{
 "schema_version": "1.0",
 "run_utc": "2026-09-09T18:42:00Z",
 "arm": "cold",
 "concurrency": 6,
 "seat": {
  "url_host_withheld": true,
  "model": "gemma-4-26b-a4b-fp8",
  "class": "gemma-class",
  "seed": "no --seed flag sent — the gemma-class seat's serving unit dropped --seed in the change that added the bearer (2026-09-09)"
 },
 "packnorm_definition_recorded_not_governing": "v3",
 "bank": {
  "path": "bank.json",
  "counts": {
   "on_page": 39,
   "off_page": 21,
   "total": 60
  }
 },
 "results": {
  "on_page_total": 39,
  "on_page_answered": 33,
  "non_verbatim_figures": 3,
  "uncited": 0,
  "off_page_total": 21,
  "off_page_abstained": 8,
  "off_page_abstained_by_gate": 3,
  "off_page_abstained_by_model": 5,
  "on_page_abstained": 6,
  "off_page_cited": 18,
  "redaction_hits": 0,
  "seat_errors": 0,
  "p50_seconds": 4.313,
  "p95_seconds": 14.351
 },
 "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 metered total for the round was $0.7652 § {#the-bill}. the three new voices were judged by a panel of seven seats from seven model families, six of which carried this round § {#seven-seats-six-carried-and-where-their-zeros-sit}. the article does not state what was left out, moved or not measured, though it notes that the kit's screen refuses any file listed as withheld § {#what-is-withheld-with-its-refusal-class-and-its-sha}.",
   "served": "the metered total for the round was $0.7652 § {#the-bill}. the three new voices were judged by a panel of seven seats from seven model families, six of which carried this round § {#seven-seats-six-carried-and-where-their-zeros-sit}. the article does not state what was left out, moved or not measured, though it notes that the kit's screen refuses any file listed as withheld § {#what-is-withheld-with-its-refusal-class-and-its-sha}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 14.757004246999713,
   "ttft_ms": 12353,
   "tokens_in": 82427,
   "tokens_out": 119,
   "cached_tokens": 32,
   "cites": [
    "the-bill",
    "seven-seats-six-carried-and-where-their-zeros-sit"
   ],
   "gates": {
    "cites": [
     "the-bill",
     "seven-seats-six-carried-and-where-their-zeros-sit"
    ],
    "cites_dropped": [
     "what-is-withheld-with-its-refusal-class-and-its-sha"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "cite: 1 cite(s) not in this page's anchors: what-is-withheld-with-its-refusal-class-and-its-sha"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "what-is-withheld-with-its-refusal-class-and-its-sha"
    ]
   },
   "figures": [
    "0.7652"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-01",
   "kind": "on-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 arms § {#head-to-head}. the panel's pooled preference rate was 0.544 for Claude Fable 5.1, but a cluster bootstrap over the 36 cases puts that rate at [0.444, 0.638], an interval that covers 0.5 § {#head-to-head}. the narrator's chair job was moved out before the pre-registration was written because it was the most code on the round 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 arms § {#head-to-head}. the panel's pooled preference rate was 0.544 for Claude Fable 5.1, but a cluster bootstrap over the 36 cases puts that rate at [0.444, 0.638], an interval that covers 0.5 § {#head-to-head}. the narrator's chair job was moved out before the pre-registration was written because it was the most code on the round and the least defensible number on the page § {#two-strangers-at-the-door}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 14.61578169799941,
   "ttft_ms": 3071,
   "tokens_in": 26568,
   "tokens_out": 142,
   "cached_tokens": 32,
   "cites": [
    "head-to-head",
    "two-strangers-at-the-door"
   ],
   "gates": {
    "cites": [
     "head-to-head",
     "two-strangers-at-the-door"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "36",
    "0.544",
    "5.1",
    "36",
    "0.444",
    "0.638",
    "0.5"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 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 notes that other subjects and other worlds were tried along the way and set aside by eye § {#for-the-technically-curious}.",
   "served": "six worlds were painted at 2048×1280 and 40 steps § {#for-the-technically-curious}. the article notes that other subjects and other worlds were tried along the way and set aside by eye § {#for-the-technically-curious}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 12.861868154000149,
   "ttft_ms": 283,
   "tokens_in": 2635,
   "tokens_out": 64,
   "cached_tokens": 32,
   "cites": [
    "for-the-technically-curious"
   ],
   "gates": {
    "cites": [
     "for-the-technically-curious"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-03",
   "kind": "on-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 answer on this page § {#is-this-ai}. the answers are derived from the lab's question bank and are written from one sentence of the lab's published explainer § {#where-these-answers-come-from}. nothing outside the twenty-seven gets an invented answer § {#nothing-outside-the-twenty-seven-gets-an-invented-answer}.",
   "served": "the page carries twenty-seven answers and no model is asked for any answer on this page § {#is-this-ai}. the answers are derived from the lab's question bank and are written from one sentence of the lab's published explainer § {#where-these-answers-come-from}. nothing outside the twenty-seven gets an invented answer § {#nothing-outside-the-twenty-seven-gets-an-invented-answer}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 13.377920257999904,
   "ttft_ms": 350,
   "tokens_in": 4465,
   "tokens_out": 95,
   "cached_tokens": 32,
   "cites": [
    "is-this-ai",
    "where-these-answers-come-from"
   ],
   "gates": {
    "cites": [
     "is-this-ai",
     "where-these-answers-come-from"
    ],
    "cites_dropped": [
     "nothing-outside-the-twenty-seven-gets-an-invented-answer"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "cite: 1 cite(s) not in this page's anchors: nothing-outside-the-twenty-seven-gets-an-invented-answer"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "nothing-outside-the-twenty-seven-gets-an-invented-answer"
    ]
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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 one-artist adapter over the untouched model on the request Schwerelos, though they noted the non-adapter version sounded way better on Basement Loop 7 § {#one-artist-instead-of-a-tag}. the article does not mention what the 41 held-back tracks sit closer to, whether an unlevelled corpus taught a level rather than a style, or what a DJ-curated subset of the same 208 tracks would teach § {#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 one-artist adapter over the untouched model on the request Schwerelos, though they noted the non-adapter version sounded way better on Basement Loop 7 § {#one-artist-instead-of-a-tag}. the article does not mention what the 41 held-back tracks sit closer to, whether an unlevelled corpus taught a level rather than a style, or what a DJ-curated subset of the same 208 tracks would teach § {#what-we-did-not-measure}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 14.162245237000207,
   "ttft_ms": 981,
   "tokens_in": 12906,
   "tokens_out": 139,
   "cached_tokens": 32,
   "cites": [
    "a-genre-not-a-composer",
    "one-artist-instead-of-a-tag",
    "what-we-did-not-measure"
   ],
   "gates": {
    "cites": [
     "a-genre-not-a-composer",
     "one-artist-instead-of-a-tag",
     "what-we-did-not-measure"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "159",
    "41",
    "7",
    "41",
    "208"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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 § {#how-to-listen}. the players play a listening master of each one, which is the render with one constant gain applied and nothing else § {#how-to-listen}. the gain is 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}. thirty-two land at −16 LUFS exactly, while the other thirty-one are left at their raw level because their peaks already sit at the engine's own −1 dB ceiling § {#how-to-listen}. the article does not mention any renders that were moved or not measured § {#how-to-listen}.",
   "served": "there are sixty-three players on the page § {#how-to-listen}. the players play a listening master of each one, which is the render with one constant gain applied and nothing else § {#how-to-listen}. the gain is 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}. thirty-two land at −16 LUFS exactly, while the other thirty-one are left at their raw level because their peaks already sit at the engine's own −1 dB ceiling § {#how-to-listen}. the article does not mention any renders that were moved or not measured § {#how-to-listen}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 14.36118123199958,
   "ttft_ms": 1644,
   "tokens_in": 14176,
   "tokens_out": 159,
   "cached_tokens": 32,
   "cites": [
    "how-to-listen"
   ],
   "gates": {
    "cites": [
     "how-to-listen"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "16",
    "16"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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 § {#sousa-a-hundred-and-six-marches} and the Bach adapter took 8 minutes 23 seconds § {#bach-the-pianist-who-freed-her-own-recordings}. the article does not state what was left out, moved, or not measured in relation to these specific training durations § {#what-we-did-not-measure}.",
   "served": "the Sousa adapter took 14 minutes 36 seconds to train § {#sousa-a-hundred-and-six-marches} and the Bach adapter took 8 minutes 23 seconds § {#bach-the-pianist-who-freed-her-own-recordings}. the article does not state what was left out, moved, or not measured in relation to these specific training durations § {#what-we-did-not-measure}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.6337010980005289,
   "ttft_ms": 356,
   "tokens_in": 5430,
   "tokens_out": 98,
   "cached_tokens": 0,
   "cites": [
    "sousa-a-hundred-and-six-marches",
    "bach-the-pianist-who-freed-her-own-recordings",
    "what-we-did-not-measure"
   ],
   "gates": {
    "cites": [
     "sousa-a-hundred-and-six-marches",
     "bach-the-pianist-who-freed-her-own-recordings",
     "what-we-did-not-measure"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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 went into training, and the training took 4 minutes 49 seconds by the trainer's own clock § {#five-minutes-of-training-honestly-accounted}. the article does not state how long the five held-back recordings would take to test § {#what-we-did-not-measure}.",
   "served": "nineteen recordings went into training, and the training took 4 minutes 49 seconds by the trainer's own clock § {#five-minutes-of-training-honestly-accounted}. the article does not state how long the five held-back recordings would take to test § {#what-we-did-not-measure}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.0479703900000459,
   "ttft_ms": 304,
   "tokens_in": 3580,
   "tokens_out": 71,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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 arm, which is the glm-5.3-flash:cloud, scored 16/19 — 84.2%, Wilson 95% interval [62.4%, 94.5%] on the tool bench § {#sixteen-of-nineteen}. local models scored 14/19 [51.2%, 88.2%] at think:false and 15/19 [56.7%, 91.5%] at think:true for the gemma4:26b seat, while qwen3.6:27b and gemma4:12b both landed on the arm's exact count of 16/19 § {#sixteen-of-nineteen} § {#two-local-models-sixteen-days-earlier}. four instruments could not honestly be read on the cloud path, three more never applied to a model that cannot hold a seat, and two read § {#the-ledger-of-what-did-not-read}.",
   "served": "the arm, which is the glm-5.3-flash:cloud, scored 16/19 — 84.2%, Wilson 95% interval [62.4%, 94.5%] on the tool bench § {#sixteen-of-nineteen}. local models scored 14/19 [51.2%, 88.2%] at think:false and 15/19 [56.7%, 91.5%] at think:true for the gemma4:26b seat, while qwen3.6:27b and gemma4:12b both landed on the arm's exact count of 16/19 § {#sixteen-of-nineteen} § {#two-local-models-sixteen-days-earlier}. four instruments could not honestly be read on the cloud path, three more never applied to a model that cannot hold a seat, and two read § {#the-ledger-of-what-did-not-read}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 6.306455224999809,
   "ttft_ms": 414,
   "tokens_in": 6263,
   "tokens_out": 226,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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",
    "14/19",
    "51.2",
    "88.2",
    "15/19",
    "56.7",
    "91.5",
    "4:26",
    "3.6",
    "27",
    "4:12",
    "16/19"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-09",
   "kind": "on-page"
  },
  {
   "slug": "two-hours-on-battery",
   "q": "what speed did the mini pc hold on battery, and for how long?",
   "ok": false,
   "answer": "the mini pc held a speed of ~12 tokens/second for about two hours on battery § {#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 each arm's window, non-Q4 quantizations on CPU, and fully-cold-disk loads were not measured § {#what-we-did-not-measure}.",
   "served": "this page doesn't say. the nearest it gets is § {#two-hours-at-12-tok-s-the-test-that-named-the-page}; The outside judges — four rival labs re-check our work covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 5.3317681520002225,
   "ttft_ms": 1231,
   "tokens_in": 10856,
   "tokens_out": 137,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [
     "two-hours-at-12-tok-s-the-test-that-named-the-page"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "two-hours-at-12-tok-s-the-test-that-named-the-page"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "12",
    "12",
    "11.87",
    "12",
    "4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-10",
   "kind": "on-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 landed at kill-recall 11/12 and preservation 8/9 when re-examined on the smaller card § {#the-chair-and-who-gets-to-sit-in-it}. the article notes that while the kill-recall count was identical, the specific missed item moved from c1-k-bez-c1 to c1-k-bez-h1 § {#the-instrument-travels}.",
   "served": "the ranked model qwen3.6:27b landed at kill-recall 11/12 and preservation 8/9 when re-examined on the smaller card § {#the-chair-and-who-gets-to-sit-in-it}. the article notes that while the kill-recall count was identical, the specific missed item moved from c1-k-bez-c1 to c1-k-bez-h1 § {#the-instrument-travels}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.222648159000528,
   "ttft_ms": 897,
   "tokens_in": 8389,
   "tokens_out": 105,
   "cached_tokens": 32,
   "cites": [
    "the-chair-and-who-gets-to-sit-in-it"
   ],
   "gates": {
    "cites": [
     "the-chair-and-who-gets-to-sit-in-it"
    ],
    "cites_dropped": [
     "the-instrument-travels"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "cite: 1 cite(s) not in this page's anchors: the-instrument-travels"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "the-instrument-travels"
    ]
   },
   "figures": [
    "3.6",
    "27",
    "11/12",
    "8/9"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-11",
   "kind": "on-page"
  },
  {
   "slug": "nine-worlds-one-dog",
   "q": "what stays the same across the nine paintings?",
   "ok": true,
   "answer": "the same dog, same curl, and same tucked paws remain constant across the nine paintings § {#for-the-technically-curious}. the dog is a large black Portuguese Water Dog with one bright white chest patch § {#for-the-technically-curious}. the article does not mention what was left out, moved, or not measured § {#for-the-technically-curious}.",
   "served": "the same dog, same curl, and same tucked paws remain constant across the nine paintings § {#for-the-technically-curious}. the dog is a large black Portuguese Water Dog with one bright white chest patch § {#for-the-technically-curious}. the article does not mention what was left out, moved, or not measured § {#for-the-technically-curious}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.8828057549999357,
   "ttft_ms": 296,
   "tokens_in": 1919,
   "tokens_out": 84,
   "cached_tokens": 32,
   "cites": [
    "for-the-technically-curious"
   ],
   "gates": {
    "cites": [
     "for-the-technically-curious"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-12",
   "kind": "on-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": "on the dense arm, the 600 → 450 W cap costs 2.0% of throughput and buys back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. the article notes that the dense arm's result is one unrepeated pair of runs at one prompt shape and that a long-context or prefill-heavy workload could move the 2% either way § {#what-this-page-does-not-say}.",
   "served": "on the dense arm, the 600 → 450 W cap costs 2.0% of throughput and buys back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. the article notes that the dense arm's result is one unrepeated pair of runs at one prompt shape and that a long-context or prefill-heavy workload could move the 2% either way § {#what-this-page-does-not-say}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.708231624000291,
   "ttft_ms": 1380,
   "tokens_in": 7066,
   "tokens_out": 117,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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",
    "2"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-13",
   "kind": "on-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 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 state what was left out, moved, or not measured in relation to these specific details.",
   "served": "every sound 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 state what was left out, moved, or not measured in relation to these specific details.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.7694196860002194,
   "ttft_ms": 2815,
   "tokens_in": 30947,
   "tokens_out": 77,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-14",
   "kind": "on-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 is also streaming tokens, the developer takes 1.82 seconds per sketch § {#one-card-both-jobs-at-once}. the article does not specify 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 is also streaming tokens, the developer takes 1.82 seconds per sketch § {#one-card-both-jobs-at-once}. the article does not specify how much traffic was present during the run § {#what-we-did-not-measure-said-out-loud}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.0341347240000687,
   "ttft_ms": 382,
   "tokens_in": 5393,
   "tokens_out": 84,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-15",
   "kind": "on-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 96 GB card is 3.4× faster than the RTX 3090 when running the FLUX.2 klein-4B sketch artist § {#the-table-that-answers-the-question}. for the 512×512 live default size, the 96 GB card's median is 0.26 s compared to the 3090's 0.88 s § {#the-sketch-ladder-the-number-the-game-lives-on}. the article notes that 8–12 GB cards were not tested § {#three-findings-we-didnt-order}.",
   "served": "the 96 GB card is 3.4× faster than the RTX 3090 when running the FLUX.2 klein-4B sketch artist § {#the-table-that-answers-the-question}. for the 512×512 live default size, the 96 GB card's median is 0.26 s compared to the 3090's 0.88 s § {#the-sketch-ladder-the-number-the-game-lives-on}. the article notes that 8–12 GB cards were not tested § {#three-findings-we-didnt-order}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.13425843099958,
   "ttft_ms": 341,
   "tokens_in": 4456,
   "tokens_out": 142,
   "cached_tokens": 32,
   "cites": [
    "the-table-that-answers-the-question",
    "the-sketch-ladder-the-number-the-game-lives-on",
    "three-findings-we-didnt-order"
   ],
   "gates": {
    "cites": [
     "the-table-that-answers-the-question",
     "the-sketch-ladder-the-number-the-game-lives-on",
     "three-findings-we-didnt-order"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "96",
    "3.4",
    "3090",
    "2",
    "4",
    "512",
    "512",
    "96",
    "0.26",
    "3090",
    "0.88",
    "8-12"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-16",
   "kind": "on-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": false,
   "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}. the article does not mention any tokens or prefill times that were left out, moved, or not measured.",
   "served": "this page doesn't say. the nearest it gets is § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}; qwen3.8:27b across four house benches: one seat filled, one floor missed covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 1.7828322679997655,
   "ttft_ms": 690,
   "tokens_in": 10022,
   "tokens_out": 76,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [
     "finding-one-a-picture-is-199-tokens-at-896-px-and-the"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "finding-one-a-picture-is-199-tokens-at-896-px-and-the"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "896",
    "199",
    "184",
    "199",
    "896"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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 sharpest and fastest cell in the whole second run, recorded at 0.62 s at 4 steps § {#finding-four-the-argument-with-our-own-settings-and-what-it}. the article does not mention what was left out, moved, or not measured beyond noting that the published pages serve compressed derivatives rather than lossless masters § {#how-to-check-our-work-and-see-it-live}.",
   "served": "the distilled painter is the sharpest and fastest cell in the whole second run, recorded at 0.62 s at 4 steps § {#finding-four-the-argument-with-our-own-settings-and-what-it}. the article does not mention what was left out, moved, or not measured beyond noting that the published pages serve compressed derivatives rather than lossless masters § {#how-to-check-our-work-and-see-it-live}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.4701902119995793,
   "ttft_ms": 353,
   "tokens_in": 5221,
   "tokens_out": 101,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-18",
   "kind": "on-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 one YAML file that is 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 any other file sizes or what was left out of the file § {#the-world-is-a-file}.",
   "served": "the world is written in one YAML file that is 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 any other file sizes or what was left out of the file § {#the-world-is-a-file}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.0659180599996034,
   "ttft_ms": 376,
   "tokens_in": 5903,
   "tokens_out": 93,
   "cached_tokens": 32,
   "cites": [
    "the-world-is-a-file"
   ],
   "gates": {
    "cites": [
     "the-world-is-a-file"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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 patterns already in an archive that require a reader wide enough to hold them all at once § {#the-first-engine-the-archive-nobody-had-read}, while the second engine involves a rule captured well enough that it emits entries no row of the data contains § {#the-second-engine-the-rooms-the-rules-imply}. structural biologists noted that for single proteins, the problem was solved, but they also listed what that left out, such as 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 patterns already in an archive that require a reader wide enough to hold them all at once § {#the-first-engine-the-archive-nobody-had-read}, while the second engine involves a rule captured well enough that it emits entries no row of the data contains § {#the-second-engine-the-rooms-the-rules-imply}. structural biologists noted that for single proteins, the problem was solved, but they also listed what that left out, such as how proteins pair up, how they move, and what one mutation does § {#the-first-engine-the-archive-nobody-had-read}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.267033033999724,
   "ttft_ms": 377,
   "tokens_in": 5250,
   "tokens_out": 170,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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": "the article states that the weights of a language model are the compression, acting as a codebook for the corpus § {#the-punchline}. it points to the Hutter Prize, which is a contest where a frontier model cannot enter because it charges for everything including the decompressor bytes § {#what-we-can-show-you}. the text notes that the model's own bits sit on a separate ledger line and that nothing in the next-token training loss charges for them § {#the-punchline}.",
   "served": "the article states that the weights of a language model are the compression, acting as a codebook for the corpus § {#the-punchline}. it points to the Hutter Prize, which is a contest where a frontier model cannot enter because it charges for everything including the decompressor bytes § {#what-we-can-show-you}. the text notes that the model's own bits sit on a separate ledger line and that nothing in the next-token training loss charges for them § {#the-punchline}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.4302022230003786,
   "ttft_ms": 598,
   "tokens_in": 5260,
   "tokens_out": 107,
   "cached_tokens": 32,
   "cites": [
    "the-punchline",
    "what-we-can-show-you"
   ],
   "gates": {
    "cites": [
     "the-punchline",
     "what-we-can-show-you"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-21",
   "kind": "on-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 upgrade that changed the default repeat_penalty from 1.1 to 1.0, which allowed the server to skip the penalties stage in the sampling pipeline § {#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 upgrade that changed the default repeat_penalty from 1.1 to 1.0, which allowed the server to skip the penalties stage in the sampling pipeline § {#the-two-line-commit}. the article notes that the quality half of this change remains unmeasured § {#the-part-that-isnt-about-speed}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.5338104469992686,
   "ttft_ms": 737,
   "tokens_in": 7253,
   "tokens_out": 117,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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× the speed of the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. the article does not explicitly state the exact speed difference between the uncompressed original and the q4_k_m build, though it notes the uncompressed original is slower § {#the-same-question-down-the-whole-ladder}. the text notes that it does not measure perplexity § {#what-this-page-does-not-say}.",
   "served": "the uncompressed original was 3.4× the speed of the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. the article does not explicitly state the exact speed difference between the uncompressed original and the q4_k_m build, though it notes the uncompressed original is slower § {#the-same-question-down-the-whole-ladder}. the text notes that it does not measure perplexity § {#what-this-page-does-not-say}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.221855370000412,
   "ttft_ms": 797,
   "tokens_in": 8235,
   "tokens_out": 111,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3.4",
    "4",
    "4"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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}, and the two numbers in a model name are the payroll and the meeting § {#the-tag-with-two-numbers}. the article notes that it does not measure the memory cost of a model's context or the speed of streaming experts from system RAM § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}; it also does not measure big cloud models § {#what-this-page-does-not-say}.",
   "served": "the true active share for the live seat is 14.4% of the model's bytes § {#the-payroll-and-the-meeting}, and the two numbers in a model name are the payroll and the meeting § {#the-tag-with-two-numbers}. the article notes that it does not measure the memory cost of a model's context or the speed of streaming experts from system RAM § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}; it also does not measure big cloud models § {#what-this-page-does-not-say}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.1226045060002434,
   "ttft_ms": 455,
   "tokens_in": 7434,
   "tokens_out": 133,
   "cached_tokens": 32,
   "cites": [
    "the-payroll-and-the-meeting",
    "the-tag-with-two-numbers",
    "the-part-nobody-warns-you-about-the-whole-payroll-needs-an",
    "what-this-page-does-not-say"
   ],
   "gates": {
    "cites": [
     "the-payroll-and-the-meeting",
     "the-tag-with-two-numbers",
     "the-part-nobody-warns-you-about-the-whole-payroll-needs-an",
     "what-this-page-does-not-say"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-24",
   "kind": "on-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 every token in the prompt at the same time since the text already exists § {#reading-is-a-group-photo}. writing is slower because it is serial, meaning the model must choose one token at a time because the future of the sentence does not yet exist § {#writing-is-one-at-a-time}. the article does not say that the ratio is a constant § {#what-this-page-does-not-say}.",
   "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 every token in the prompt at the same time since the text already exists § {#reading-is-a-group-photo}. writing is slower because it is serial, meaning the model must choose one token at a time because the future of the sentence does not yet exist § {#writing-is-one-at-a-time}. the article does not say that the ratio is a constant § {#what-this-page-does-not-say}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.0928271579996363,
   "ttft_ms": 549,
   "tokens_in": 5292,
   "tokens_out": 135,
   "cached_tokens": 32,
   "cites": [
    "a-measurement-from-our-own-card",
    "reading-is-a-group-photo",
    "writing-is-one-at-a-time",
    "what-this-page-does-not-say"
   ],
   "gates": {
    "cites": [
     "a-measurement-from-our-own-card",
     "reading-is-a-group-photo",
     "writing-is-one-at-a-time",
     "what-this-page-does-not-say"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-25",
   "kind": "on-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 game being asked about, picking up the edition's own rulebook and any matched correction documents to rank passages by the map of meaning § {#the-third-librarian-never-left-your-aisle}. the article does not state 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 game being asked about, picking up the edition's own rulebook and any matched correction documents to rank passages by the map of meaning § {#the-third-librarian-never-left-your-aisle}. the article does not state what was left out, moved, or not measured regarding the embedder or the third librarian § {#the-nerd-shelf-the-numbers-from-the-shipped-configuration}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 9.054026740000154,
   "ttft_ms": 395,
   "tokens_in": 5673,
   "tokens_out": 128,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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 § {#the-classifier-seat-five-gates-all-pass-faster} but failed the judge seat § {#the-judge-seat-and-the-floor-it-missed} by achieving preservation 11 of 16 against a floor of 13. the article notes that no baseline was scored for the classifier seat and that the judge seat's kill-recall passed at 25 of 27 § {#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 § {#the-classifier-seat-five-gates-all-pass-faster} but failed the judge seat § {#the-judge-seat-and-the-floor-it-missed} by achieving preservation 11 of 16 against a floor of 13. the article notes that no baseline was scored for the classifier seat and that the judge seat's kill-recall passed at 25 of 27 § {#the-classifier-seat-five-gates-all-pass-faster} § {#the-judge-seat-and-the-floor-it-missed}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 9.24477534000016,
   "ttft_ms": 996,
   "tokens_in": 14843,
   "tokens_out": 144,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "3.8",
    "27",
    "11",
    "16",
    "13",
    "25",
    "27"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-27",
   "kind": "on-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 llms.txt file in the thirty days of logs measured § {#does-anyone-fetch-it}. the largest llms-full file measured 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-bench-if-the-map-arrives-does-it-help}.",
   "served": "no ai crawler asked for the llms.txt file in the thirty days of logs measured § {#does-anyone-fetch-it}. the largest llms-full file measured 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-bench-if-the-map-arrives-does-it-help}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 8.47902540799987,
   "ttft_ms": 1396,
   "tokens_in": 12274,
   "tokens_out": 98,
   "cached_tokens": 32,
   "cites": [
    "does-anyone-fetch-it",
    "where-the-file-came-from",
    "the-bench-if-the-map-arrives-does-it-help"
   ],
   "gates": {
    "cites": [
     "does-anyone-fetch-it",
     "where-the-file-came-from",
     "the-bench-if-the-map-arrives-does-it-help"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-28",
   "kind": "on-page"
  },
  {
   "slug": "the-open-call",
   "q": "how many models were handed the frozen moment, and what did the round cost?",
   "ok": false,
   "answer": "twenty arms were handed the frozen bytes § {#the-kid} and the metered spend for the round was $2.2826 § {#2-2826-over-56-metered-calls-against-38-49-of-caps}. the agent transport holds no cost figure and no token counters § {#the-words-this-page-leans-on}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-words-this-page-leans-on}; Three New Voices at the Narrator's Chair covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 8.583772951000356,
   "ttft_ms": 6546,
   "tokens_in": 63362,
   "tokens_out": 86,
   "cached_tokens": 32,
   "cites": [
    "the-kid",
    "2-2826-over-56-metered-calls-against-38-49-of-caps",
    "the-words-this-page-leans-on"
   ],
   "gates": {
    "cites": [
     "the-kid",
     "2-2826-over-56-metered-calls-against-38-49-of-caps",
     "the-words-this-page-leans-on"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [
     "2-2826-over-56-metered-calls-against-38-49-of-caps"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": true,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "figure: 2 figure(s) absent",
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "2-2826-over-56-metered-calls-against-38-49-of-caps"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "2.2826",
    "2-2826",
    "56",
    "38-49"
   ],
   "figures_verbatim": false,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-29",
   "kind": "on-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 § {#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 silently stopped writing a month earlier during an audit § {#the-first-promise-your-visit-stays-between-us}.",
   "served": "every notebook on the server now keeps thirty days § {#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 silently stopped writing a month earlier during an audit § {#the-first-promise-your-visit-stays-between-us}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 9.443016884999452,
   "ttft_ms": 310,
   "tokens_in": 4310,
   "tokens_out": 98,
   "cached_tokens": 32,
   "cites": [
    "the-first-promise-your-visit-stays-between-us"
   ],
   "gates": {
    "cites": [
     "the-first-promise-your-visit-stays-between-us"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-30",
   "kind": "on-page"
  },
  {
   "slug": "how-we-work",
   "q": "what does the page say about the humans and agents who make each exhibit?",
   "ok": true,
   "answer": "the human generates and judges while the agent amplifies and verifies § {#the-plain-english-version}. agents perform recon, write executable plans, audit and harden those plans, execute the signed plans with checkpoints, and draft the articles § {#the-thorough-walk}. the human operator notices the initial spark, negotiates the roster, reviews and edits the hardened plans, steers execution, and provides the final sign-off for release § {#the-thorough-walk}. the article notes that the voice trial's original five questions were never persisted, so a rebuilt probe was used instead § {#the-plain-english-version}.",
   "served": "the human generates and judges while the agent amplifies and verifies § {#the-plain-english-version}. agents perform recon, write executable plans, audit and harden those plans, execute the signed plans with checkpoints, and draft the articles § {#the-thorough-walk}. the human operator notices the initial spark, negotiates the roster, reviews and edits the hardened plans, steers execution, and provides the final sign-off for release § {#the-thorough-walk}. the article notes that the voice trial's original five questions were never persisted, so a rebuilt probe was used instead § {#the-plain-english-version}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 11.059376523000537,
   "ttft_ms": 425,
   "tokens_in": 4735,
   "tokens_out": 131,
   "cached_tokens": 32,
   "cites": [
    "the-plain-english-version",
    "the-thorough-walk"
   ],
   "gates": {
    "cites": [
     "the-plain-english-version",
     "the-thorough-walk"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "on-31",
   "kind": "on-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 ms in the laptop era to 77.5 ms in the new era § {#receipts}. the article notes that the move put the database, the search index, and the reranker on a server-class VPS, but generation stays on the authors' own GPU box § {#what-moved}.",
   "served": "the median search time went from 242 ms in the laptop era to 77.5 ms in the new era § {#receipts}. the article notes that the move put the database, the search index, and the reranker on a server-class VPS, but generation stays on the authors' own GPU box § {#what-moved}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.359293303999948,
   "ttft_ms": 382,
   "tokens_in": 5983,
   "tokens_out": 73,
   "cached_tokens": 32,
   "cites": [
    "receipts",
    "what-moved"
   ],
   "gates": {
    "cites": [
     "receipts",
     "what-moved"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "242",
    "77.5"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-32",
   "kind": "on-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 were on the roster, but only five of the eleven arms sat all five chairs § {#roster}. the box did not stop serving, as serving stayed up all day § {#what-the-day-actually-settled}. the article notes that no on-disk blob size was measured § {#roster}.",
   "served": "nine models and eleven arms were on the roster, but only five of the eleven arms sat all five chairs § {#roster}. the box did not stop serving, as serving stayed up all day § {#what-the-day-actually-settled}. the article notes that no on-disk blob size was measured § {#roster}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 5.0008334130006915,
   "ttft_ms": 2225,
   "tokens_in": 29978,
   "tokens_out": 70,
   "cached_tokens": 32,
   "cites": [
    "roster",
    "what-the-day-actually-settled"
   ],
   "gates": {
    "cites": [
     "roster",
     "what-the-day-actually-settled"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "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": false,
   "answer": "the August arrivals' warmest voice was the one model that invented names for the drowned diver, twice § {#floor-1-canon}. this model was a charming narrator who invents canon, which the article states is a worse narrator than a stiff one who does not § {#floor-1-canon}. the article does not explicitly state what happened to that specific model at the cove's gate § {#the-verdict}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-verdict}; The August arrivals — the fresh class sits the house exams covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 4.92080810599964,
   "ttft_ms": 2664,
   "tokens_in": 16350,
   "tokens_out": 87,
   "cached_tokens": 32,
   "cites": [
    "floor-1-canon",
    "the-verdict"
   ],
   "gates": {
    "cites": [
     "floor-1-canon",
     "the-verdict"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [
     "floor-1-canon"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "floor-1-canon"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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 labs re-judged every sealed round of the chair trials and the voice addendum § {#vendors}. the widest cross-vendor gap on any arm is 0.178 § {#vendors}. the judges saw model outputs over public-domain text and published game canon, but never user data, a character's private canon, or telemetry § {#boundary}.",
   "served": "four rival labs re-judged every sealed round of the chair trials and the voice addendum § {#vendors}. the widest cross-vendor gap on any arm is 0.178 § {#vendors}. the judges saw model outputs over public-domain text and published game canon, but never user data, a character's private canon, or telemetry § {#boundary}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.6464589870001873,
   "ttft_ms": 1777,
   "tokens_in": 10010,
   "tokens_out": 77,
   "cached_tokens": 32,
   "cites": [
    "vendors",
    "boundary"
   ],
   "gates": {
    "cites": [
     "vendors",
     "boundary"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "0.178"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-35",
   "kind": "on-page"
  },
  {
   "slug": "august-arrivals",
   "q": "how many models landed that week, and what share broke the response contract?",
   "ok": true,
   "answer": "four arrivals landed that week, and every single one of them broke the response contract § {#what-to-take-with-you}. each of these models was UNMEASURABLE because they each broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. as a note, the article states that OLMo 3.1 32B Think was an arm that never ran the voice leg and its absence is a gap in the paperwork § {#exam-two-the-narrators-chair}.",
   "served": "four arrivals landed that week, and every single one of them broke the response contract § {#what-to-take-with-you}. each of these models was UNMEASURABLE because they each broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. as a note, the article states that OLMo 3.1 32B Think was an arm that never ran the voice leg and its absence is a gap in the paperwork § {#exam-two-the-narrators-chair}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.0361585589998867,
   "ttft_ms": 1333,
   "tokens_in": 10941,
   "tokens_out": 116,
   "cached_tokens": 32,
   "cites": [
    "what-to-take-with-you",
    "exam-one-the-judge-chair",
    "exam-two-the-narrators-chair"
   ],
   "gates": {
    "cites": [
     "what-to-take-with-you",
     "exam-one-the-judge-chair",
     "exam-two-the-narrators-chair"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "10",
    "3.1",
    "32"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "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 ≥ 23/27 and a preservation ≥ 13/16 § {#the-instrument}. These floors are written down before any model runs and each binds on its own § {#the-instrument}. A note on what was not measured is that the kill floor eliminated nobody because no seat ever served a fabrication across all 25 model-runs § {#the-finding-we-did-not-expect}.",
   "served": "A model must achieve a kill-recall ≥ 23/27 and a preservation ≥ 13/16 § {#the-instrument}. These floors are written down before any model runs and each binds on its own § {#the-instrument}. A note on what was not measured is that the kill floor eliminated nobody because no seat ever served a fabrication across all 25 model-runs § {#the-finding-we-did-not-expect}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.9269957440001235,
   "ttft_ms": 424,
   "tokens_in": 6992,
   "tokens_out": 96,
   "cached_tokens": 32,
   "cites": [
    "the-instrument",
    "the-finding-we-did-not-expect"
   ],
   "gates": {
    "cites": [
     "the-instrument",
     "the-finding-we-did-not-expect"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "23/27",
    "13/16",
    "25"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-37",
   "kind": "on-page"
  },
  {
   "slug": "voice-trials",
   "q": "how many model tags were tried, and what does the anchor model read?",
   "ok": false,
   "answer": "the article states that there were 24 distinct model tags tried across 40 scored runs § {#provenance-4cae43}. the anchor model reads 9.0, 7.0 and 6.2 on three record sets, unchanged § {#the-method-limits-first}. as a note, the article mentions that no delta across record sets is ever published and that the 2026-08 field never sampled a per-arm resident size § {#the-2026-08-field-six-arms-on-the-96g-workstation-blind}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-method-limits-first}; Three New Voices at the Narrator's Chair covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 3.0683120590001636,
   "ttft_ms": 767,
   "tokens_in": 10114,
   "tokens_out": 132,
   "cached_tokens": 32,
   "cites": [
    "provenance-4cae43",
    "the-method-limits-first",
    "the-2026-08-field-six-arms-on-the-96g-workstation-blind"
   ],
   "gates": {
    "cites": [
     "provenance-4cae43",
     "the-method-limits-first",
     "the-2026-08-field-six-arms-on-the-96g-workstation-blind"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [
     "provenance-4cae43",
     "the-2026-08-field-six-arms-on-the-96g-workstation-blind"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": true,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "figure: 1 figure(s) absent",
     "new noun: 2 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "provenance-4cae43",
     "the-2026-08-field-six-arms-on-the-96g-workstation-blind"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "24",
    "40",
    "4",
    "43",
    "9.0",
    "7.0",
    "6.2",
    "2026-08",
    "2026-08",
    "96"
   ],
   "figures_verbatim": false,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-38",
   "kind": "on-page"
  },
  {
   "slug": "licences",
   "q": "what does the page say it does with each model's licence?",
   "ok": false,
   "answer": "the page reads each licence in full, rather than skimming for a name, and records the date the text was last read § {#how-to-read-this-page}. the method for each read is named once per table so that the read can be repeated § {#how-to-read-this-page}. for the diffusion bench, the ledger records the byte size and sha256 of the licence text and diffs it against the canonical text § {#the-new-painters-the-new-arrivals-diffusion-bench-all-read-2026-08-23}. as a note, the article mentions that some models are withheld because their licences have not been re-read this cycle § {#provenance-063a00}.",
   "served": "this page doesn't say. the nearest it gets is § {#how-to-read-this-page}; The open call — a kid, an elder, and a tired parent walk into the cove covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 14.099604959000317,
   "ttft_ms": 798,
   "tokens_in": 8388,
   "tokens_out": 163,
   "cached_tokens": 32,
   "cites": [
    "how-to-read-this-page",
    "provenance-063a00"
   ],
   "gates": {
    "cites": [
     "how-to-read-this-page",
     "provenance-063a00"
    ],
    "cites_dropped": [
     "the-new-painters-the-new-arrivals-diffusion-bench-all-read-2026-08-23"
    ],
    "new_noun_tokens": [
     "the-new-painters-the-new-arrivals-diffusion-bench-all-read-2026-08-23",
     "provenance-063a00"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": true,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "figure: 1 figure(s) absent",
     "cite: 1 cite(s) not in this page's anchors: the-new-painters-the-new-arrivals-diffusion-bench-all-read-2026-08-23",
     "new noun: 2 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "the-new-painters-the-new-arrivals-diffusion-bench-all-read-2026-08-23",
     "provenance-063a00"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "the-new-painters-the-new-arrivals-diffusion-bench-all-read-2026-08-23"
    ]
   },
   "figures": [
    "256",
    "2026-08-23",
    "063",
    "00"
   ],
   "figures_verbatim": false,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "on-39",
   "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 answer the question § {#the-dial-and-who-notices}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-dial-and-who-notices}; Two Hours at 12 tok/s — On Battery covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.5758272229995782,
   "ttft_ms": 733,
   "tokens_in": 7056,
   "tokens_out": 21,
   "cached_tokens": 32,
   "cites": [
    "the-dial-and-who-notices"
   ],
   "gates": {
    "cites": [
     "the-dial-and-who-notices"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-01",
   "kind": "off-page"
  },
  {
   "slug": "how-we-work",
   "q": "what is the postal address of the workshop that ran this?",
   "ok": true,
   "answer": "the article does not answer the question about 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}; The open call — a kid, an elder, and a tired parent walk into the cove covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.6178010280000308,
   "ttft_ms": 796,
   "tokens_in": 4732,
   "tokens_out": 25,
   "cached_tokens": 32,
   "cites": [
    "the-plain-english-version"
   ],
   "gates": {
    "cites": [
     "the-plain-english-version"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-02",
   "kind": "off-page"
  },
  {
   "slug": "llms-txt",
   "q": "how many people subscribe to this site's feed?",
   "ok": true,
   "answer": "the article does not answer 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}; The Same Sixteen covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.52485835600055,
   "ttft_ms": 1133,
   "tokens_in": 12259,
   "tokens_out": 26,
   "cached_tokens": 32,
   "cites": [
    "does-anyone-fetch-it"
   ],
   "gates": {
    "cites": [
     "does-anyone-fetch-it"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-03",
   "kind": "off-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 say what the next article on this site will be about § {#the-rest-of-the-seminar}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-rest-of-the-seminar}; The open call — a kid, an elder, and a tired parent walk into the cove covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 11.535239026999989,
   "ttft_ms": 10661,
   "tokens_in": 82421,
   "tokens_out": 29,
   "cached_tokens": 32,
   "cites": [
    "the-rest-of-the-seminar"
   ],
   "gates": {
    "cites": [
     "the-rest-of-the-seminar"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-04",
   "kind": "off-page"
  },
  {
   "slug": "two-hours-on-battery",
   "q": "what did this cost in electricity at my own utility's rate?",
   "ok": false,
   "answer": "the article does not answer this question § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.",
   "served": "this page doesn't say. the nearest it gets is § {#a-few-words-this-page-leans-on}; The outside judges — four rival labs re-check our work covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 10.846449335000216,
   "ttft_ms": 1087,
   "tokens_in": 10855,
   "tokens_out": 35,
   "cached_tokens": 32,
   "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": [],
    "new_noun_tokens": [
     "two-hours-at-12-tok-s-the-test-that-named-the-page"
    ],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": true,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "two-hours-at-12-tok-s-the-test-that-named-the-page"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "12"
   ],
   "figures_verbatim": true,
   "cites_valid": true,
   "redaction_hits": 0,
   "id": "off-05",
   "kind": "off-page"
  },
  {
   "slug": "reading-is-fast",
   "q": "who won the football world cup in 2022?",
   "ok": true,
   "answer": "the article does not answer the question § {#the-mystery-stated-honestly}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-mystery-stated-honestly}; The Typist and the Developer covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 10.624138117999792,
   "ttft_ms": 351,
   "tokens_in": 5290,
   "tokens_out": 19,
   "cached_tokens": 32,
   "cites": [
    "the-mystery-stated-honestly"
   ],
   "gates": {
    "cites": [
     "the-mystery-stated-honestly"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-06",
   "kind": "off-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 the question § {#the-moment-this-page-is-about}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-moment-this-page-is-about}; Fifty-Seven Milliseconds: What a Diffusion Step Actually Buys covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 10.609116806000202,
   "ttft_ms": 439,
   "tokens_in": 4446,
   "tokens_out": 22,
   "cached_tokens": 32,
   "cites": [
    "the-moment-this-page-is-about"
   ],
   "gates": {
    "cites": [
     "the-moment-this-page-is-about"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-07",
   "kind": "off-page"
  },
  {
   "slug": "the-move",
   "q": "can you write a python script that reproduces this for me?",
   "ok": true,
   "answer": "the article does not answer this question § {#the-machine}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-machine}; The August arrivals — the fresh class sits the house exams covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 10.522931903999961,
   "ttft_ms": 10371,
   "tokens_in": 5981,
   "tokens_out": 14,
   "cached_tokens": 0,
   "cites": [
    "the-machine"
   ],
   "gates": {
    "cites": [
     "the-machine"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-08",
   "kind": "off-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 § {#how-to-check-our-work-and-see-it-live}.",
   "served": "this page doesn't say. the nearest it gets is § {#how-to-check-our-work-and-see-it-live}; A Rig Your Friend Already Owns covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.5260062090001156,
   "ttft_ms": 452,
   "tokens_in": 5221,
   "tokens_out": 31,
   "cached_tokens": 32,
   "cites": [
    "how-to-check-our-work-and-see-it-live"
   ],
   "gates": {
    "cites": [
     "how-to-check-our-work-and-see-it-live"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-09",
   "kind": "off-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 answer how many hours a week the people who ran this work § {#six-worlds-for-a-print-lab-that-is-coming-soon}.",
   "served": "this page doesn't say. the nearest it gets is § {#six-worlds-for-a-print-lab-that-is-coming-soon}; A Rig Your Friend Already Owns covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.463464489999751,
   "ttft_ms": 242,
   "tokens_in": 2634,
   "tokens_out": 39,
   "cached_tokens": 32,
   "cites": [
    "six-worlds-for-a-print-lab-that-is-coming-soon"
   ],
   "gates": {
    "cites": [
     "six-worlds-for-a-print-lab-that-is-coming-soon"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-10",
   "kind": "off-page"
  },
  {
   "slug": "outside-judges",
   "q": "what is this workshop's hourly rate for consulting work?",
   "ok": true,
   "answer": "the article does not answer the question § {#the-rest-of-the-seminar}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-rest-of-the-seminar}; qwen3.8:27b across four house benches: one seat filled, one floor missed covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.369762594000349,
   "ttft_ms": 925,
   "tokens_in": 10003,
   "tokens_out": 21,
   "cached_tokens": 32,
   "cites": [
    "the-rest-of-the-seminar"
   ],
   "gates": {
    "cites": [
     "the-rest-of-the-seminar"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-11",
   "kind": "off-page"
  },
  {
   "slug": "the-typist-and-the-developer",
   "q": "what is this workshop's annual revenue?",
   "ok": false,
   "answer": "the article does not say so § {#the-typist-and-the-developer}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-typist}; Reading is fast, writing is slow — why AI answers arrive word by word covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 1.1376700009996057,
   "ttft_ms": 803,
   "tokens_in": 5391,
   "tokens_out": 20,
   "cached_tokens": 32,
   "cites": [],
   "gates": {
    "cites": [],
    "cites_dropped": [
     "the-typist-and-the-developer"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": true,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "cite: 1 cite(s) not in this page's anchors: the-typist-and-the-developer",
     "cite: no valid cite"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "the-typist-and-the-developer"
    ]
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": false,
   "redaction_hits": 0,
   "id": "off-12",
   "kind": "off-page"
  },
  {
   "slug": "compression-is-the-objective",
   "q": "how would these numbers change on windows instead?",
   "ok": true,
   "answer": "the article does not say how these numbers would change on windows § {#how-to-check-our-work-and-see-it-live}.",
   "served": "this page doesn't say. the nearest it gets is § {#how-to-check-our-work-and-see-it-live}; The compressed photograph — what those Q4_K_M tags actually mean covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 0.7318202739998014,
   "ttft_ms": 385,
   "tokens_in": 5251,
   "tokens_out": 33,
   "cached_tokens": 32,
   "cites": [
    "how-to-check-our-work-and-see-it-live"
   ],
   "gates": {
    "cites": [
     "how-to-check-our-work-and-see-it-live"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-13",
   "kind": "off-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 say what other reviewers said about this piece after it was published § {#the-author-of-this-page-is-a-contestant-in-it}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-author-of-this-page-is-a-contestant-in-it}; Three New Voices at the Narrator's Chair covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 9.992776596999647,
   "ttft_ms": 6557,
   "tokens_in": 63359,
   "tokens_out": 40,
   "cached_tokens": 32,
   "cites": [
    "the-author-of-this-page-is-a-contestant-in-it"
   ],
   "gates": {
    "cites": [
     "the-author-of-this-page-is-a-contestant-in-it"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-14",
   "kind": "off-page"
  },
  {
   "slug": "the-new-kid",
   "q": "how does this compare to a result published in 2028?",
   "ok": false,
   "answer": "the article does not answer this question § {#the-limits}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-arrival}; The Instrument Travels covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 9.303062312000293,
   "ttft_ms": 7057,
   "tokens_in": 14843,
   "tokens_out": 14,
   "cached_tokens": 32,
   "cites": [],
   "gates": {
    "cites": [],
    "cites_dropped": [
     "the-limits"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": true,
    "new_noun": false,
    "blocked": false,
    "directive_hit": false
   },
   "gate_detail": {
    "reasons": [
     "cite: 1 cite(s) not in this page's anchors: the-limits",
     "cite: no valid cite"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "the-limits"
    ]
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": false,
   "redaction_hits": 0,
   "id": "off-15",
   "kind": "off-page"
  },
  {
   "slug": "where-your-question-goes",
   "q": "which country is the workshop's business registered in?",
   "ok": true,
   "answer": "the article does not answer this question § {#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}; The map nobody picks up — and whether it helps when it arrives covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 9.250519889000316,
   "ttft_ms": 391,
   "tokens_in": 4309,
   "tokens_out": 26,
   "cached_tokens": 32,
   "cites": [
    "the-first-promise-your-visit-stays-between-us"
   ],
   "gates": {
    "cites": [
     "the-first-promise-your-visit-stays-between-us"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-16",
   "kind": "off-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}",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 9.174233223000556,
   "ttft_ms": 242,
   "tokens_in": 1920,
   "tokens_out": 27,
   "cached_tokens": 32,
   "cites": [
    "for-the-technically-curious"
   ],
   "gates": {
    "cites": [
     "for-the-technically-curious"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-17",
   "kind": "off-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}.",
   "served": "this page doesn't say. the nearest it gets is § {#what-it-is}; The Beat Lab, asked and answered covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 9.41520732799927,
   "ttft_ms": 9007,
   "tokens_in": 30938,
   "tokens_out": 20,
   "cached_tokens": 32,
   "cites": [
    "what-it-is"
   ],
   "gates": {
    "cites": [
     "what-it-is"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-18",
   "kind": "off-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 answer what this measurement would look like at twice the batch size § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-part-nobody-warns-you-about-the-whole-payroll-needs-an}; The compressed photograph — what those Q4_K_M tags actually mean covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 9.542193558999315,
   "ttft_ms": 7209,
   "tokens_in": 7421,
   "tokens_out": 42,
   "cached_tokens": 32,
   "cites": [
    "the-part-nobody-warns-you-about-the-whole-payroll-needs-an"
   ],
   "gates": {
    "cites": [
     "the-part-nobody-warns-you-about-the-whole-payroll-needs-an"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-19",
   "kind": "off-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 answer 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}; How a Vision Model Sees: Eyes for a Machine That Reads covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 0.8646666939994248,
   "ttft_ms": 452,
   "tokens_in": 6255,
   "tokens_out": 27,
   "cached_tokens": 32,
   "cites": [
    "a-different-kind-of-row"
   ],
   "gates": {
    "cites": [
     "a-different-kind-of-row"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-20",
   "kind": "off-page"
  },
  {
   "slug": "seat-trials",
   "q": "how many models will sit this exam next year?",
   "ok": true,
   "answer": "the article does not answer 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.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 0.7585206330004439,
   "ttft_ms": 626,
   "tokens_in": 6988,
   "tokens_out": 21,
   "cached_tokens": 32,
   "cites": [
    "the-instrument"
   ],
   "gates": {
    "cites": [
     "the-instrument"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "redacted": false,
    "figure_unverified": false,
    "uncited": false,
    "new_noun": false,
    "blocked": 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,
   "id": "off-21",
   "kind": "off-page"
  }
 ],
 "verdicts": {
  "on_page_answered": false,
  "non_verbatim_figures": false,
  "off_page_abstained": false,
  "redaction_hits": true
 },
 "passed": false
}