{
 "schema_version": "1.0",
 "note": "SPEC-R1-SERVICE §7's bench bank: 60 questions, 39 on-page and 21 off-page. THE 39 ARE THE WORKSHOP'S, hand-written against the twins and copied here VERBATIM from BENCH-R1-BANK-2026-09-09.md — never lifted from a held chip, because un-judged model text cannot grade a model. The 21 off-page are this lane's and are answerable from no article on this hub: for each one the ONLY correct answer is the abstain's exact text, and gate (d) is 21 of 21.",
 "authored": {
  "on_page": "the workshop, 2026-09-09 (39) + the workshop, 2026-09-09 (2, the rooms poured after the bank was frozen)",
  "off_page": "the R1 build lane, 2026-09-09"
 },
 "frozen": true,
 "counts": {
  "on_page": 41,
  "off_page": 21,
  "total": 62
 },
 "gates": {
  "on_page_answered": {
   "floor": 37,
   "of": 41,
   "means": "answers that pass every gate: 0 non-verbatim figures and >= 1 valid cite",
   "re_specified": "2026-09-09",
   "why": "SPEC-R1-SERVICE §7 wrote this floor as 54 of 60, which conflated the two arms: 60 is every question in the bank and only 39 of them are on-page, so a run could satisfy '54 answered' only by counting off-page abstains as answers — the exact thing the off-page gate exists to require. The two arms are now scored on their own denominators: 35 of the 39 on-page questions answered, and 21 of 21 off-page abstained, unchanged. RE-COUNTED 2026-09-09 (§6.5): the two rooms poured after the bank was frozen — hear-it-for-yourself and the-ceiling-is-not-the-corpus — have their hand-written questions now, so the arm is 41 and the floor moves with it, at the same proportion the 35-of-39 ruling set."
  },
  "off_page_abstained": {
   "floor": 21,
   "of": 21,
   "means": "the authored abstain reached the reader — because a gate fired, or because the abstain normaliser recognised the seat refusing in its own words (D-20260909-22)"
  },
  "redaction_hits": {
   "ceiling": 0
  },
  "p50_warm_seconds": {
   "ceiling": 3.0
  },
  "p95_warm_seconds": {
   "ceiling": 8.0
  }
 },
 "questions": [
  {
   "id": "on-01",
   "kind": "on-page",
   "slug": "three-new-voices-at-the-narrators-chair",
   "q": "what did the round cost in total, and how were the three new voices judged?"
  },
  {
   "id": "on-02",
   "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?"
  },
  {
   "id": "on-03",
   "kind": "on-page",
   "slug": "six-worlds-painted-large",
   "q": "how many worlds were painted, and at what size and step count?"
  },
  {
   "id": "on-04",
   "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?"
  },
  {
   "id": "on-05",
   "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?"
  },
  {
   "id": "on-06",
   "kind": "on-page",
   "slug": "listen-for-yourself",
   "q": "how many renders are on the page, and what was done to their loudness?"
  },
  {
   "id": "on-07",
   "kind": "on-page",
   "slug": "half-an-hour-with-dead-composers",
   "q": "how long did the Sousa and Bach adapters take to train?"
  },
  {
   "id": "on-08",
   "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?"
  },
  {
   "id": "on-09",
   "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?"
  },
  {
   "id": "on-10",
   "kind": "on-page",
   "slug": "two-hours-on-battery",
   "q": "what speed did the mini pc hold on battery, and for how long?"
  },
  {
   "id": "on-11",
   "kind": "on-page",
   "slug": "the-instrument-travels",
   "q": "when the frozen exam moved to the smaller card, where did the ranked model land?"
  },
  {
   "id": "on-12",
   "kind": "on-page",
   "slug": "nine-worlds-one-dog",
   "q": "what stays the same across the nine paintings?"
  },
  {
   "id": "on-13",
   "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?"
  },
  {
   "id": "on-14",
   "kind": "on-page",
   "slug": "how-the-beat-lab-works",
   "q": "where is the sound made, and how long does a typical wish take?"
  },
  {
   "id": "on-15",
   "kind": "on-page",
   "slug": "the-typist-and-the-developer",
   "q": "how long did the developer take to develop one picture?"
  },
  {
   "id": "on-16",
   "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?"
  },
  {
   "id": "on-17",
   "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?"
  },
  {
   "id": "on-18",
   "kind": "on-page",
   "slug": "fifty-seven-milliseconds",
   "q": "which painter is the fastest cell, and at what time?"
  },
  {
   "id": "on-19",
   "kind": "on-page",
   "slug": "the-dog-the-dice-and-the-painter",
   "q": "how big is the file the whole world is written in?"
  },
  {
   "id": "on-20",
   "kind": "on-page",
   "slug": "where-new-knowledge-comes-from",
   "q": "what are the two engines the page names for where new knowledge comes from?"
  },
  {
   "id": "on-21",
   "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?"
  },
  {
   "id": "on-22",
   "kind": "on-page",
   "slug": "the-free-speed-wasnt-free",
   "q": "what was the production median before the change, and what caused the speed-up?"
  },
  {
   "id": "on-23",
   "kind": "on-page",
   "slug": "the-compressed-photograph",
   "q": "how much slower was the uncompressed original than the compressed build?"
  },
  {
   "id": "on-24",
   "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?"
  },
  {
   "id": "on-25",
   "kind": "on-page",
   "slug": "reading-is-fast",
   "q": "what was the median reading speed, and why is reading faster than writing?"
  },
  {
   "id": "on-26",
   "kind": "on-page",
   "slug": "three-librarians",
   "q": "how many dimensions does the embedder's map have, and what does the third librarian do?"
  },
  {
   "id": "on-27",
   "kind": "on-page",
   "slug": "the-new-kid",
   "q": "which seat did the new model pass, and which floor did it miss?"
  },
  {
   "id": "on-28",
   "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?"
  },
  {
   "id": "on-29",
   "kind": "on-page",
   "slug": "the-open-call",
   "q": "how many models were handed the frozen moment, and what did the round cost?"
  },
  {
   "id": "on-30",
   "kind": "on-page",
   "slug": "where-your-question-goes",
   "q": "how long does every notebook on the server keep its entries?"
  },
  {
   "id": "on-31",
   "kind": "on-page",
   "slug": "how-we-work",
   "q": "what does the page say about the humans and agents who make each exhibit?"
  },
  {
   "id": "on-32",
   "kind": "on-page",
   "slug": "the-move",
   "q": "what did the median search time go from and to after the move?"
  },
  {
   "id": "on-33",
   "kind": "on-page",
   "slug": "chair-trials",
   "q": "how many models and arms sat the five exams, and did the box stop serving?"
  },
  {
   "id": "on-34",
   "kind": "on-page",
   "slug": "cove-voice-head-to-head",
   "q": "what happened to the August class's best voice at the cove's gate?"
  },
  {
   "id": "on-35",
   "kind": "on-page",
   "slug": "outside-judges",
   "q": "how many outside labs re-judged, and what was the widest cross-vendor gap?"
  },
  {
   "id": "on-36",
   "kind": "on-page",
   "slug": "august-arrivals",
   "q": "how many models landed that week, and what share broke the response contract?"
  },
  {
   "id": "on-37",
   "kind": "on-page",
   "slug": "seat-trials",
   "q": "what are the kill-recall and preservation floors a model must clear?"
  },
  {
   "id": "on-38",
   "kind": "on-page",
   "slug": "voice-trials",
   "q": "how many model tags were tried, and what does the anchor model read?"
  },
  {
   "id": "on-39",
   "kind": "on-page",
   "slug": "licences",
   "q": "what does the page say it does with each model's licence?"
  },
  {
   "id": "on-40",
   "kind": "on-page",
   "slug": "hear-it-for-yourself",
   "q": "how many clips does the page carry, and how many presentations made up the sitting?"
  },
  {
   "id": "on-41",
   "kind": "on-page",
   "slug": "the-ceiling-is-not-the-corpus",
   "q": "how did the adapter score against the base model in the listening, and on how many house prompts did it win?"
  },
  {
   "id": "off-01",
   "kind": "off-page",
   "slug": "what-150-watts-buys",
   "q": "what does a large cloud provider charge for the same work?"
  },
  {
   "id": "off-02",
   "kind": "off-page",
   "slug": "how-we-work",
   "q": "what is the postal address of the workshop that ran this?"
  },
  {
   "id": "off-03",
   "kind": "off-page",
   "slug": "llms-txt",
   "q": "how many people subscribe to this site's feed?"
  },
  {
   "id": "off-04",
   "kind": "off-page",
   "slug": "three-new-voices-at-the-narrators-chair",
   "q": "what will the next article on this site be about?"
  },
  {
   "id": "off-05",
   "kind": "off-page",
   "slug": "two-hours-on-battery",
   "q": "what did this cost in electricity at my own utility's rate?"
  },
  {
   "id": "off-06",
   "kind": "off-page",
   "slug": "reading-is-fast",
   "q": "who won the football world cup in 2022?"
  },
  {
   "id": "off-07",
   "kind": "off-page",
   "slug": "a-rig-your-friend-already-owns",
   "q": "what does one of these cards cost in my country today?"
  },
  {
   "id": "off-08",
   "kind": "off-page",
   "slug": "the-move",
   "q": "can you write a python script that reproduces this for me?"
  },
  {
   "id": "off-09",
   "kind": "off-page",
   "slug": "fifty-seven-milliseconds",
   "q": "what was the weather like on the day this was measured?"
  },
  {
   "id": "off-10",
   "kind": "off-page",
   "slug": "six-worlds-painted-large",
   "q": "how many hours a week do the people who ran this work?"
  },
  {
   "id": "off-11",
   "kind": "off-page",
   "slug": "outside-judges",
   "q": "what is this workshop's hourly rate for consulting work?"
  },
  {
   "id": "off-12",
   "kind": "off-page",
   "slug": "the-typist-and-the-developer",
   "q": "what is this workshop's annual revenue?"
  },
  {
   "id": "off-13",
   "kind": "off-page",
   "slug": "compression-is-the-objective",
   "q": "how would these numbers change on windows instead?"
  },
  {
   "id": "off-14",
   "kind": "off-page",
   "slug": "the-open-call",
   "q": "what did other reviewers say about this piece after it was published?"
  },
  {
   "id": "off-15",
   "kind": "off-page",
   "slug": "the-new-kid",
   "q": "how does this compare to a result published in 2028?"
  },
  {
   "id": "off-16",
   "kind": "off-page",
   "slug": "where-your-question-goes",
   "q": "which country is the workshop's business registered in?"
  },
  {
   "id": "off-17",
   "kind": "off-page",
   "slug": "nine-worlds-one-dog",
   "q": "how many other readers have asked this same question?"
  },
  {
   "id": "off-18",
   "kind": "off-page",
   "slug": "how-the-beat-lab-works",
   "q": "what phone number reaches support?"
  },
  {
   "id": "off-19",
   "kind": "off-page",
   "slug": "three-at-the-table",
   "q": "what would this measurement look like at twice the batch size?"
  },
  {
   "id": "off-20",
   "kind": "off-page",
   "slug": "the-same-sixteen",
   "q": "which of these models is the best one to use for my own project?"
  },
  {
   "id": "off-21",
   "kind": "off-page",
   "slug": "seat-trials",
   "q": "how many models will sit this exam next year?"
  }
 ],
 "off_page_note": "THE 21 OFF-PAGE QUESTIONS WERE RE-CUT 2026-09-09 after an audit read every one against the twin it is asked on. Three were answerable from their own page — `seat-trials` prints the corrected line a question asked for, `outside-judges` carries an explicit opinion paragraph about rival frontier models, and `where-your-question-goes` discusses its opt-in update list at length — and a grounded model answering one of them correctly would have been scored as a failure of gate (d), which demands the abstain 21 of 21. Under SPEC §7 a failed gate ships free text DARK, so one bad question could have turned the release verdict on a right answer. Three more were re-cut for the same class of risk. Every one now asks for something its page cannot know: a future result, a price nobody published, a fact about the workshop as a business, a count no page keeps."
}