{
 "schema_version": "1.0",
 "run_utc": "2026-09-09T18:45:56Z",
 "arm": "warm",
 "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": 32,
  "non_verbatim_figures": 3,
  "uncited": 1,
  "off_page_total": 21,
  "off_page_abstained": 10,
  "off_page_abstained_by_gate": 4,
  "off_page_abstained_by_model": 6,
  "on_page_abstained": 7,
  "off_page_cited": 17,
  "redaction_hits": 0,
  "seat_errors": 0,
  "p50_seconds": 4.603,
  "p95_seconds": 13.504
 },
 "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 outside this house, six of which read, with every reply being held to a standard of speaking in the town's own tongue and using only facts present in the context § {#the-chair-and-who-sat-it-before}. the article notes that the reasoning for GLM 5.3 was withheld and that the kit's persona blocks and sealed bundle interiors were not included § {#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 outside this house, six of which read, with every reply being held to a standard of speaking in the town's own tongue and using only facts present in the context § {#the-chair-and-who-sat-it-before}. the article notes that the reasoning for GLM 5.3 was withheld and that the kit's persona blocks and sealed bundle interiors were not included § {#what-is-withheld-with-its-refusal-class-and-its-sha}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 13.5255025259994,
   "ttft_ms": 11035,
   "tokens_in": 82427,
   "tokens_out": 142,
   "cached_tokens": 32,
   "cites": [
    "the-bill",
    "the-chair-and-who-sat-it-before"
   ],
   "gates": {
    "cites": [
     "the-bill",
     "the-chair-and-who-sat-it-before"
    ],
    "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",
    "5.3"
   ],
   "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, and a cluster bootstrap over those 36 cases put that rate at [0.444, 0.638], an interval that covers 0.5 § {#head-to-head}. the narrator's chair job was moved out of this round before pre-registration was written because it was the most code and the least defensible number on the page § {#two-strangers-at-the-door}.",
   "served": "the blind head-to-head used 36 cases and did not separate the two arms § {#head-to-head}. the panel's pooled preference rate was 0.544 for Claude Fable 5.1, and a cluster bootstrap over those 36 cases put that rate at [0.444, 0.638], an interval that covers 0.5 § {#head-to-head}. the narrator's chair job was moved out of this round before pre-registration was written because it was the most code and the least defensible number on the page § {#two-strangers-at-the-door}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 12.990832392000812,
   "ttft_ms": 727,
   "tokens_in": 26568,
   "tokens_out": 141,
   "cached_tokens": 26304,
   "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": 11.61231586500071,
   "ttft_ms": 240,
   "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 § {#where-these-answers-come-from}. the answers are derived from the lab's own question bank and are not written twice § {#the-beat-lab}. nothing outside the twenty-seven gets an invented answer § {#the-beat-lab}.",
   "served": "the page carries twenty-seven answers and no model is asked for any answer on this page § {#where-these-answers-come-from}. the answers are derived from the lab's own question bank and are not written twice § {#the-beat-lab}. nothing outside the twenty-seven gets an invented answer § {#the-beat-lab}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 11.732972081001208,
   "ttft_ms": 352,
   "tokens_in": 4465,
   "tokens_out": 74,
   "cached_tokens": 32,
   "cites": [
    "where-these-answers-come-from"
   ],
   "gates": {
    "cites": [
     "where-these-answers-come-from"
    ],
    "cites_dropped": [
     "the-beat-lab"
    ],
    "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-beat-lab"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "the-beat-lab"
    ]
   },
   "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, who was unblinded, stated that the only adapter they preferred was the one-artist control, which they noted might be slightly better than the untouched version on the request Schwerelos § {#one-artist-instead-of-a-tag}. The article does not mention what the listener preferred regarding the wide adapter, noting instead that the ear's verdict on the wide adapter was that it added weird rhythms that the non-adapter version did not § {#one-artist-instead-of-a-tag}. The text notes that 41 tracks were held back for a test not yet run and that the listener's preference for the control was only heard on two requests § {#what-we-did-not-measure}.",
   "served": "The adapter was trained on 159 tracks from 41 releases § {#a-genre-not-a-composer}. The one listener, who was unblinded, stated that the only adapter they preferred was the one-artist control, which they noted might be slightly better than the untouched version on the request Schwerelos § {#one-artist-instead-of-a-tag}. The article does not mention what the listener preferred regarding the wide adapter, noting instead that the ear's verdict on the wide adapter was that it added weird rhythms that the non-adapter version did not § {#one-artist-instead-of-a-tag}. The text notes that 41 tracks were held back for a test not yet run and that the listener's preference for the control was only heard on two requests § {#what-we-did-not-measure}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 14.249072640999657,
   "ttft_ms": 1659,
   "tokens_in": 12906,
   "tokens_out": 181,
   "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",
    "41"
   ],
   "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}. thirty-two of these mastered copies 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 notes that the raw renders sit in audio/ and are what every measured number on this page was read off § {#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}. thirty-two of these mastered copies 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 notes that the raw renders sit in audio/ and are what every measured number on this page was read off § {#how-to-listen}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 12.72364439300145,
   "ttft_ms": 1011,
   "tokens_in": 14176,
   "tokens_out": 130,
   "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"
   ],
   "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 mention what was left out, moved, or not measured in relation to these specific training times § {#the-bill}.",
   "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 mention what was left out, moved, or not measured in relation to these specific training times § {#the-bill}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.5044282379985816,
   "ttft_ms": 361,
   "tokens_in": 5430,
   "tokens_out": 92,
   "cached_tokens": 0,
   "cites": [
    "sousa-a-hundred-and-six-marches",
    "bach-the-pianist-who-freed-her-own-recordings",
    "the-bill"
   ],
   "gates": {
    "cites": [
     "sousa-a-hundred-and-six-marches",
     "bach-the-pianist-who-freed-her-own-recordings",
     "the-bill"
    ],
    "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 will 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 will take to test § {#what-we-did-not-measure}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.2805414120011847,
   "ttft_ms": 354,
   "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": 6.800604217,
   "ttft_ms": 412,
   "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}. the article notes that it did not measure the gpu-server half of the outage test § {#two-hours-at-12-tok-s-the-test-that-named-the-page}.",
   "served": "this page doesn't say. the nearest it gets is § {#two-hours-at-12-tok-s-the-test-that-named-the-page}; The outside judges — four rival labs re-check our work covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 4.133100989000013,
   "ttft_ms": 961,
   "tokens_in": 10856,
   "tokens_out": 91,
   "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",
    "12",
    "12"
   ],
   "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": false,
   "answer": "the ranked model qwen3.6:27b landed at kill-recall 11/12 and preservation 8/9 § {#the-instrument-travels}. the article notes that the preservation delta is one item, which is under the pre-registered two-item tie band and reads TIED § {#the-instrument-travels}.",
   "served": "this page doesn't say. the nearest it gets is § {#schema-perfect-and-still-blocked}; qwen3.8:27b across four house benches: one seat filled, one floor missed covers it more directly.",
   "abstained": true,
   "abstain_source": "gate",
   "seconds": 3.8831232890006504,
   "ttft_ms": 804,
   "tokens_in": 8389,
   "tokens_out": 75,
   "cached_tokens": 32,
   "cites": [],
   "gates": {
    "cites": [],
    "cites_dropped": [
     "the-instrument-travels"
    ],
    "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-instrument-travels",
     "cite: no valid cite"
    ],
    "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": false,
   "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 stay the same 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 anything that was left out, moved, or not measured § {#for-the-technically-curious}.",
   "served": "the same dog, same curl, and same tucked paws stay the same 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 anything that was left out, moved, or not measured § {#for-the-technically-curious}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.479377227000441,
   "ttft_ms": 448,
   "tokens_in": 1919,
   "tokens_out": 86,
   "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": "the 600 → 450 W cap costs the dense arm 2.0% of throughput and buys back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. at concurrency 16, the throughput moved from 94.6 to 92.7 tok/s per stream § {#the-answer-in-one-paragraph}. the article notes that it did not measure a long-context or prefill-heavy workload, which could move the 2% either way § {#what-this-page-does-not-say}.",
   "served": "the 600 → 450 W cap costs the dense arm 2.0% of throughput and buys back 138 W, 11 °C, and a 28% jump in efficiency § {#the-answer-in-one-paragraph}. at concurrency 16, the throughput moved from 94.6 to 92.7 tok/s per stream § {#the-answer-in-one-paragraph}. the article notes that it did not measure a long-context or prefill-heavy workload, which could move the 2% either way § {#what-this-page-does-not-say}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.6029171610007324,
   "ttft_ms": 434,
   "tokens_in": 7066,
   "tokens_out": 140,
   "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",
    "16",
    "94.6",
    "92.7",
    "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 mention how long the genie's voice takes to arrive or how long the machine takes to play a beat § {#what-it-is}.",
   "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 mention how long the genie's voice takes to arrive or how long the machine takes to play a beat § {#what-it-is}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.2012747610006045,
   "ttft_ms": 2262,
   "tokens_in": 30947,
   "tokens_out": 88,
   "cached_tokens": 32,
   "cites": [
    "the-sound-is-made-on-your-device",
    "what-happens-when-you-ask-the-genie",
    "what-it-is"
   ],
   "gates": {
    "cites": [
     "the-sound-is-made-on-your-device",
     "what-happens-when-you-ask-the-genie",
     "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": [
    "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 § {#one-card-both-jobs-at-once}. the article notes that it did not instrument how much traffic there was § {#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 § {#one-card-both-jobs-at-once}. the article notes that it did not instrument how much traffic there was § {#what-we-did-not-measure-said-out-loud}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.7821269139985816,
   "ttft_ms": 394,
   "tokens_in": 5393,
   "tokens_out": 82,
   "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 96G card was 3.4× faster than the 3090 for the FLUX.2 klein-4B sketch artist § {#the-table-that-answers-the-question}. for the 512×512 live default sketch size, the 96G card's median was 0.26 s while the 3090's was 0.88 s § {#the-sketch-ladder-the-number-the-game-lives-on}. the article notes that it did not test 8–12 GB cards § {#three-findings-we-didnt-order}.",
   "served": "the 96G card was 3.4× faster than the 3090 for the FLUX.2 klein-4B sketch artist § {#the-table-that-answers-the-question}. for the 512×512 live default sketch size, the 96G card's median was 0.26 s while the 3090's was 0.88 s § {#the-sketch-ladder-the-number-the-game-lives-on}. the article notes that it did not test 8–12 GB cards § {#three-findings-we-didnt-order}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 3.0615397620003932,
   "ttft_ms": 435,
   "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 other token counts or prefill times for that specific resolution § {#finding-one-a-picture-is-199-tokens-at-896-px-and-the}.",
   "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": 2.268858948998968,
   "ttft_ms": 751,
   "tokens_in": 10022,
   "tokens_out": 101,
   "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",
    "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, recording 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 in relation to this specific painter § {#finding-four-the-argument-with-our-own-settings-and-what-it}.",
   "served": "the distilled painter is the sharpest and fastest cell in the whole second run, recording 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 in relation to this specific painter § {#finding-four-the-argument-with-our-own-settings-and-what-it}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.4847902589990554,
   "ttft_ms": 345,
   "tokens_in": 5221,
   "tokens_out": 97,
   "cached_tokens": 32,
   "cites": [
    "finding-four-the-argument-with-our-own-settings-and-what-it"
   ],
   "gates": {
    "cites": [
     "finding-four-the-argument-with-our-own-settings-and-what-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": [
    "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}. the article does not mention any other file sizes or dimensions § {#the-world-is-a-file}.",
   "served": "the world is written in one YAML file that is 16,705 lines § {#the-world-is-a-file}. the article does not mention any other file sizes or dimensions § {#the-world-is-a-file}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.4460056550014997,
   "ttft_ms": 395,
   "tokens_in": 5903,
   "tokens_out": 54,
   "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 a reader wide enough to hold an archive like the sequence databases and the Protein Data Bank all at once § {#the-first-engine-the-archive-nobody-had-read}. the second engine involves a compression that captures a generating rule to emit entries that no row of the data contains § {#the-second-engine-the-rooms-the-rules-imply}. structural biologists noted that what was left out included 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 a reader wide enough to hold an archive like the sequence databases and the Protein Data Bank all at once § {#the-first-engine-the-archive-nobody-had-read}. the second engine involves a compression that captures a generating rule to emit entries that no row of the data contains § {#the-second-engine-the-rooms-the-rules-imply}. structural biologists noted that what was left out included 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": 3.0837625870008196,
   "ttft_ms": 564,
   "tokens_in": 5250,
   "tokens_out": 159,
   "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 are the compression, acting as the codebook for a corpus § {#the-punchline}. it points to the Hutter Prize, which charges for everything including self-extracting entries and every decompressor byte counted § {#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 are the compression, acting as the codebook for a corpus § {#the-punchline}. it points to the Hutter Prize, which charges for everything including self-extracting entries and every decompressor byte counted § {#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": 2.1927184550004313,
   "ttft_ms": 362,
   "tokens_in": 5260,
   "tokens_out": 99,
   "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 on 2026-08-15 § {#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 removed a penalties stage from the sampler pipeline § {#the-hunt-change-one-thing}. 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 on 2026-08-15 § {#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 removed a penalties stage from the sampler pipeline § {#the-hunt-change-one-thing}. the article notes that the quality half of this change remains unmeasured § {#the-part-that-isnt-about-speed}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 2.5403441109992855,
   "ttft_ms": 487,
   "tokens_in": 7253,
   "tokens_out": 127,
   "cached_tokens": 32,
   "cites": [
    "the-day-the-box-got-faster",
    "the-hunt-change-one-thing",
    "the-part-that-isnt-about-speed"
   ],
   "gates": {
    "cites": [
     "the-day-the-box-got-faster",
     "the-hunt-change-one-thing",
     "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",
    "2026-08-15",
    "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 q8 build was 28% slower in tokens per second than the q4 build § {#the-same-brain-at-two-compressions}. the article does not explicitly state the exact speed difference between the uncompressed original and the q4 build, though it provides their individual speeds § {#the-same-question-down-the-whole-ladder}.",
   "served": "the uncompressed original was 3.4× the speed of the trained-4-bit build § {#the-same-question-down-the-whole-ladder}. the q8 build was 28% slower in tokens per second than the q4 build § {#the-same-brain-at-two-compressions}. the article does not explicitly state the exact speed difference between the uncompressed original and the q4 build, though it provides their individual speeds § {#the-same-question-down-the-whole-ladder}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 9.225190201001169,
   "ttft_ms": 778,
   "tokens_in": 8235,
   "tokens_out": 114,
   "cached_tokens": 32,
   "cites": [
    "the-same-question-down-the-whole-ladder",
    "the-same-brain-at-two-compressions"
   ],
   "gates": {
    "cites": [
     "the-same-question-down-the-whole-ladder",
     "the-same-brain-at-two-compressions"
    ],
    "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",
    "8",
    "28",
    "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 did not measure the speed of 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 did not measure the speed of big cloud models § {#what-this-page-does-not-say}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 1.8824692580001283,
   "ttft_ms": 735,
   "tokens_in": 7434,
   "tokens_out": 88,
   "cached_tokens": 32,
   "cites": [
    "the-payroll-and-the-meeting",
    "the-tag-with-two-numbers",
    "what-this-page-does-not-say"
   ],
   "gates": {
    "cites": [
     "the-payroll-and-the-meeting",
     "the-tag-with-two-numbers",
     "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 a prompt at the same time since the text already exists § {#reading-is-a-group-photo}. writing is slower because it is serial, as the model must choose tokens one at a time because the future of the sentence does not yet exist § {#writing-is-one-at-a-time}. the article does not state what the reading speed would be if the guesser were turned off § {#the-number-that-argued-back}.",
   "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 a prompt at the same time since the text already exists § {#reading-is-a-group-photo}. writing is slower because it is serial, as the model must choose tokens one at a time because the future of the sentence does not yet exist § {#writing-is-one-at-a-time}. the article does not state what the reading speed would be if the guesser were turned off § {#the-number-that-argued-back}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 9.139572445999875,
   "ttft_ms": 358,
   "tokens_in": 5292,
   "tokens_out": 141,
   "cached_tokens": 32,
   "cites": [
    "a-measurement-from-our-own-card",
    "reading-is-a-group-photo",
    "writing-is-one-at-a-time",
    "the-number-that-argued-back"
   ],
   "gates": {
    "cites": [
     "a-measurement-from-our-own-card",
     "reading-is-a-group-photo",
     "writing-is-one-at-a-time",
     "the-number-that-argued-back"
    ],
    "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 specific game being asked about, picking up the edition's own rulebook and any matched correction documents to rank passages by 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 specific game being asked about, picking up the edition's own rulebook and any matched correction documents to rank passages by 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": 9.342946495000433,
   "ttft_ms": 382,
   "tokens_in": 5673,
   "tokens_out": 126,
   "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 on all five pre-registered gates § {#the-classifier-seat-five-gates-all-pass-faster}, but it failed the judge seat by achieving preservation 11 of 16 against a floor of 13 § {#the-judge-seat-and-the-floor-it-missed}. the article notes that no baseline was scored for the classifier seat and that the judge seat's preservation miss is not a demonstration that the arm cannot preserve § {#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 on all five pre-registered gates § {#the-classifier-seat-five-gates-all-pass-faster}, but it failed the judge seat by achieving preservation 11 of 16 against a floor of 13 § {#the-judge-seat-and-the-floor-it-missed}. the article notes that no baseline was scored for the classifier seat and that the judge seat's preservation miss is not a demonstration that the arm cannot preserve § {#the-classifier-seat-five-gates-all-pass-faster} § {#the-judge-seat-and-the-floor-it-missed}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 9.38490410399936,
   "ttft_ms": 928,
   "tokens_in": 14843,
   "tokens_out": 150,
   "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"
   ],
   "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": 8.343136340001365,
   "ttft_ms": 1288,
   "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 § {#five-things-before-any-figure} and the round's metered spend 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-author-of-this-page-is-a-contestant-in-it}.",
   "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": 8.761448004999693,
   "ttft_ms": 7126,
   "tokens_in": 63362,
   "tokens_out": 101,
   "cached_tokens": 32,
   "cites": [
    "five-things-before-any-figure",
    "2-2826-over-56-metered-calls-against-38-49-of-caps",
    "the-author-of-this-page-is-a-contestant-in-it"
   ],
   "gates": {
    "cites": [
     "five-things-before-any-figure",
     "2-2826-over-56-metered-calls-against-38-49-of-caps",
     "the-author-of-this-page-is-a-contestant-in-it"
    ],
    "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": 1.7446481799997855,
   "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 them, and draft the articles, while the human operator notices the initial spark, negotiates the roster, reviews and signs off on hardened plans, steers execution at checkpoints, and provides the final word on release § {#the-thorough-walk}. the human makes the work true by deciding what is worth testing and what the numbers mean, whereas agents make the work bigger by testing more models and verifying more claims § {#the-thorough-walk}. 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 them, and draft the articles, while the human operator notices the initial spark, negotiates the roster, reviews and signs off on hardened plans, steers execution at checkpoints, and provides the final word on release § {#the-thorough-walk}. the human makes the work true by deciding what is worth testing and what the numbers mean, whereas agents make the work bigger by testing more models and verifying more claims § {#the-thorough-walk}. 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": 5.404616978999911,
   "ttft_ms": 334,
   "tokens_in": 4735,
   "tokens_out": 158,
   "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 original 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 original GPU box § {#what-moved}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 0.9287165610003285,
   "ttft_ms": 420,
   "tokens_in": 5983,
   "tokens_out": 71,
   "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 sat the chairs, with only five of the eleven arms sitting all five chairs § {#roster}. 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 sat the chairs, with only five of the eleven arms sitting all five chairs § {#roster}. 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": 4.800539891999506,
   "ttft_ms": 3276,
   "tokens_in": 29978,
   "tokens_out": 61,
   "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 charming narrator who invents canon is considered a worse narrator than a stiff one who does not § {#floor-1-canon}. the article does not mention what happened to this 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": 4.844011188000877,
   "ttft_ms": 1052,
   "tokens_in": 16350,
   "tokens_out": 79,
   "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 article notes that the judges never saw 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 article notes that the judges never saw user data, a character's private canon, or telemetry § {#boundary}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.603912013999434,
   "ttft_ms": 1616,
   "tokens_in": 10010,
   "tokens_out": 68,
   "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 fresh models arrived that week, and all four broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. specifically, the failure rates for the cohort were 16.3%, 51.2%, 55.8% and 62.8% § {#exam-one-the-judge-chair}. the article notes that OLMo 3.1 32B Think was on the seat table and in the residency census but was never on the voice leg's roster § {#exam-two-the-narrators-chair}.",
   "served": "four fresh models arrived that week, and all four broke the response contract on more than 10% of calls § {#exam-one-the-judge-chair}. specifically, the failure rates for the cohort were 16.3%, 51.2%, 55.8% and 62.8% § {#exam-one-the-judge-chair}. the article notes that OLMo 3.1 32B Think was on the seat table and in the residency census but was never on the voice leg's roster § {#exam-two-the-narrators-chair}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 6.608764112999779,
   "ttft_ms": 3723,
   "tokens_in": 10941,
   "tokens_out": 130,
   "cached_tokens": 32,
   "cites": [
    "exam-one-the-judge-chair",
    "exam-two-the-narrators-chair"
   ],
   "gates": {
    "cites": [
     "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",
    "16.3",
    "51.2",
    "55.8",
    "62.8",
    "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}. note that the article mentions one candidate was blocked at the billing probe and never ran § {#the-instrument}.",
   "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}. note that the article mentions one candidate was blocked at the billing probe and never ran § {#the-instrument}.",
   "abstained": false,
   "abstain_source": null,
   "seconds": 4.484393421000277,
   "ttft_ms": 3587,
   "tokens_in": 6992,
   "tokens_out": 75,
   "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": [
    "23/27",
    "13/16"
   ],
   "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 24 distinct model tags were 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": 14.520051522000358,
   "ttft_ms": 750,
   "tokens_in": 10114,
   "tokens_out": 131,
   "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 states that each row carries the licence, what that licence asks of us, and what it permits you § {#how-to-read-this-page}. the method for each read is named once per table so that a reader can repeat the read themselves § {#how-to-read-this-page}. the article notes that unread models are withheld and that some rows are receipts rather than full readings § {#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": 13.097650288000295,
   "ttft_ms": 1139,
   "tokens_in": 8388,
   "tokens_out": 97,
   "cached_tokens": 32,
   "cites": [
    "how-to-read-this-page",
    "provenance-063a00"
   ],
   "gates": {
    "cites": [
     "how-to-read-this-page",
     "provenance-063a00"
    ],
    "cites_dropped": [],
    "new_noun_tokens": [
     "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",
     "new noun: 1 token(s) the article does not carry"
    ],
    "new_noun_tokens": [
     "provenance-063a00"
    ],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": []
   },
   "figures": [
    "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-moment-this-page-is-about}.",
   "served": "this page doesn't say. the nearest it gets is § {#the-moment-this-page-is-about}; Two Hours at 12 tok/s — On Battery covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 2.0407696410002245,
   "ttft_ms": 1307,
   "tokens_in": 7056,
   "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-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 § {#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": 1.9624714389992732,
   "ttft_ms": 978,
   "tokens_in": 4732,
   "tokens_out": 18,
   "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": 2.06499822799924,
   "ttft_ms": 1757,
   "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": false,
   "answer": "the article does not say what the next article on this site will be about § {#the-exam}.",
   "served": "this page doesn't say. the nearest it gets is § {#come-down-into-the-cove}; 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": 11.297510637999949,
   "ttft_ms": 10634,
   "tokens_in": 82421,
   "tokens_out": 22,
   "cached_tokens": 32,
   "cites": [],
   "gates": {
    "cites": [],
    "cites_dropped": [
     "the-exam"
    ],
    "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-exam",
     "cite: no valid cite"
    ],
    "new_noun_tokens": [],
    "new_noun_tokens_withheld": 0,
    "cites_dropped": [
     "the-exam"
    ]
   },
   "figures": [],
   "figures_verbatim": true,
   "cites_valid": false,
   "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": 10.949342478999824,
   "ttft_ms": 867,
   "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": 10.55874500400023,
   "ttft_ms": 795,
   "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": 10.703324090000024,
   "ttft_ms": 10446,
   "tokens_in": 4446,
   "tokens_out": 22,
   "cached_tokens": 0,
   "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": 0.4952836029988248,
   "ttft_ms": 397,
   "tokens_in": 5981,
   "tokens_out": 14,
   "cached_tokens": 32,
   "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 answer the question § {#what-a-step-is-in-one-paragraph}.",
   "served": "this page doesn't say. the nearest it gets is § {#what-a-step-is-in-one-paragraph}; A Rig Your Friend Already Owns covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.4397921359995962,
   "ttft_ms": 430,
   "tokens_in": 5221,
   "tokens_out": 24,
   "cached_tokens": 32,
   "cites": [
    "what-a-step-is-in-one-paragraph"
   ],
   "gates": {
    "cites": [
     "what-a-step-is-in-one-paragraph"
    ],
    "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": 1.489068328999565,
   "ttft_ms": 412,
   "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 about the workshop's hourly rate for consulting work § {#what-to-take-with-you}.",
   "served": "this page doesn't say. the nearest it gets is § {#what-to-take-with-you}; qwen3.8:27b across four house benches: one seat filled, one floor missed covers it more directly.",
   "abstained": true,
   "abstain_source": "model",
   "seconds": 1.5102666729999328,
   "ttft_ms": 977,
   "tokens_in": 10003,
   "tokens_out": 30,
   "cached_tokens": 32,
   "cites": [
    "what-to-take-with-you"
   ],
   "gates": {
    "cites": [
     "what-to-take-with-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": "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 what this workshop's annual revenue is § {#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": 1.2221064019995538,
   "ttft_ms": 828,
   "tokens_in": 5391,
   "tokens_out": 27,
   "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": 1.1173437739998917,
   "ttft_ms": 826,
   "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": 10.391999974999635,
   "ttft_ms": 7109,
   "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": 9.150752530000318,
   "ttft_ms": 920,
   "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": 9.633054837999225,
   "ttft_ms": 7157,
   "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 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": 9.609033315999113,
   "ttft_ms": 7056,
   "tokens_in": 1920,
   "tokens_out": 26,
   "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": 9.72947421599929,
   "ttft_ms": 9047,
   "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 this question § {#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": 9.696374975999788,
   "ttft_ms": 7288,
   "tokens_in": 7421,
   "tokens_out": 33,
   "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": 0.8861415650007984,
   "ttft_ms": 404,
   "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": 0.6844864989998314,
   "ttft_ms": 544,
   "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,
  "p50_warm_seconds": false,
  "p95_warm_seconds": false
 },
 "passed": false
}