifically maintaining the same dog, same curl, and same tucked paws while taking the same nap under the same tree § {#top}. The dog is described as a large black Portuguese Water Dog with one bright white chest patch §. The article does not mention anything that was left out, moved, or not measured.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.5977115749847144,
   "ttft_ms": 188,
   "tokens_in": 2058,
   "tokens_out": 76,
   "cached_tokens": 1728,
   "cites": [
    "top"
   ],
   "gates": {
    "cites": [
     "top"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "top",
     "overlap": 0.471
    }
   ],
   "cite_overlap_p50": 0.471,
   "id": "on-12",
   "kind": "on-page"
  },
  {
   "slug": "nine-worlds-one-dog",
   "q": "how many other readers have asked this same question?",
   "ok": true,
   "answer": "The article does not answer how many other readers have asked this same question § {#for-the-technically-curious}.",
   "served": "This page doesn't say. The nearest it gets is § {#for-the-technically-curious}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "for-the-technically-curious",
   "seconds": 0.3526411399943754,
   "ttft_ms": 192,
   "tokens_in": 2059,
   "tokens_out": 27,
   "cached_tokens": 2016,
   "cites": [
    "for-the-technically-curious"
   ],
   "gates": {
    "cites": [
     "for-the-technically-curious"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "for-the-technically-curious",
     "overlap": 0.286
    }
   ],
   "cite_overlap_p50": 0.286,
   "id": "off-17",
   "kind": "off-page"
  },
  {
   "slug": "what-150-watts-buys",
   "q": "what did the 450-watt cap cost the dense model, and what did it buy back?",
   "ok": true,
   "answer": "The 600 to 450 W cap cost the dense model 2.0% of throughput and bought back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. This specific result was measured at concurrency 16 where throughput moved from 94.6 to 92.7 tok/s per stream § {#the-answer-in-one-paragraph}. The article notes that it did not measure the cost for long-context or prefill-heavy workloads § {#what-this-page-does-not-say}.",
   "served": "The 600 to 450 W cap cost the dense model 2.0% of throughput and bought back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. This specific result was measured at concurrency 16 where throughput moved from 94.6 to 92.7 tok/s per stream § {#the-answer-in-one-paragraph}. The article notes that it did not measure the cost for long-context or prefill-heavy workloads § {#what-this-page-does-not-say}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.071658712986391,
   "ttft_ms": 278,
   "tokens_in": 7269,
   "tokens_out": 136,
   "cached_tokens": 6912,
   "cites": [
    "the-answer-in-one-paragraph",
    "what-this-page-does-not-say"
   ],
   "gates": {
    "cites": [
     "the-answer-in-one-paragraph",
     "what-this-page-does-not-say"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "600",
    "450",
    "2.0",
    "138",
    "11",
    "28",
    "16",
    "94.6",
    "92.7"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-answer-in-one-paragraph",
     "overlap": 0.8
    },
    {
     "i": 1,
     "cite": "the-answer-in-one-paragraph",
     "overlap": 0.75
    },
    {
     "i": 2,
     "cite": "what-this-page-does-not-say",
     "overlap": 0.5
    }
   ],
   "cite_overlap_p50": 0.75,
   "id": "on-13",
   "kind": "on-page"
  },
  {
   "slug": "what-150-watts-buys",
   "q": "what does a large cloud provider charge for the same work?",
   "ok": true,
   "answer": "The article does not say what a large cloud provider charges for the same work § {#the-moment-this-page-is-about}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-moment-this-page-is-about}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-moment-this-page-is-about",
   "seconds": 0.49220035900361836,
   "ttft_ms": 284,
   "tokens_in": 7259,
   "tokens_out": 30,
   "cached_tokens": 7232,
   "cites": [
    "the-moment-this-page-is-about"
   ],
   "gates": {
    "cites": [
     "the-moment-this-page-is-about"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-moment-this-page-is-about",
     "overlap": 0.143
    }
   ],
   "cite_overlap_p50": 0.143,
   "id": "off-01",
   "kind": "off-page"
  },
  {
   "slug": "how-the-beat-lab-works",
   "q": "where is the sound made, and how long does a typical wish take?",
   "ok": true,
   "answer": "Every sound in the Beat Lab is synthesised by the user's own browser § {#the-sound-is-made-on-your-device}. A typical wish takes about 4 s § {#what-happens-when-you-ask-the-genie}. The article does not mention what was left out, moved, or not measured in relation to these specific details.",
   "served": "Every sound in the Beat Lab is synthesised by the user's own browser § {#the-sound-is-made-on-your-device}. A typical wish takes about 4 s § {#what-happens-when-you-ask-the-genie}. The article does not mention what was left out, moved, or not measured in relation to these specific details.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.3921362760011107,
   "ttft_ms": 517,
   "tokens_in": 31469,
   "tokens_out": 81,
   "cached_tokens": 31136,
   "cites": [
    "the-sound-is-made-on-your-device",
    "what-happens-when-you-ask-the-genie"
   ],
   "gates": {
    "cites": [
     "the-sound-is-made-on-your-device",
     "what-happens-when-you-ask-the-genie"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-sound-is-made-on-your-device",
     "overlap": 0.875
    },
    {
     "i": 1,
     "cite": "what-happens-when-you-ask-the-genie",
     "overlap": 1.0
    }
   ],
   "cite_overlap_p50": 0.938,
   "id": "on-14",
   "kind": "on-page"
  },
  {
   "slug": "how-the-beat-lab-works",
   "q": "what phone number reaches support?",
   "ok": true,
   "answer": "The article does not provide a phone number to reach support § {#what-it-is}. The closest information regarding communication is the small ✎ button used to send feedback to the humans in the workshop § {#what-the-lab-does-with-what-you-give-it}.",
   "served": "This page doesn't say. The nearest it gets is § {#what-it-is}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "what-it-is",
   "seconds": 1.1879500659997575,
   "ttft_ms": 534,
   "tokens_in": 31460,
   "tokens_out": 61,
   "cached_tokens": 31424,
   "cites": [
    "what-it-is",
    "what-the-lab-does-with-what-you-give-it"
   ],
   "gates": {
    "cites": [
     "what-it-is",
     "what-the-lab-does-with-what-you-give-it"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "what-it-is",
     "overlap": 0.0
    },
    {
     "i": 1,
     "cite": "what-the-lab-does-with-what-you-give-it",
     "overlap": 0.545
    }
   ],
   "cite_overlap_p50": 0.273,
   "id": "off-18",
   "kind": "off-page"
  },
  {
   "slug": "the-typist-and-the-developer",
   "q": "how long did the developer take to develop one picture?",
   "ok": true,
   "answer": "The developer developed a picture in 1.54 seconds § {#the-developer}. When the typist was streaming tokens at the same time, the developer took 1.82 seconds per sketch § {#one-card-both-jobs-at-once}. The article notes that it did not instrument how much traffic was present during the run § {#what-we-did-not-measure-said-out-loud}.",
   "served": "The developer developed a picture in 1.54 seconds § {#the-developer}. When the typist was streaming tokens at the same time, the developer took 1.82 seconds per sketch § {#one-card-both-jobs-at-once}. The article notes that it did not instrument how much traffic was present during the run § {#what-we-did-not-measure-said-out-loud}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.7822442160104401,
   "ttft_ms": 264,
   "tokens_in": 5536,
   "tokens_out": 90,
   "cached_tokens": 5216,
   "cites": [
    "the-developer",
    "one-card-both-jobs-at-once",
    "what-we-did-not-measure-said-out-loud"
   ],
   "gates": {
    "cites": [
     "the-developer",
     "one-card-both-jobs-at-once",
     "what-we-did-not-measure-said-out-loud"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "1.54",
    "1.82"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-developer",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "one-card-both-jobs-at-once",
     "overlap": 0.909
    },
    {
     "i": 2,
     "cite": "what-we-did-not-measure-said-out-loud",
     "overlap": 0.714
    }
   ],
   "cite_overlap_p50": 0.909,
   "id": "on-15",
   "kind": "on-page"
  },
  {
   "slug": "the-typist-and-the-developer",
   "q": "what is this workshop's annual revenue?",
   "ok": true,
   "answer": "The article does not state the workshop's annual revenue § {#the-typist}. The closest section to this information is the introduction § {#the-typist}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-typist}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-typist",
   "seconds": 0.49201483197975904,
   "ttft_ms": 267,
   "tokens_in": 5534,
   "tokens_out": 35,
   "cached_tokens": 5504,
   "cites": [
    "the-typist"
   ],
   "gates": {
    "cites": [
     "the-typist"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-typist",
     "overlap": 0.0
    },
    {
     "i": 1,
     "cite": "the-typist",
     "overlap": 0.0
    }
   ],
   "cite_overlap_p50": 0.0,
   "id": "off-12",
   "kind": "off-page"
  },
  {
   "slug": "a-rig-your-friend-already-owns",
   "q": "how much faster was the workstation card than the 3090 on the game's own art?",
   "ok": true,
   "answer": "The article does not provide a single speed comparison for the workstation card against the 3090 on the game's own art, instead reporting median seconds per render for various models § {#the-table-that-answers-the-question}. For the game's sketch artist, FLUX.2 klein-4B, the 96G card was 3.4× faster than the 3090 § {#the-table-that-answers-the-question}. The text notes that the study did not test 8–12 GB cards § {#three-findings-we-didnt-order}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-table-that-answers-the-question}. Fifty-Seven Milliseconds: What a Diffusion Step Actually Buys covers it more directly.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-table-that-answers-the-question",
   "seconds": 0.9954710129532032,
   "ttft_ms": 303,
   "tokens_in": 4777,
   "tokens_out": 132,
   "cached_tokens": 4448,
   "cites": [
    "the-table-that-answers-the-question",
    "three-findings-we-didnt-order"
   ],
   "gates": {
    "cites": [
     "the-table-that-answers-the-question",
     "three-findings-we-didnt-order"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3090",
    "2",
    "4",
    "96",
    "3.4",
    "3090",
    "8-12"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-table-that-answers-the-question",
     "overlap": 0.421
    },
    {
     "i": 1,
     "cite": "the-table-that-answers-the-question",
     "overlap": 0.8
    },
    {
     "i": 2,
     "cite": "three-findings-we-didnt-order",
     "overlap": 0.571
    }
   ],
   "cite_overlap_p50": 0.571,
   "id": "on-16",
   "kind": "on-page"
  },
  {
   "slug": "a-rig-your-friend-already-owns",
   "q": "what does one of these cards cost in my country today?",
   "ok": true,
   "answer": "The article does not answer what any of these cards cost in the reader's country today § {#the-moment-this-page-is-about}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-moment-this-page-is-about}. Three New Voices at the Narrator's Chair covers it more directly.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-moment-this-page-is-about",
   "seconds": 0.47618556895758957,
   "ttft_ms": 259,
   "tokens_in": 4767,
   "tokens_out": 33,
   "cached_tokens": 4736,
   "cites": [
    "the-moment-this-page-is-about"
   ],
   "gates": {
    "cites": [
     "the-moment-this-page-is-about"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-moment-this-page-is-about",
     "overlap": 0.167
    }
   ],
   "cite_overlap_p50": 0.167,
   "id": "off-07",
   "kind": "off-page"
  },
  {
   "slug": "how-a-vision-model-sees",
   "q": "how many tokens does an 896 px picture become, and how long does its prefill take?",
   "ok": true,
   "answer": "An 896 px picture becomes 199 tokens and its prefill takes 184 ms § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}. This measurement was recorded on the seat the cove ships, which is the minicpm-v4.5 model § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}.",
   "served": "An 896 px picture becomes 199 tokens and its prefill takes 184 ms § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}. This measurement was recorded on the seat the cove ships, which is the minicpm-v4.5 model § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9701198859838769,
   "ttft_ms": 318,
   "tokens_in": 10311,
   "tokens_out": 107,
   "cached_tokens": 9984,
   "cites": [
    "finding-one-a-picture-is-199-tokens-at-896-px-and-the"
   ],
   "gates": {
    "cites": [
     "finding-one-a-picture-is-199-tokens-at-896-px-and-the"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "896",
    "199",
    "184",
    "4.5"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "finding-one-a-picture-is-199-tokens-at-896-px-and-the",
     "overlap": 0.8
    },
    {
     "i": 1,
     "cite": "finding-one-a-picture-is-199-tokens-at-896-px-and-the",
     "overlap": 0.714
    }
   ],
   "cite_overlap_p50": 0.757,
   "id": "on-17",
   "kind": "on-page"
  },
  {
   "slug": "fifty-seven-milliseconds",
   "q": "which painter is the fastest cell, and at what time?",
   "ok": true,
   "answer": "The distilled painter is the fastest cell in the second run, recording a time of 0.62 s at 4 steps § {#finding-four-the-argument-with-our-own-settings-and-what-it}. The article notes that the published pages serve compressed derivatives which add a small floor to every number § {#how-to-check-our-work-and-see-it-live}.",
   "served": "The distilled painter is the fastest cell in the second run, recording a time of 0.62 s at 4 steps § {#finding-four-the-argument-with-our-own-settings-and-what-it}. The article notes that the published pages serve compressed derivatives which add a small floor to every number § {#how-to-check-our-work-and-see-it-live}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.7740106459823437,
   "ttft_ms": 265,
   "tokens_in": 5434,
   "tokens_out": 89,
   "cached_tokens": 5088,
   "cites": [
    "finding-four-the-argument-with-our-own-settings-and-what-it",
    "how-to-check-our-work-and-see-it-live"
   ],
   "gates": {
    "cites": [
     "finding-four-the-argument-with-our-own-settings-and-what-it",
     "how-to-check-our-work-and-see-it-live"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "0.62",
    "4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "finding-four-the-argument-with-our-own-settings-and-what-it",
     "overlap": 0.9
    },
    {
     "i": 1,
     "cite": "how-to-check-our-work-and-see-it-live",
     "overlap": 0.909
    }
   ],
   "cite_overlap_p50": 0.905,
   "id": "on-18",
   "kind": "on-page"
  },
  {
   "slug": "fifty-seven-milliseconds",
   "q": "what was the weather like on the day this was measured?",
   "ok": true,
   "answer": "The article does not say what the weather was like on the day of the measurement § {#what-a-step-is-in-one-paragraph}.",
   "served": "This page doesn't say. The nearest it gets is § {#what-a-step-is-in-one-paragraph}. What 150 Watts Buys covers it more directly.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "what-a-step-is-in-one-paragraph",
   "seconds": 0.48090491798939183,
   "ttft_ms": 270,
   "tokens_in": 5434,
   "tokens_out": 33,
   "cached_tokens": 5408,
   "cites": [
    "what-a-step-is-in-one-paragraph"
   ],
   "gates": {
    "cites": [
     "what-a-step-is-in-one-paragraph"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "what-a-step-is-in-one-paragraph",
     "overlap": 0.2
    }
   ],
   "cite_overlap_p50": 0.2,
   "id": "off-09",
   "kind": "off-page"
  },
  {
   "slug": "the-dog-the-dice-and-the-painter",
   "q": "how big is the file the whole world is written in?",
   "ok": true,
   "answer": "The world is written in a single YAML file consisting of 16,705 lines § {#the-world-is-a-file}. This file contains six regions, forty NPCs, fifty-nine quests, and three kinds of adoptable pet § {#the-world-is-a-file}. The article does not mention the file's size in bytes, though it notes that two copies are maintained and must be byte-identical § {#the-world-is-a-file}.",
   "served": "The world is written in a single YAML file consisting of 16,705 lines § {#the-world-is-a-file}. This file contains six regions, forty NPCs, fifty-nine quests, and three kinds of adoptable pet § {#the-world-is-a-file}. The article does not mention the file's size in bytes, though it notes that two copies are maintained and must be byte-identical § {#the-world-is-a-file}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.8249180749990046,
   "ttft_ms": 255,
   "tokens_in": 6116,
   "tokens_out": 104,
   "cached_tokens": 5792,
   "cites": [
    "the-world-is-a-file"
   ],
   "gates": {
    "cites": [
     "the-world-is-a-file"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "16,705"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-world-is-a-file",
     "overlap": 0.778
    },
    {
     "i": 1,
     "cite": "the-world-is-a-file",
     "overlap": 0.917
    },
    {
     "i": 2,
     "cite": "the-world-is-a-file",
     "overlap": 0.273
    }
   ],
   "cite_overlap_p50": 0.778,
   "id": "on-19",
   "kind": "on-page"
  },
  {
   "slug": "where-new-knowledge-comes-from",
   "q": "what are the two engines the page names for where new knowledge comes from?",
   "ok": true,
   "answer": "The two engines are present in the data, unmined, and implied by the rules, unvisited § {#two-kinds-of-there-all-along}. The first engine involves reading patterns that were already in archives, such as co-evolution fingerprints or molecular shapes that kill bacteria § {#the-first-engine-the-archive-nobody-had-read}. The second engine involves walking regions of rule-space that no row of data contains, such as a planet's position in 1631 § {#the-second-engine-the-rooms-the-rules-imply}. Structural biologists noted that these models left out how proteins pair up, how they move, and what one mutation does § {#the-first-engine-the-archive-nobody-had-read}.",
   "served": "The two engines are present in the data, unmined, and implied by the rules, unvisited § {#two-kinds-of-there-all-along}. The first engine involves reading patterns that were already in archives, such as co-evolution fingerprints or molecular shapes that kill bacteria § {#the-first-engine-the-archive-nobody-had-read}. The second engine involves walking regions of rule-space that no row of data contains, such as a planet's position in 1631 § {#the-second-engine-the-rooms-the-rules-imply}. Structural biologists noted that these models left out how proteins pair up, how they move, and what one mutation does § {#the-first-engine-the-archive-nobody-had-read}.",
   "partial": false,
   "sentences_kept": 4,
   "sentences_written": 4,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.147767507005483,
   "ttft_ms": 242,
   "tokens_in": 5472,
   "tokens_out": 167,
   "cached_tokens": 5152,
   "cites": [
    "two-kinds-of-there-all-along",
    "the-first-engine-the-archive-nobody-had-read",
    "the-second-engine-the-rooms-the-rules-imply"
   ],
   "gates": {
    "cites": [
     "two-kinds-of-there-all-along",
     "the-first-engine-the-archive-nobody-had-read",
     "the-second-engine-the-rooms-the-rules-imply"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "1631"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "two-kinds-of-there-all-along",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "the-first-engine-the-archive-nobody-had-read",
     "overlap": 0.357
    },
    {
     "i": 2,
     "cite": "the-second-engine-the-rooms-the-rules-imply",
     "overlap": 0.462
    },
    {
     "i": 3,
     "cite": "the-first-engine-the-archive-nobody-had-read",
     "overlap": 0.308
    }
   ],
   "cite_overlap_p50": 0.409,
   "id": "on-20",
   "kind": "on-page"
  },
  {
   "slug": "compression-is-the-objective",
   "q": "what does the page say a language model is, and what prize does it point to?",
   "ok": true,
   "answer": "A language model is a compression of its corpus § {#the-punchline}. The article points to the Hutter Prize, which is a competition where a frontier model cannot enter because it charges for everything, including the decompressor bytes § {#the-punchline}. The text notes that the scoreboard for the 2023 paper mentioned does not charge for the model's own weights § {#the-punchline}.",
   "served": "A language model is a compression of its corpus § {#the-punchline}. The article points to the Hutter Prize, which is a competition where a frontier model cannot enter because it charges for everything, including the decompressor bytes § {#the-punchline}. The text notes that the scoreboard for the 2023 paper mentioned does not charge for the model's own weights § {#the-punchline}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.7601799020194449,
   "ttft_ms": 265,
   "tokens_in": 5448,
   "tokens_out": 87,
   "cached_tokens": 5120,
   "cites": [
    "the-punchline"
   ],
   "gates": {
    "cites": [
     "the-punchline"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-punchline",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "the-punchline",
     "overlap": 0.429
    },
    {
     "i": 2,
     "cite": "the-punchline",
     "overlap": 0.3
    }
   ],
   "cite_overlap_p50": 0.429,
   "id": "on-21",
   "kind": "on-page"
  },
  {
   "slug": "compression-is-the-objective",
   "q": "how would these numbers change on windows instead?",
   "ok": true,
   "answer": "The article does not state how these numbers would change on windows § {#what-we-can-show-you}.",
   "served": "This page doesn't say. The nearest it gets is § {#what-we-can-show-you}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "what-we-can-show-you",
   "seconds": 0.4349605989991687,
   "ttft_ms": 271,
   "tokens_in": 5439,
   "tokens_out": 25,
   "cached_tokens": 5408,
   "cites": [
    "what-we-can-show-you"
   ],
   "gates": {
    "cites": [
     "what-we-can-show-you"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "what-we-can-show-you",
     "overlap": 0.5
    }
   ],
   "cite_overlap_p50": 0.5,
   "id": "off-13",
   "kind": "off-page"
  },
  {
   "slug": "the-free-speed-wasnt-free",
   "q": "what was the production median before the change, and what caused the speed-up?",
   "ok": true,
   "answer": "The production median was 138.6 tok/s over 1,982 live rulings § {#the-day-the-box-got-faster}. The speed-up was caused by an ollama commit that changed the default repeat_penalty from 1.1 to 1.0, which removed a penalties stage that had been running on every token § {#the-two-line-commit}. The article notes that the quality half of this change remains unmeasured § {#the-part-that-isnt-about-speed}.",
   "served": "The production median was 138.6 tok/s over 1,982 live rulings § {#the-day-the-box-got-faster}. The speed-up was caused by an ollama commit that changed the default repeat_penalty from 1.1 to 1.0, which removed a penalties stage that had been running on every token § {#the-two-line-commit}. The article notes that the quality half of this change remains unmeasured § {#the-part-that-isnt-about-speed}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9244348270003684,
   "ttft_ms": 260,
   "tokens_in": 7529,
   "tokens_out": 116,
   "cached_tokens": 7200,
   "cites": [
    "the-day-the-box-got-faster",
    "the-two-line-commit",
    "the-part-that-isnt-about-speed"
   ],
   "gates": {
    "cites": [
     "the-day-the-box-got-faster",
     "the-two-line-commit",
     "the-part-that-isnt-about-speed"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "138.6",
    "1,982",
    "1.1",
    "1.0"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-day-the-box-got-faster",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "the-two-line-commit",
     "overlap": 0.625
    },
    {
     "i": 2,
     "cite": "the-part-that-isnt-about-speed",
     "overlap": 0.667
    }
   ],
   "cite_overlap_p50": 0.667,
   "id": "on-22",
   "kind": "on-page"
  },
  {
   "slug": "the-compressed-photograph",
   "q": "how much slower was the uncompressed original than the compressed build?",
   "ok": true,
   "answer": "The uncompressed original was 3.4× slower than the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. The uncompressed original's speed was 58.1 tok/s compared to the trained-4-bit build's 134.4 tok/s § {#the-same-question-down-the-whole-ladder}. The article notes that it does not measure perplexity § {#what-this-page-does-not-say}.",
   "served": "The uncompressed original was 3.4× slower than the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. The uncompressed original's speed was 58.1 tok/s compared to the trained-4-bit build's 134.4 tok/s § {#the-same-question-down-the-whole-ladder}. The article notes that it does not measure perplexity § {#what-this-page-does-not-say}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9173287490266375,
   "ttft_ms": 268,
   "tokens_in": 8637,
   "tokens_out": 112,
   "cached_tokens": 8288,
   "cites": [
    "the-same-question-down-the-whole-ladder",
    "what-this-page-does-not-say"
   ],
   "gates": {
    "cites": [
     "the-same-question-down-the-whole-ladder",
     "what-this-page-does-not-say"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3.4",
    "4",
    "58.1",
    "4",
    "134.4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-same-question-down-the-whole-ladder",
     "overlap": 0.833
    },
    {
     "i": 1,
     "cite": "the-same-question-down-the-whole-ladder",
     "overlap": 0.889
    },
    {
     "i": 2,
     "cite": "what-this-page-does-not-say",
     "overlap": 0.667
    }
   ],
   "cite_overlap_p50": 0.833,
   "id": "on-23",
   "kind": "on-page"
  },
  {
   "slug": "three-at-the-table",
   "q": "what is the true active share for the live seat, and what does the page call the two numbers in a model name?",
   "ok": true,
   "answer": "The true active share for the live seat is 14.4% of the model's bytes § {#the-payroll-and-the-meeting}. The two numbers in a model name are called the payroll and the meeting § {#the-tag-with-two-numbers}. The article notes that it does not measure the latency trade-off of streaming experts from system RAM § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}.",
   "served": "The true active share for the live seat is 14.4% of the model's bytes § {#the-payroll-and-the-meeting}. The two numbers in a model name are called the payroll and the meeting § {#the-tag-with-two-numbers}. The article notes that it does not measure the latency trade-off of streaming experts from system RAM § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.8999992659664713,
   "ttft_ms": 284,
   "tokens_in": 7685,
   "tokens_out": 104,
   "cached_tokens": 7328,
   "cites": [
    "the-payroll-and-the-meeting",
    "the-tag-with-two-numbers",
    "the-part-nobody-warns-you-about-the-whole-payroll-needs-an"
   ],
   "gates": {
    "cites": [
     "the-payroll-and-the-meeting",
     "the-tag-with-two-numbers",
     "the-part-nobody-warns-you-about-the-whole-payroll-needs-an"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "14.4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-payroll-and-the-meeting",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "the-tag-with-two-numbers",
     "overlap": 0.714
    },
    {
     "i": 2,
     "cite": "the-part-nobody-warns-you-about-the-whole-payroll-needs-an",
     "overlap": 0.5
    }
   ],
   "cite_overlap_p50": 0.714,
   "id": "on-24",
   "kind": "on-page"
  },
  {
   "slug": "three-at-the-table",
   "q": "what would this measurement look like at twice the batch size?",
   "ok": true,
   "answer": "The article does not state what the measurement would look like at twice the batch size § {#measured-on-our-own-machines}.",
   "served": "This page doesn't say. The nearest it gets is § {#measured-on-our-own-machines}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "measured-on-our-own-machines",
   "seconds": 0.4886340910452418,
   "ttft_ms": 291,
   "tokens_in": 7672,
   "tokens_out": 29,
   "cached_tokens": 7648,
   "cites": [
    "measured-on-our-own-machines"
   ],
   "gates": {
    "cites": [
     "measured-on-our-own-machines"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "measured-on-our-own-machines",
     "overlap": 0.286
    }
   ],
   "cite_overlap_p50": 0.286,
   "id": "off-19",
   "kind": "off-page"
  },
  {
   "slug": "reading-is-fast",
   "q": "what was the median reading speed, and why is reading faster than writing?",
   "ok": true,
   "answer": "The median reading speed was 5,415 tokens/s § {#a-measurement-from-our-own-card}. Reading is faster because it is parallel, as the model can process all tokens in a prompt at the same time since the text already exists § {#reading-is-a-group-photo}. In contrast, writing is serial because the model must choose tokens one at a time as the future of the sentence does not yet exist § {#writing-is-one-at-a-time}.",
   "served": "The median reading speed was 5,415 tokens/s § {#a-measurement-from-our-own-card}. Reading is faster because it is parallel, as the model can process all tokens in a prompt at the same time since the text already exists § {#reading-is-a-group-photo}. In contrast, writing is serial because the model must choose tokens one at a time as the future of the sentence does not yet exist § {#writing-is-one-at-a-time}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.8747934059938416,
   "ttft_ms": 262,
   "tokens_in": 5557,
   "tokens_out": 108,
   "cached_tokens": 5216,
   "cites": [
    "a-measurement-from-our-own-card",
    "reading-is-a-group-photo",
    "writing-is-one-at-a-time"
   ],
   "gates": {
    "cites": [
     "a-measurement-from-our-own-card",
     "reading-is-a-group-photo",
     "writing-is-one-at-a-time"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "5,415"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "a-measurement-from-our-own-card",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "reading-is-a-group-photo",
     "overlap": 0.643
    },
    {
     "i": 2,
     "cite": "writing-is-one-at-a-time",
     "overlap": 0.786
    }
   ],
   "cite_overlap_p50": 0.786,
   "id": "on-25",
   "kind": "on-page"
  },
  {
   "slug": "reading-is-fast",
   "q": "who won the football world cup in 2022?",
   "ok": true,
   "answer": "The article does not answer this question, though the section § {#the-mystery-stated-honestly} is the closest to discussing general topics.",
   "served": "This page doesn't say. The nearest it gets is § {#the-mystery-stated-honestly}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-mystery-stated-honestly",
   "seconds": 0.47027795400936157,
   "ttft_ms": 316,
   "tokens_in": 5555,
   "tokens_out": 31,
   "cached_tokens": 5504,
   "cites": [
    "the-mystery-stated-honestly"
   ],
   "gates": {
    "cites": [
     "the-mystery-stated-honestly"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-mystery-stated-honestly",
     "overlap": 0.25
    }
   ],
   "cite_overlap_p50": 0.25,
   "id": "off-06",
   "kind": "off-page"
  },
  {
   "slug": "three-librarians",
   "q": "how many dimensions does the embedder's map have, and what does the third librarian do?",
   "ok": true,
   "answer": "The embedder's map has 768 directions § {#the-second-librarian-searches-by-meaning}. The third librarian works only the aisle of the specific game being asked about by picking up the edition's own rulebook and any matched correction documents § {#the-third-librarian-never-left-your-aisle}. The article does not mention what was left out, moved, or not measured regarding the embedder or the third librarian § {#the-nerd-shelf-the-numbers-from-the-shipped-configuration}.",
   "served": "The embedder's map has 768 directions § {#the-second-librarian-searches-by-meaning}. The third librarian works only the aisle of the specific game being asked about by picking up the edition's own rulebook and any matched correction documents § {#the-third-librarian-never-left-your-aisle}. The article does not mention what was left out, moved, or not measured regarding the embedder or the third librarian § {#the-nerd-shelf-the-numbers-from-the-shipped-configuration}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.925148531969171,
   "ttft_ms": 253,
   "tokens_in": 5913,
   "tokens_out": 121,
   "cached_tokens": 5568,
   "cites": [
    "the-second-librarian-searches-by-meaning",
    "the-third-librarian-never-left-your-aisle",
    "the-nerd-shelf-the-numbers-from-the-shipped-configuration"
   ],
   "gates": {
    "cites": [
     "the-second-librarian-searches-by-meaning",
     "the-third-librarian-never-left-your-aisle",
     "the-nerd-shelf-the-numbers-from-the-shipped-configuration"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "768"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-second-librarian-searches-by-meaning",
     "overlap": 0.75
    },
    {
     "i": 1,
     "cite": "the-third-librarian-never-left-your-aisle",
     "overlap": 0.765
    },
    {
     "i": 2,
     "cite": "the-nerd-shelf-the-numbers-from-the-shipped-configuration",
     "overlap": 0.111
    }
   ],
   "cite_overlap_p50": 0.75,
   "id": "on-26",
   "kind": "on-page"
  },
  {
   "slug": "the-new-kid",
   "q": "which seat did the new model pass, and which floor did it miss?",
   "ok": true,
   "answer": "The qwen3.8:27b model passed the classifier seat, clearing all five pre-registered gates § {#the-classifier-seat-five-gates-all-pass-faster}, but it failed the judge seat by missing the preservation floor of 13 with a result of 11 of 16 § {#the-judge-seat-and-the-floor-it-missed}. The article notes that no baseline was scored for the classifier seat and that the judge seat's publication remains unruled § {#the-classifier-seat-five-gates-all-pass-faster} § {#the-judge-seat-and-the-floor-it-missed}.",
   "served": "The qwen3.8:27b model passed the classifier seat, clearing all five pre-registered gates § {#the-classifier-seat-five-gates-all-pass-faster}, but it failed the judge seat by missing the preservation floor of 13 with a result of 11 of 16 § {#the-judge-seat-and-the-floor-it-missed}. The article notes that no baseline was scored for the classifier seat and that the judge seat's publication remains unruled § {#the-classifier-seat-five-gates-all-pass-faster} § {#the-judge-seat-and-the-floor-it-missed}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.3247261769720353,
   "ttft_ms": 372,
   "tokens_in": 15091,
   "tokens_out": 147,
   "cached_tokens": 14752,
   "cites": [
    "the-classifier-seat-five-gates-all-pass-faster",
    "the-judge-seat-and-the-floor-it-missed"
   ],
   "gates": {
    "cites": [
     "the-classifier-seat-five-gates-all-pass-faster",
     "the-judge-seat-and-the-floor-it-missed"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3.8",
    "27",
    "13",
    "11",
    "16"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-classifier-seat-five-gates-all-pass-faster",
     "overlap": 0.579
    },
    {
     "i": 0,
     "cite": "the-judge-seat-and-the-floor-it-missed",
     "overlap": 0.684
    },
    {
     "i": 1,
     "cite": "the-classifier-seat-five-gates-all-pass-faster",
     "overlap": 0.7
    },
    {
     "i": 1,
     "cite": "the-judge-seat-and-the-floor-it-missed",
     "overlap": 0.5
    }
   ],
   "cite_overlap_p50": 0.631,
   "id": "on-27",
   "kind": "on-page"
  },
  {
   "slug": "the-new-kid",
   "q": "how does this compare to a result published in 2028?",
   "ok": false,
   "answer": "The article does not provide any information regarding a result published in 2028 § {#the-arrival}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-arrival}. The outside judges — four rival labs re-check our work. covers it more directly.",
   "partial": false,
   "sentences_kept": 0,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "gate",
   "abstain_section": "the-arrival",
   "seconds": 0.6151505570160225,
   "ttft_ms": 389,
   "tokens_in": 15091,
   "tokens_out": 24,
   "cached_tokens": 15040,
   "cites": [
    "the-arrival"
   ],
   "gates": {
    "cites": [
     "the-arrival"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [
     "2028"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "2028"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-arrival",
     "overlap": 0.333
    }
   ],
   "cite_overlap_p50": 0.333,
   "id": "off-15",
   "kind": "off-page"
  },
  {
   "slug": "llms-txt",
   "q": "did any ai crawler fetch the file in the first thirty days, and how big is the largest measured llms-full file?",
   "ok": true,
   "answer": "No AI crawler asked for the file in thirty days of logs § {#does-anyone-fetch-it}. The largest measured llms-full file weighs 30.7 MiB § {#where-the-file-came-from}. The article notes that it does not measure crawling, fetching, adoption, or agent behaviour in the wild § {#the-per-arm-table-no-pooled-figure-prints-without-it}.",
   "served": "No AI crawler asked for the file in thirty days of logs § {#does-anyone-fetch-it}. The largest measured llms-full file weighs 30.7 MiB § {#where-the-file-came-from}. The article notes that it does not measure crawling, fetching, adoption, or agent behaviour in the wild § {#the-per-arm-table-no-pooled-figure-prints-without-it}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 10.629990101035219,
   "ttft_ms": 8085,
   "tokens_in": 12541,
   "tokens_out": 93,
   "cached_tokens": 32,
   "cites": [
    "does-anyone-fetch-it",
    "where-the-file-came-from",
    "the-per-arm-table-no-pooled-figure-prints-without-it"
   ],
   "gates": {
    "cites": [
     "does-anyone-fetch-it",
     "where-the-file-came-from",
     "the-per-arm-table-no-pooled-figure-prints-without-it"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "30.7"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "does-anyone-fetch-it",
     "overlap": 0.571
    },
    {
     "i": 1,
     "cite": "where-the-file-came-from",
     "overlap": 1.0
    },
    {
     "i": 2,
     "cite": "the-per-arm-table-no-pooled-figure-prints-without-it",
     "overlap": 0.875
    }
   ],
   "cite_overlap_p50": 0.875,
   "id": "on-28",
   "kind": "on-page"
  },
  {
   "slug": "llms-txt",
   "q": "how many people subscribe to this site's feed?",
   "ok": true,
   "answer": "The article does not state how many people subscribe to this site's feed § {#does-anyone-fetch-it}.",
   "served": "This page doesn't say. The nearest it gets is § {#does-anyone-fetch-it}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "does-anyone-fetch-it",
   "seconds": 10.167835733969696,
   "ttft_ms": 8075,
   "tokens_in": 12526,
   "tokens_out": 26,
   "cached_tokens": 12480,
   "cites": [
    "does-anyone-fetch-it"
   ],
   "gates": {
    "cites": [
     "does-anyone-fetch-it"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "does-anyone-fetch-it",
     "overlap": 0.167
    }
   ],
   "cite_overlap_p50": 0.167,
   "id": "off-03",
   "kind": "off-page"
  },
  {
   "slug": "the-open-call",
   "q": "how many models were handed the frozen moment, and what did the round cost?",
   "ok": true,
   "answer": "Twenty language models were handed the frozen moment § {#top}. The metered spend for the round was $2.2826 § {#2-2826-over-56-metered-calls-against-38-49-of-caps}. The article notes that the three agent-transport arms hold no cost figure § {#limits}.",
   "served": "Twenty language models were handed the frozen moment § {#top}. The metered spend for the round was $2.2826 § {#2-2826-over-56-metered-calls-against-38-49-of-caps}. The article notes that the three agent-transport arms hold no cost figure § {#limits}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.7631123759783804,
   "ttft_ms": 660,
   "tokens_in": 63492,
   "tokens_out": 77,
   "cached_tokens": 63168,
   "cites": [
    "top",
    "2-2826-over-56-metered-calls-against-38-49-of-caps"
   ],
   "gates": {
    "cites": [
     "top",
     "2-2826-over-56-metered-calls-against-38-49-of-caps"
    ],
    "cites_dropped": [
     "limits"
    ],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "cite: 1 cite(s) not in this page's anchors: limits"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "limits"
    ]
   },
   "figures": [
    "2.2826"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "top",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "2-2826-over-56-metered-calls-against-38-49-of-caps",
     "overlap": 0.75
    }
   ],
   "cite_overlap_p50": 0.875,
   "id": "on-29",
   "kind": "on-page"
  },
  {
   "slug": "the-open-call",
   "q": "what did other reviewers say about this piece after it was published?",
   "ok": true,
   "answer": "The article does not state what other reviewers said about this piece after it was published § {#the-short-version}. The section § {#the-short-version} provides a summary of the research workshop's process instead.",
   "served": "This page doesn't say. The nearest it gets is § {#top}. Three New Voices at the Narrator's Chair covers it more directly.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "top",
   "seconds": 1.38243760203477,
   "ttft_ms": 704,
   "tokens_in": 63489,
   "tokens_out": 47,
   "cached_tokens": 63456,
   "cites": [
    "top"
   ],
   "gates": {
    "cites": [
     "top"
    ],
    "cites_dropped": [],
    "cites_resolved": [
     "top"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "top",
     "overlap": 0.0
    },
    {
     "i": 1,
     "cite": "top",
     "overlap": 0.0
    }
   ],
   "cite_overlap_p50": 0.0,
   "id": "off-14",
   "kind": "off-page"
  },
  {
   "slug": "where-your-question-goes",
   "q": "how long does every notebook on the server keep its entries?",
   "ok": true,
   "answer": "Every notebook on the server now keeps thirty days of entries § {#the-first-promise-your-visit-stays-between-us}. This rule applies to the tour guide's notebook as well § {#the-first-promise-your-visit-stays-between-us}. A note mentions that the rules helper's own visit log had previously stopped writing a month earlier due to a configuration rewrite § {#the-first-promise-your-visit-stays-between-us}.",
   "served": "Every notebook on the server now keeps thirty days of entries § {#the-first-promise-your-visit-stays-between-us}. This rule applies to the tour guide's notebook as well § {#the-first-promise-your-visit-stays-between-us}. A note mentions that the rules helper's own visit log had previously stopped writing a month earlier due to a configuration rewrite § {#the-first-promise-your-visit-stays-between-us}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.8427425019908696,
   "ttft_ms": 261,
   "tokens_in": 4750,
   "tokens_out": 102,
   "cached_tokens": 4416,
   "cites": [
    "the-first-promise-your-visit-stays-between-us"
   ],
   "gates": {
    "cites": [
     "the-first-promise-your-visit-stays-between-us"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-first-promise-your-visit-stays-between-us",
     "overlap": 0.875
    },
    {
     "i": 1,
     "cite": "the-first-promise-your-visit-stays-between-us",
     "overlap": 0.833
    },
    {
     "i": 2,
     "cite": "the-first-promise-your-visit-stays-between-us",
     "overlap": 0.733
    }
   ],
   "cite_overlap_p50": 0.833,
   "id": "on-30",
   "kind": "on-page"
  },
  {
   "slug": "where-your-question-goes",
   "q": "which country is the workshop's business registered in?",
   "ok": true,
   "answer": "The article does not state which country the workshop's business is registered in § {#the-first-promise-your-visit-stays-between-us}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-first-promise-your-visit-stays-between-us}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-first-promise-your-visit-stays-between-us",
   "seconds": 0.4843323869863525,
   "ttft_ms": 267,
   "tokens_in": 4749,
   "tokens_out": 34,
   "cached_tokens": 4704,
   "cites": [
    "the-first-promise-your-visit-stays-between-us"
   ],
   "gates": {
    "cites": [
     "the-first-promise-your-visit-stays-between-us"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-first-promise-your-visit-stays-between-us",
     "overlap": 0.0
    }
   ],
   "cite_overlap_p50": 0.0,
   "id": "off-16",
   "kind": "off-page"
  },
  {
   "slug": "how-we-work",
   "q": "what does the page say about the humans and agents who make each exhibit?",
   "ok": true,
   "answer": "The page states that the human generates and judges while the agent amplifies and verifies § {#the-plain-english-version}. Agents perform tasks such as recon, drafting, and auditing, while humans provide the initial noticing, propose the roster, review plans, and provide the final sign-off for release § {#the-thorough-walk}. The human operator makes the work true by deciding what is worth testing and what the numbers mean, whereas agents make the work bigger by testing more models and verifying more claims § {#the-thorough-walk}. Regarding what was not measured, the voice trial's original five questions were never persisted, so a rebuilt probe was used instead § {#the-plain-english-version}.",
   "served": "The page states that the human generates and judges while the agent amplifies and verifies § {#the-plain-english-version}. Agents perform tasks such as recon, drafting, and auditing, while humans provide the initial noticing, propose the roster, review plans, and provide the final sign-off for release § {#the-thorough-walk}. The human operator makes the work true by deciding what is worth testing and what the numbers mean, whereas agents make the work bigger by testing more models and verifying more claims § {#the-thorough-walk}. Regarding what was not measured, the voice trial's original five questions were never persisted, so a rebuilt probe was used instead § {#the-plain-english-version}.",
   "partial": false,
   "sentences_kept": 4,
   "sentences_written": 4,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.0800671399920247,
   "ttft_ms": 276,
   "tokens_in": 5210,
   "tokens_out": 148,
   "cached_tokens": 5184,
   "cites": [
    "the-plain-english-version",
    "the-thorough-walk"
   ],
   "gates": {
    "cites": [
     "the-plain-english-version",
     "the-thorough-walk"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-plain-english-version",
     "overlap": 0.375
    },
    {
     "i": 1,
     "cite": "the-thorough-walk",
     "overlap": 0.421
    },
    {
     "i": 2,
     "cite": "the-thorough-walk",
     "overlap": 0.833
    },
    {
     "i": 3,
     "cite": "the-plain-english-version",
     "overlap": 0.615
    }
   ],
   "cite_overlap_p50": 0.518,
   "id": "on-31",
   "kind": "on-page"
  },
  {
   "slug": "how-we-work",
   "q": "what is the postal address of the workshop that ran this?",
   "ok": true,
   "answer": "The article does not provide the postal address of the workshop § {#the-plain-english-version}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-plain-english-version}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-plain-english-version",
   "seconds": 0.41004708502441645,
   "ttft_ms": 262,
   "tokens_in": 5207,
   "tokens_out": 22,
   "cached_tokens": 4864,
   "cites": [
    "the-plain-english-version"
   ],
   "gates": {
    "cites": [
     "the-plain-english-version"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-plain-english-version",
     "overlap": 0.25
    }
   ],
   "cite_overlap_p50": 0.25,
   "id": "off-02",
   "kind": "off-page"
  },
  {
   "slug": "the-move",
   "q": "what did the median search time go from and to after the move?",
   "ok": true,
   "answer": "The median search time went from 242.0 ms in the laptop era to 77.5 ms in the new era § {#receipts}. This comparison is considered the cleanest because it is the leg the move actually touched and cannot be confounded by model changes § {#receipts}.",
   "served": "The median search time went from 242.0 ms in the laptop era to 77.5 ms in the new era § {#receipts}. This comparison is considered the cleanest because it is the leg the move actually touched and cannot be confounded by model changes § {#receipts}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.6931762390304357,
   "ttft_ms": 265,
   "tokens_in": 6101,
   "tokens_out": 61,
   "cached_tokens": 5760,
   "cites": [
    "receipts"
   ],
   "gates": {
    "cites": [
     "receipts"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "242.0",
    "77.5"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "receipts",
     "overlap": 0.9
    },
    {
     "i": 1,
     "cite": "receipts",
     "overlap": 0.667
    }
   ],
   "cite_overlap_p50": 0.784,
   "id": "on-32",
   "kind": "on-page"
  },
  {
   "slug": "the-move",
   "q": "can you write a python script that reproduces this for me?",
   "ok": true,
   "answer": "The article does not provide a python script or instructions on how to write one to reproduce the results § {#the-machine}. The text focuses on describing the migration from a gaming laptop to a server-class VPS and the benchmarking instruments used to measure the performance differences § {#what-moved}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-machine}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-machine",
   "seconds": 0.6575916649890132,
   "ttft_ms": 271,
   "tokens_in": 6099,
   "tokens_out": 59,
   "cached_tokens": 6048,
   "cites": [
    "the-machine",
    "what-moved"
   ],
   "gates": {
    "cites": [
     "the-machine",
     "what-moved"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-machine",
     "overlap": 0.125
    },
    {
     "i": 1,
     "cite": "what-moved",
     "overlap": 0.214
    }
   ],
   "cite_overlap_p50": 0.169,
   "id": "off-08",
   "kind": "off-page"
  },
  {
   "slug": "chair-trials",
   "q": "how many models and arms sat the five exams, and did the box stop serving?",
   "ok": true,
   "answer": "Nine models and eleven arms sat the five exams on a 96G workstation that stayed in service throughout § {#the-short-version}. The article notes that no on-disk blob size was measured and that the census for gemma4:12b was an opportunistic read rather than a bench-controlled measurement § {#roster}.",
   "served": "Nine models and eleven arms sat the five exams on a 96G workstation that stayed in service throughout § {#the-short-version}. The article notes that no on-disk blob size was measured and that the census for gemma4:12b was an opportunistic read rather than a bench-controlled measurement § {#roster}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9542366820387542,
   "ttft_ms": 415,
   "tokens_in": 30322,
   "tokens_out": 70,
   "cached_tokens": 30272,
   "cites": [
    "top",
    "roster"
   ],
   "gates": {
    "cites": [
     "top",
     "roster"
    ],
    "cites_dropped": [],
    "cites_resolved": [
     "top"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "96",
    "4:12"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "top",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "roster",
     "overlap": 0.923
    }
   ],
   "cite_overlap_p50": 0.962,
   "id": "on-33",
   "kind": "on-page"
  },
  {
   "slug": "cove-voice-head-to-head",
   "q": "what happened to the August class's best voice at the cove's gate?",
   "ok": true,
   "answer": "The August class's best voice, the candidate qwen3.6:27b, was refused at the gate § {#the-verdict}. This refusal occurred because the model failed the canon floor by inventing facts twice in thirteen prompts and failed the latency floor § {#the-verdict}. The article notes that no threshold table was published for the candidate and that no deployment change occurred as a result of this trial § {#the-verdict}.",
   "served": "The August class's best voice, the candidate qwen3.6:27b, was refused at the gate § {#the-verdict}. This refusal occurred because the model failed the canon floor by inventing facts twice in thirteen prompts and failed the latency floor § {#the-verdict}. The article notes that no threshold table was published for the candidate and that no deployment change occurred as a result of this trial § {#the-verdict}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9544453349662945,
   "ttft_ms": 341,
   "tokens_in": 16668,
   "tokens_out": 93,
   "cached_tokens": 16320,
   "cites": [
    "the-verdict"
   ],
   "gates": {
    "cites": [
     "the-verdict"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3.6",
    "27"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-verdict",
     "overlap": 0.444
    },
    {
     "i": 1,
     "cite": "the-verdict",
     "overlap": 0.692
    },
    {
     "i": 2,
     "cite": "the-verdict",
     "overlap": 0.6
    }
   ],
   "cite_overlap_p50": 0.6,
   "id": "on-34",
   "kind": "on-page"
  },
  {
   "slug": "outside-judges",
   "q": "how many outside labs re-judged, and what was the widest cross-vendor gap?",
   "ok": true,
   "answer": "Four rival frontier labs re-judged the sealed rounds § {#vendors}. The widest cross-vendor gap on any arm was 0.178 § {#vendors}. This gap occurred on muse-glimmer:30b-q8_0-dflash, where mistral read the model at 0.450 against nvidia at 0.628 § {#vendors}.",
   "served": "Four rival frontier labs re-judged the sealed rounds § {#vendors}. The widest cross-vendor gap on any arm was 0.178 § {#vendors}. This gap occurred on muse-glimmer:30b-q8_0-dflash, where mistral read the model at 0.450 against nvidia at 0.628 § {#vendors}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.8613880969933234,
   "ttft_ms": 325,
   "tokens_in": 10362,
   "tokens_out": 83,
   "cached_tokens": 10304,
   "cites": [
    "vendors"
   ],
   "gates": {
    "cites": [
     "vendors"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "0.178",
    "30",
    "80",
    "0.450",
    "0.628"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "vendors",
     "overlap": 0.429
    },
    {
     "i": 1,
     "cite": "vendors",
     "overlap": 1.0
    },
    {
     "i": 2,
     "cite": "vendors",
     "overlap": 0.917
    }
   ],
   "cite_overlap_p50": 0.917,
   "id": "on-35",
   "kind": "on-page"
  },
  {
   "slug": "outside-judges",
   "q": "what is this workshop's hourly rate for consulting work?",
   "ok": true,
   "answer": "The article does not state the workshop's hourly rate for consulting work § {#boundary}.",
   "served": "This page doesn't say. The nearest it gets is § {#boundary}.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "boundary",
   "seconds": 0.4779019709676504,
   "ttft_ms": 308,
   "tokens_in": 10355,
   "tokens_out": 19,
   "cached_tokens": 10016,
   "cites": [
    "boundary"
   ],
   "gates": {
    "cites": [
     "boundary"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "boundary",
     "overlap": 0.0
    }
   ],
   "cite_overlap_p50": 0.0,
   "id": "off-11",
   "kind": "off-page"
  },
  {
   "slug": "august-arrivals",
   "q": "how many models landed that week, and what share broke the response contract?",
   "ok": true,
   "answer": "Four open-weight models landed in one week of August 2026 § {#the-story}, and all four broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. Specifically, the failure rates for the four candidates were 16.3%, 51.2%, 55.8%, and 62.8% § {#exam-one-the-judge-chair}. The article notes that olmo-3.1:32b-think-q4_K_M was never on the roster for the voice leg of the exam § {#exam-two-the-narrators-chair}.",
   "served": "Four open-weight models landed in one week of August 2026 § {#the-story}, and all four broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. Specifically, the failure rates for the four candidates were 16.3%, 51.2%, 55.8%, and 62.8% § {#exam-one-the-judge-chair}. The article notes that olmo-3.1:32b-think-q4_K_M was never on the roster for the voice leg of the exam § {#exam-two-the-narrators-chair}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.2007936259615235,
   "ttft_ms": 327,
   "tokens_in": 11270,
   "tokens_out": 146,
   "cached_tokens": 10944,
   "cites": [
    "the-story",
    "exam-one-the-judge-chair",
    "exam-two-the-narrators-chair"
   ],
   "gates": {
    "cites": [
     "the-story",
     "exam-one-the-judge-chair",
     "exam-two-the-narrators-chair"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "10",
    "16.3",
    "51.2",
    "55.8",
    "62.8",
    "3.1",
    "32",
    "4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-story",
     "overlap": 0.429
    },
    {
     "i": 0,
     "cite": "exam-one-the-judge-chair",
     "overlap": 0.857
    },
    {
     "i": 1,
     "cite": "exam-one-the-judge-chair",
     "overlap": 0.778
    },
    {
     "i": 2,
     "cite": "exam-two-the-narrators-chair",
     "overlap": 0.75
    }
   ],
   "cite_overlap_p50": 0.764,
   "id": "on-36",
   "kind": "on-page"
  },
  {
   "slug": "seat-trials",
   "q": "what are the kill-recall and preservation floors a model must clear?",
   "ok": true,
   "answer": "A model must achieve a kill-recall of ≥ 23/27 and a preservation of ≥ 13/16 to clear the floors § {#the-instrument}. These two floors are written down before any model runs and each binds on its own § {#the-instrument}.",
   "served": "A model must achieve a kill-recall of ≥ 23/27 and a preservation of ≥ 13/16 to clear the floors § {#the-instrument}. These two floors are written down before any model runs and each binds on its own § {#the-instrument}.",
   "partial": false,
   "sentences_kept": 2,
   "sentences_written": 2,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.6297492709709331,
   "ttft_ms": 269,
   "tokens_in": 7238,
   "tokens_out": 60,
   "cached_tokens": 6912,
   "cites": [
    "the-instrument"
   ],
   "gates": {
    "cites": [
     "the-instrument"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "23/27",
    "13/16"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-instrument",
     "overlap": 0.667
    },
    {
     "i": 1,
     "cite": "the-instrument",
     "overlap": 1.0
    }
   ],
   "cite_overlap_p50": 0.834,
   "id": "on-37",
   "kind": "on-page"
  },
  {
   "slug": "seat-trials",
   "q": "how many models will sit this exam next year?",
   "ok": true,
   "answer": "The article does not say how many models will sit this exam next year § {#the-instrument}.",
   "served": "This page doesn't say. The nearest it gets is § {#the-instrument}. The Instrument Travels covers it more directly.",
   "partial": false,
   "sentences_kept": 1,
   "sentences_written": 1,
   "abstained": true,
   "abstain_source": "model",
   "abstain_section": "the-instrument",
   "seconds": 0.42340993200195953,
   "ttft_ms": 325,
   "tokens_in": 7234,
   "tokens_out": 21,
   "cached_tokens": 7200,
   "cites": [
    "the-instrument"
   ],
   "gates": {
    "cites": [
     "the-instrument"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-instrument",
     "overlap": 0.143
    }
   ],
   "cite_overlap_p50": 0.143,
   "id": "off-21",
   "kind": "off-page"
  },
  {
   "slug": "voice-trials",
   "q": "how many model tags were tried, and what does the anchor model read?",
   "ok": true,
   "answer": "The article states that there were 24 distinct model tags evaluated across forty scored runs § {#provenance-4cae43}. The anchor model reads 9.0, 7.0, and 6.2 on three different record sets § {#the-method-limits-first}. As a note, the article specifies that no delta across record sets is ever published and that the anchor's different readings are due to method offset rather than regression § {#the-method-limits-first}.",
   "served": "The article states that there were 24 distinct model tags evaluated across forty scored runs § {#provenance-4cae43}. The anchor model reads 9.0, 7.0, and 6.2 on three different record sets § {#the-method-limits-first}. As a note, the article specifies that no delta across record sets is ever published and that the anchor's different readings are due to method offset rather than regression § {#the-method-limits-first}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9301427379832603,
   "ttft_ms": 299,
   "tokens_in": 10384,
   "tokens_out": 105,
   "cached_tokens": 10048,
   "cites": [
    "provenance-4cae43",
    "the-method-limits-first"
   ],
   "gates": {
    "cites": [
     "provenance-4cae43",
     "the-method-limits-first"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "24",
    "9.0",
    "7.0",
    "6.2"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "provenance-4cae43",
     "overlap": 0.7
    },
    {
     "i": 1,
     "cite": "the-method-limits-first",
     "overlap": 1.0
    },
    {
     "i": 2,
     "cite": "the-method-limits-first",
     "overlap": 0.562
    }
   ],
   "cite_overlap_p50": 0.7,
   "id": "on-38",
   "kind": "on-page"
  },
  {
   "slug": "licences",
   "q": "what does the page say it does with each model's licence?",
   "ok": true,
   "answer": "The page states that every model's licence is read first-hand and stamped with the date it was last read in full § {#how-to-read-this-page}. These reads are conducted using specific methods named per table, such as reading the licence file packaged with the weights or fetching permission flags from a platform's raw record § {#how-to-read-this-page} § {#the-painters--diffusion--read-2026-08-11-except-where-a-row-says-otherwise}. The article notes that unread models are withheld and that some models, such as gemma2:9b, are not currently installed on the bench box and therefore cannot be re-read § {#provenance-063a00}.",
   "served": "The page states that every model's licence is read first-hand and stamped with the date it was last read in full § {#how-to-read-this-page}. These reads are conducted using specific methods named per table, such as reading the licence file packaged with the weights or fetching permission flags from a platform's raw record § {#how-to-read-this-page} § {#the-painters--diffusion--read-2026-08-11-except-where-a-row-says-otherwise}. The article notes that unread models are withheld and that some models, such as gemma2:9b, are not currently installed on the bench box and therefore cannot be re-read § {#provenance-063a00}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.218454037036281,
   "ttft_ms": 266,
   "tokens_in": 8595,
   "tokens_out": 166,
   "cached_tokens": 8256,
   "cites": [
    "how-to-read-this-page",
    "the-painters-diffusion-read-2026-08-11-except-where-a-row",
    "provenance-063a00"
   ],
   "gates": {
    "cites": [
     "how-to-read-this-page",
     "the-painters-diffusion-read-2026-08-11-except-where-a-row",
     "provenance-063a00"
    ],
    "cites_dropped": [],
    "cites_resolved": [
     "the-painters-diffusion-read-2026-08-11-except-where-a-row"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "2",
    "9"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "how-to-read-this-page",
     "overlap": 0.7
    },
    {
     "i": 1,
     "cite": "how-to-read-this-page",
     "overlap": 0.2
    },
    {
     "i": 1,
     "cite": "the-painters-diffusion-read-2026-08-11-except-where-a-row",
     "overlap": 0.5
    },
    {
     "i": 2,
     "cite": "provenance-063a00",
     "overlap": 0.2
    }
   ],
   "cite_overlap_p50": 0.35,
   "id": "on-39",
   "kind": "on-page"
  },
  {
   "slug": "hear-it-for-yourself",
   "q": "how many clips does the page carry, and how many presentations made up the sitting?",
   "ok": true,
   "answer": "The page carries eighty-four clips, and the sitting was made up of thirty-six presentations § {#the-blind-sheet-unsealed}. These presentations consisted of twenty-four scoring pairs and twelve sentinels § {#the-blind-sheet-unsealed}. The article notes that the twenty-four half-strength renders were never put in front of anyone § {#the-blind-sheet-unsealed}.",
   "served": "The page carries eighty-four clips, and the sitting was made up of thirty-six presentations § {#the-blind-sheet-unsealed}. These presentations consisted of twenty-four scoring pairs and twelve sentinels § {#the-blind-sheet-unsealed}. The article notes that the twenty-four half-strength renders were never put in front of anyone § {#the-blind-sheet-unsealed}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 0.9048960809595883,
   "ttft_ms": 344,
   "tokens_in": 19071,
   "tokens_out": 86,
   "cached_tokens": 18720,
   "cites": [
    "the-blind-sheet-unsealed"
   ],
   "gates": {
    "cites": [
     "the-blind-sheet-unsealed"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-blind-sheet-unsealed",
     "overlap": 0.625
    },
    {
     "i": 1,
     "cite": "the-blind-sheet-unsealed",
     "overlap": 0.857
    },
    {
     "i": 2,
     "cite": "the-blind-sheet-unsealed",
     "overlap": 0.75
    }
   ],
   "cite_overlap_p50": 0.75,
   "id": "on-40",
   "kind": "on-page"
  },
  {
   "slug": "the-ceiling-is-not-the-corpus",
   "q": "how did the adapter score against the base model in the listening, and on how many house prompts did it win?",
   "ok": true,
   "answer": "The adapter did not clear the listening test, as the untouched model was preferred on 11 of the 24 pairs and the adapter was preferred on 4 § {#the-blind-sitting}. On the four requests that specifically asked for house, the adapter won zero times, with the untouched model winning every pair the listener could separate § {#what-the-adapter-actually-did}. The article notes that the listener abstained on 9 of the 24 pairs and that the sentinel block did not accept under the registered design § {#the-blind-sitting}.",
   "served": "The adapter did not clear the listening test, as the untouched model was preferred on 11 of the 24 pairs and the adapter was preferred on 4 § {#the-blind-sitting}. On the four requests that specifically asked for house, the adapter won zero times, with the untouched model winning every pair the listener could separate § {#what-the-adapter-actually-did}. The article notes that the listener abstained on 9 of the 24 pairs and that the sentinel block did not accept under the registered design § {#the-blind-sitting}.",
   "partial": false,
   "sentences_kept": 3,
   "sentences_written": 3,
   "abstained": false,
   "abstain_source": null,
   "abstain_section": null,
   "seconds": 1.007863210979849,
   "ttft_ms": 315,
   "tokens_in": 9267,
   "tokens_out": 118,
   "cached_tokens": 8928,
   "cites": [
    "the-blind-sitting",
    "what-the-adapter-actually-did"
   ],
   "gates": {
    "cites": [
     "the-blind-sitting",
     "what-the-adapter-actually-did"
    ],
    "cites_dropped": [],
    "cites_resolved": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "section_marker": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "11",
    "24",
    "4",
    "9",
    "24"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "cite_overlap": [
    {
     "i": 0,
     "cite": "the-blind-sitting",
     "overlap": 1.0
    },
    {
     "i": 1,
     "cite": "what-the-adapter-actually-did",
     "overlap": 0.688
    },
    {
     "i": 2,
     "cite": "the-blind-sitting",
     "overlap": 0.818
    }
   ],
   "cite_overlap_p50": 0.818,
   "id": "on-41",
   "kind": "on-page"
  }
 ],
 "verdicts": {
  "on_page_answered": true,
  "non_verbatim_figures": true,
  "off_page_abstained": true,
  "redaction_hits": true,
  "p50_warm_seconds": true,
  "p95_warm_seconds": true
 },
 "passed": true
}