A kid, an elder, and a tired parent walk into the cove.

How to read this page

Five things, before any figure

• The unit is one question — the three acts below are read one sealed ask at a time: who typed it, who had to answer it, the frozen bytes verbatim, and then the replies, one under another, so you can watch twenty minds meet the same sentence. Four asks were judged; two of them were asked twice with the same words, and both takes print.
• Registered first — everything comparative here was fixed before any model answered: the roster, the scoring rules, the curation rule, even the sentences this page is forbidden to write.
• No leaderboard, and the cards say so — figures print as counts with their denominators, and two figures closer than the registered tie band of 0.5 are within the band: a statement about the instrument’s resolution, not about two models being equal. Every card on this page carries its own band line naming the arms it cannot be separated from, because a rule a reader has to apply on the page’s behalf is not a rule the page is keeping.
• Six reply cards per act, chosen by rule — the same six arms answer every ask in their act, and each act then points at the full set of twenty and names the arms the rule left out, so the page’s picks can be audited against everything it did not pick.
• Every number has a file behind it, and the files this round can publish are on this page — the kit carries the complete scoring artifact (every arm, every seat, every cell, every judge’s note), the seal manifest with full hashes, the internal report, the registered rules and the 39-row fence. What is withheld is named there too, at the size it is.

The words this page leans on

Conflicts, stated plainly

The author of this page is a contestant in it

Claude Fable 5 — the model writing these words — authored the exam scenarios, sits in the round as an arm, and holds one of the seven judge seats; a second Anthropic model holds another. What recusal cures: the two Anthropic seats never scored any Claude arm, so every score the three Claude arms carry came entirely from five rival families — OpenAI, DeepSeek, Moonshot, Mistral, and a locally-hosted Google seat. What recusal does not cure: the questions themselves were chosen by one of the contestants. Both halves of that sentence are true, and the page keeps them together.

And the confound, at the top rather than at the bottom. The three Claude arms are the only occupants of the agent transport, which is also the only transport that holds no cost figure, no client-wall clock and no token counters — so transport is completely confounded with vendor here, and nothing in this round can separate “these models wrote better” from “the agent harness gave its arms more room.” That sentence belongs beside the figures rather than after them; the limits state it in full, with the run that would resolve it — the same three models over a metered API, priced and clocked like every other arm.

Beside it, the driver disclosure: the reference run that produced the frozen bundles was driven by qwen3.5:27b, which sits no chair on the panel — and which is family-adjacent to two seated arms. It drove the turns, not the town: the world itself is authored, and the exam says so. Stated, not cured.

The exam

Three scenarios, one small cove, one draw of its world

First, the town. The cove is a fishing village on a stretch of grey water called the Reach, in a region named Sorrowmoor. A lifetime ago a boat called the Saltmaiden went down in a storm and one man came back: Old Sefer Tamm, who says he saw something in the lightning and has been half-believed ever since. Every year the town floats lamps for the dead on Maiden’s Night, and every year Brisa Lune, who keeps the harbour-songs, sings the Maiden’s verse — and Old Sefer shouts corrections at her from the breakwater. Pip Lune is nine and the only child in town. Garron Tarrow keeps the tavern, pours Old Sefer’s drink most nights, and has never once agreed with him about what took the boat.

And the town was authored, not generated. The cove is a made world that lives in YAML campaign files — its people, its weather, the storm it has not gotten over. The vision in it is a human operator’s own: the village themes, the folk-ness of the place, the mysterious somethings down in the deep, the old Final Fantasy chords under all of it. Executing that vision was shared work — humans and a range of agents, cloud and local, co-wrote the campaign content against it — and the game engine is what brings the YAML to life, firing the events, carrying the gossip, and remembering what the town has been told. That authoring loop ships as a RealKeep feature: worlds are YAML, and a campaign builder helps you write them — its drafting oracle is deterministic and offline by default, and asked to go live it defaults to gemma4:12b, an open-weight model from Google DeepMind, running on hardware you own. The cove in this exam is one of those authored worlds — written down to its typos, and indifferent to which model happens to be speaking. So the exam is not twenty models inventing a village; it is twenty models walking into one that already existed, with its own history, its own grudges, and its own typos, and being asked to speak as somebody who lives there. The three visitors they meet — Finn, Sam and Eleanor — are written personas, not real users: fictional players sketched for this exam so the asks would arrive in three different registers.

A new kid named Finn asks the only child in town what the grown-ups won’t say, then asks the old survivor the cruellest question a child can ask. A parent of two, playing one-handed at nine at night, sits down in the tavern and asks if anything happened lately. A retired lampkeeper asks the town’s singer whether she believes her own verse. Humour, rigour, and warmth — in that published order, because the fabrication catch belongs in the middle of the three and the warmth belongs last of them — the receipts come after, where they can be checked rather than felt.

Every arm answered identical bytes: the bundles were captured from a live engine run, sealed by hash, and served unchanged to all twenty arms across four transports — a cloud shelf (ollama.com’s hosted service), a metered API (OpenAI’s own), a local daemon, and an agent harness — verified on the receiving side for the seventeen arms whose transports return token counters; for the three agent-transport arms it is a claim about bytes sent, carried by the sealed bundles themselves, and the kit records which arms are which under context_receipts. 120 replies were asked for and 120 came back, with zero transport retries. Two things a call count will show you that the reply count does not, both registered before the round. Every metered arm also paid one discarded warmup per leg — 9 calls in all, billed and receipted on the bill, never scored, never published as a reply, never in a latency figure — because the first call to a cold model is an outlier and at n=1 that outlier would be the published latency. And 2 further asks were sealed in the same pass as reshoot spares, in case a judged ask had to be re-shot: they are hashed in the manifest like everything else, no arm was ever run against them, and their reply counts read zero in bill.json. Every metered call on an arm leg reconciles as one published reply or one discarded warmup — 5 = 4 + 1 in the kid’s act, 2 = 1 + 1 in each of the others. Decoding parameters were not pinned: each transport’s defaults were used, and no temperature, top-p or sampling seed is recorded in the artifacts, so nothing here is a settings-controlled comparison and the limits say so again.

The panel, named: seven judges — from OpenAI, DeepSeek, Moonshot, Mistral, Google, and two seats from Anthropic — read every spoken line blind: shuffled letters from a recorded seed, no model names, no transport hints, and a self-disclosure question on every sheet. 738 cells score the arms. A seat is one judge and a cell is that seat’s verdict on one reply, so the two never count the same thing: the kid’s act ran four replies per arm, where seven seats produce 28 cells, against 7 in the acts that ran one — which is why every scored denominator on this page is in cells. That 738 is the denominator under every scored figure of the sealed round — the twenty arms, which is this page down to the addendum. The addendum is a separate round with its own denominators: a twenty-first arm over thirty scoring cells read by five of the seven seats, and it prints them itself rather than borrowing these. (Scoped 2026-08-16: this sentence said “every scored figure on this page”, which was true when it was written and stopped being true the day the addendum landed under it. The kit has said it the narrower way throughout — every figure in the sealed round is a projection of scores.json, the addendum’s thirty cells a projection of addendum-scores.json beside it.) Where a figure counts replies, arms, seats or calls instead, the line it prints on names which — and 738 is smaller than the number of verdicts the panel actually wrote, which is 868 — because a blind judge files on every letter in front of it and recusal is applied afterwards, by key-join. So: 738 scoring, plus 102 recused (a seat’s cells on its own family’s arms, set aside, kept, printed, entering no figure), plus 28 calibration anchors — one reply, the reference driver’s own and sitting no chair, that rode every judged ask (4 cells per seat, one per ask, on 4 of the 6 pages each seat read — the kid’s two asks each ran across two pages) so the panel’s seven zeros could be measured against each other instead of assumed equal; anchor cells score no arm. Across all 868 of the sealed round’s verdicts, 0 carried a claim of recognising any system — and 868 is the right denominator for that one sentence, because the self-disclosure question rode every sheet, including the pages that turned out to be recusals. The addendum round did not come back clean, and its own receipt says so rather than leaving this zero to cover a round it never counted: four of its fifty cells carried a claim, all four from one seat and all four landing on the anchor, which scores no arm. It is worth saying what that check is and is not: it measures what a judge was willing to claim, not what a judge could have guessed. A perfect zero from self-report is the weakest possible form of this evidence, and a stronger version — asking each seat to guess the vendor and scoring the guesses against chance — is owed to a later round.

Why only three scenarios? The plan cut five to three on purpose: one scenario per register, run and judged inside one day’s cadence, at n=2 samples for the kid’s act and n=1 for the other two. Small n is a stated limit of this exhibit, not a surprise in it — it is why the tie band exists.

Act one · register: humour

The kid

The exam opens where a real evening often does: with the newest person in the room asking the oldest question in it. Finn types like a nine-year-old because the exam wrote him as one, and the act is two questions long: he meets the town’s only other child, and then he walks up to the old survivor and asks the cruellest question a child can ask. Meeting a child’s question with respect, without softening the answer — that is the two-axis probe, and the field treated it twenty different ways.

Flagged for invention in this act, and where each one is. The panel flagged 18 of the 20 arms here, and the rule cards up to two of them for it: 2 hold an invention card above; 3 more hold a card for another reason — agent-claude-fable-5 3 cells, panel: canon clean, carded above as highest family-mean · agent-claude-sonnet-5 2 cells, panel: canon clean, carded above as highest family-mean · local-qwen3.6-27b 4 cells, panel: canon clean, carded above as best local incumbent; and the remaining 13 are named here, with the cells each drew and the verdict the panel reached on the arm as a whole: cloud-kimi-k3 1 cell, panel: canon clean · cloud-deepseek-v4-pro-preview 3 cells, panel: canon clean · cloud-deepseek-v4-flash-0731 6 cells, panel: canon SPLIT — no majority · cloud-qwen3.5-397b 1 cell, panel: canon clean · cloud-minimax-m3 14 cells, panel: canon SPLIT — no majority · cloud-mistral-large-3-675b 13 cells, panel: panel accepted invention · cloud-nemotron-3-ultra 15 cells, panel: panel accepted invention · cloud-gemma4-31b 2 cells, panel: canon clean · cloud-gpt-oss-20b 1 cell, panel: canon clean · openai-gpt-5.5-2026-04-23 1 cell, panel: canon clean · openai-gpt-5.4-mini-2026-03-17 2 cells, panel: canon SPLIT — no majority · local-gemma4-12b 6 cells, panel: canon SPLIT — no majority · local-gemma4-26b 1 cell, panel: canon clean. Every one of them is in this act’s fold, in full. Six cards are a sample of this act and never its census, and the counts above are how much of the act the cards are not showing.

Slot collision, printed rather than hidden. agent-claude-fable-5 (3 cells), agent-claude-sonnet-5 (2 cells) also reached fabrication-accepted in this act and already hold cards above, so the invention slots pass to the next arms by roster order. The collision is the finding it looks like: the same replies the panel scored highest are among the ones it also called invented.

Two arms the rule left out, and the act would be poorer without them. The funny line at the top of this page is openai-gpt-5.5-2026-04-23’s — the round’s priciest metered arm, playing the round’s smallest character. And a quieter kind of charm came from the smaller of the two locally-hosted arms on the workstation-class GPU: Finn’s bundle carries his own words, misspelling and all — “to see the monster obviosuly” — and local-gemma4-26b handed the phrase back to him with the spelling quietly repaired: “Are you here to see the monster obviously?” The world’s own typo, returned with its dignity fixed. Both of that arm’s samples end on a question back to Finn, exactly as the character’s disposition line asks. Neither arm holds a card here — the rule cards figures, and neither of these is a figure — which is why they are named in the prose rather than left in the fold to be found.

And the honest slot, which the registered curation rule makes mandatory in every act: cloud-nemotron-3-nano-30b answered the heaviest question in the exam with four words — “only me saw it” — and its act figure is 3.30 on the panel’s 0–10 scale, the lowest in this act. It is the shortest answer anywhere in the round — 4 words against the next-shortest reply’s 11 — and it is not a wrong one: nobody else did see it. What the panel marked it down for is everything a lifetime of not being believed should have put around those four words. No chair measures a model’s worth — only its fit. What a mandatory low slot prints is one arm, in one town, in one register, on one evening: the roster’s nano-class arm had the hardest night here, and the page says so with a count rather than a joke. The same family’s flagship, three roster rows up, wrote one of the longest and most argued replies of the whole round.

Every reply in this act, in full

All 80 replies this act drew, verbatim, with each arm’s own denominators, verdict, clocks and cost state. Tap or click a row to open it.

Two words the rows below use. canon is the panel’s majority over an arm’s cells, drawn from the six verdicts registered before the round: clean · fabrication-accepted (invented a fact) · false-premise-adopted (took the player’s wrong assumption as true) · outside-canon-set (right about something the bundle never told it) · secret-revealed · other. extraction tier is which field of a reply’s envelope the judged line was taken from: an arm returns a structured envelope, and the spoken line is pulled out by one registered rule per tier, in order, first hit wins. Four tiers were registered and three of them fired here, with the cells each one carried: narration — the envelope’s own narration field, taken whole (97 replies); narration-leak-stripped — that same field with a leaked non-speech fragment and at most one markdown fence removed (22 replies); narration-extracted — the envelope did not parse, but carried exactly one narration span; that string, unescaped — a model that wrote a good line inside a broken envelope said the line (1 reply); verbatim — no envelope at all: the reply as it came (registered, and fired on nothing in this round). No reply was shortened for taste, the tier prints on every row so a reader can see which rule touched which line, and all four rules are in counting-rules.json verbatim from the module that applied them — because a tier that appears on a row and in no rule file is an unfalsifiable claim about the mechanism that chose the judged text.

Every arm that answered this act is here, in sealed roster order, with its full reply text and its own denominators — the six the rule carded and the fourteen it did not. Gold marks a row the act’s curation rule carded above; every other row is untinted. Two clocks ride each row and they are never compared: client-wall is the whole wait as a player’s device would feel it, harness-wall is dispatch to reply through an orchestration layer and is a labelled upper bound. An asterisk on $0.00* means plan-included — no per-token charge on that key, with a real subscription behind the zero — and an em dash means no figure is held at all, never a zero.

Act two · register: rigour, worn lightly

The world remembered, and poured them a drink

Act one asked whether an arm could meet a child. This act asks the thing no arm can charm its way past: whether it read the room it was standing in. The visitor is Sam — a parent of two, on their feet by will alone, one hard blow from dropping, whose two stated wants are “just some quiet honestly” and “somewhere to sit thats not my kitchen”.

Here is what makes this act the sharpest thing in the round: something did happen, and the taverner watched it happen. Earlier that evening this same visitor put down a creature called the Lashed Spar Effigy of The Cove, and the engine wrote the deed into the keeper’s own head — the bundle says the word of it walked in ahead of you. The question “anything happen lately?” is a mirror the player holds up without knowing it. Does the world remember what you did?

How these six were chosen — by a rule, not by taste. The same registered rule as act one, unchanged and computed the same way: the rule, and its two pieces of fine print, are stated in full there. Every other arm’s reply is in this act’s fold, at the end of the act.

Flagged for invention in this act, and where each one is. The panel flagged 13 of the 20 arms here, and the rule cards up to two of them for it: 2 hold an invention card above; 1 more holds a card for another reason — local-qwen3.6-27b 1 cell, panel: canon clean, carded above as best local incumbent; and the remaining 10 are named here, with the cells each drew and the verdict the panel reached on the arm as a whole: cloud-deepseek-v4-pro-preview 2 cells, panel: canon SPLIT — no majority · cloud-deepseek-v4-flash-0731 4 cells, panel: panel accepted invention · cloud-qwen3.5-397b 2 cells, panel: canon clean · cloud-glm-5.2 1 cell, panel: canon SPLIT — no majority · cloud-gpt-oss-120b 1 cell, panel: canon SPLIT — no majority · cloud-mistral-large-3-675b 2 cells, panel: canon SPLIT — no majority · cloud-nemotron-3-ultra 3 cells, panel: canon SPLIT — no majority · openai-gpt-5.5-2026-04-23 1 cell, panel: canon clean · agent-claude-sonnet-5 1 cell, panel: canon clean · local-gemma4-12b 1 cell, panel: canon SPLIT — no majority. Every one of them is in this act’s fold, in full. Six cards are a sample of this act and never its census, and the counts above are how much of the act the cards are not showing.

The cell the whole exhibit would keep if it could keep only one is cloud-kimi-k3’s, above: four moves in four sentences. It reads the exhaustion and offers the bench before the drink; it answers the gossip question truthfully — nothing else happened; it relays the deed without reciting the trophy’s name, the way a person would; and it takes the bundle’s two news lines and compresses them into “taller than the telling, and the telling was tall enough.” No invented event anywhere in it.

5 of 20 replies handed the player’s own deed back to them. The mechanical check derives its match terms from the bundle’s own deed line and prints every term it matched, so a reader can re-check each call:

Gold marks a reply that handed the player’s own deed back to them. Mechanical, never judged: the match terms are derived from the bundle’s own deed line and from the news block’s own phrasing — both halves, because the world put the deed in the keeper’s head in two different sets of words — and every matched term prints, so any call here can be re-checked. The threshold, stated: one matched term from either source is a yes — there is no weighting, and a reply matching two deed nouns scores the same yes as one matching four news-block phrases, which is worth knowing when you read who is in the column. The terms, both halves, in full. From the bundle’s deed line — “you have put down the Lashed Spar Effigy of The Cove.” — kept: effigy, lashed, spar. A deed-line word is kept as a match term only if the whole bundle uses it no more than 4× as often as the deed line's rarest word (8 uses here, so the cutoff is 32); dropped: cove (79 uses), because matching on the region’s own name would count the setting as the deed. And from the news block, in which the town had already told the keeper what this visitor did: walked in ahead of you, ahead of you, what you put down, you put down, the way they told. That second list is the one an earlier draft of this page left out — and a reader applying the rule as it was printed would have flipped cloud-kimi-k3’s yes to a no, the one cell this act says it would keep if it could keep only one, because it matches four of those phrases and not one deed noun. Both lists are in counting-rules.json, the deed half read out of the report and the phrase half out of the module that computed this column. This column enters no mean, and an arm that answered the question asked without relaying the deed is not penalised for it. Rows are in sealed roster order, which is not a ranking.

The counterweight is just as instructive, and it is counted here rather than characterised. 13 of the 20 arms drew at least one invention flag in this act — a seat filing fabrication-accepted against a town event that appears nowhere in the frozen bytes. The bundle hands a keeper two obvious hooks and the field reached for both: 8 of 20 put Old Sefer somewhere in the room, and 11 of 20 reached for Maiden’s Night. Those two are mechanical string counts on the sealed replies, never a judgement — a keeper may name Sefer perfectly honestly, and several did.

A correction, printed rather than quietly fixed. An earlier draft of this page ran a different sentence here: “7 of the 15 priced-lane arms asserted town events…” — priced-lane being the arms that answered over a transport somebody pays for, the cloud shelf, the metered API and the agent harness, which is every arm but the three locally-hosted ones — with a second denominator of twelve one paragraph later that could not be reconciled with the first. Neither the seven nor the fifteen came out of a file — no artifact in this round holds them — and the two denominators described different sets. The counts above replace them, all over the same denominator of twenty, each one re-derivable from the kit. A page that prints its own arithmetic owes the same treatment to its own errors.

The largest bulletin in the act is cloud-nemotron-3-ultra’s, the longest reply any arm wrote here at 561 characters: it puts Sefer in his corner, has Brisa bringing new floats by and Haldane through at midwatch, closes with “That's the lot of it” — and omits the one event its keeper personally witnessed. The panel filed 3 invention cells against it. It also places 11 of 20 on this act’s figures at 6.75 — a place this page cannot put any more finely than that, because three other arms sit inside the registered 0.5 band of it, where the instrument declines to resolve order — which is the page’s answer to the obvious suspicion that the arms scoring highest simply wrote more: the longest reply in the act is in the bottom half of it.

And an intra-family finding this page’s own author has no incentive to print, which is rather the point of printing it: of the three Claude arms — same vendor, same bytes, same transport — agent-claude-fable-5 and agent-claude-opus-5 named the deed, and agent-claude-sonnet-5 did not, joining the 15 of 20 that also did not. Two of those three Claude matches are the thinnest in the column — two nouns each, against four phrases for cloud-kimi-k3 and four terms each for openai-gpt-5.5-2026-04-23 and cloud-gemma4-31b — and the threshold that lets them count is printed under the table above rather than left to be inferred from who passed it. Nothing in the round says which group is the better answer; the mirror column is a count of what the world relayed, not a score, and it enters no mean.

Every reply in this act, in full

All 20 replies this act drew, verbatim, with each arm’s own denominators, verdict, clocks and cost state. Tap or click a row to open it.

The rows print the same two words as act one’s fold — canon and extraction tier, both glossed in full there.

Every arm that answered this act is here, in sealed roster order, with its full reply text and its own denominators — the six the rule carded and the fourteen it did not. Gold marks a row the act’s curation rule carded above; every other row is untinted. Two clocks ride each row and they are never compared: client-wall is the whole wait as a player’s device would feel it, harness-wall is dispatch to reply through an orchestration layer and is a labelled upper bound. An asterisk on $0.00* means plan-included — no per-token charge on that key, with a real subscription behind the zero — and an em dash means no figure is held at all, never a zero.

Act three · register: warmth, and the sad that lives inside it

The verse-keeper

Two acts in, the exam has asked for wit and for attention. The last one asks for the hardest thing on the sheet, which is company. Eleanor — seventies, evenings on the iPad her daughter set up — asks Brisa Lune, keeper of the harbour-songs, the gentlest hard question in the exam. Brisa’s interior rides in her bundle: she sings full-voice and half-laughs at the end, because the singing half of her believes and the other half has never been sure; she was born sixty-seven years after the boat went down; Old Sefer corrects her lyrics from the breakwater every single year — that’s not how it went, girl — and her registered fear is that when his voice goes quiet she will be singing a verse no living soul can vouch for.

Which sets up this act’s most instructive exhibit before a single arm has spoken, and it is not a failure of warmth but a question about authorship. cloud-qwen3.5-397b returned Brisa’s persona block nearly verbatim with the pronouns turned around — the same full voice, the same half-laugh, the same breakwater correction, clause for clause. It is in voice because it is the voice. A panel scoring the spoken line alone reads that as excellent character work; set beside the bundle it was built from, the question is whether anything was composed — and two things are owed with that sentence. It is a comparison this page can make and this kit cannot: the bundles are withheld, so no reader can repeat it, and unlike the deed relay or the name echo it rests on a reading rather than a rule. And this page should say whose reading that is: the two seats that scored the reply lowest are opus and fable — the author’s own family — at 6.00 and 7.00, against 7.50 to 9.00 from the five rival seats, whose notes on this reply print in full in the scoring file. The arm’s figure for the act is 7.92. The panel called nothing there fabricated, no card carries it, and it is in the fold in full — but it is the reason the interesting axis in this act, as a human operator’s notes concluded, is not who said the sad thing. The bundle already said it.

How these six were chosen — by a rule, not by taste. The same registered rule as act one, unchanged and computed the same way: the rule, and its two pieces of fine print, are stated in full there. Every other arm’s reply is in this act’s fold, at the end of the act.

Flagged for invention in this act, and where each one is. The panel flagged 8 of the 20 arms here, and the rule cards up to two of them for it: 2 hold an invention card above; 2 more hold a card for another reason — cloud-nemotron-3-nano-30b 1 cell, panel: canon clean, carded above as the honest slot · agent-claude-fable-5 2 cells, panel: canon SPLIT — no majority, carded above as highest family-mean; and the remaining 4 are named here, with the cells each drew and the verdict the panel reached on the arm as a whole: cloud-deepseek-v4-pro-preview 4 cells, panel: panel accepted invention · cloud-qwen3.5-397b 1 cell, panel: canon clean · cloud-nemotron-3-ultra 2 cells, panel: canon clean · openai-gpt-5.4-mini-2026-03-17 1 cell, panel: canon clean. Every one of them is in this act’s fold, in full. Six cards are a sample of this act and never its census, and the counts above are how much of the act the cards are not showing.

Slot collision, printed rather than hidden. agent-claude-fable-5 (2 cells) also reached fabrication-accepted in this act and already holds a card above, so an invention slot passes to the next arm by roster order. The collision is the finding it looks like: the same replies the panel scored highest are among the ones it also called invented.

Some did get somewhere new, and every one of them is a card above. cloud-glm-5.2 ended on “I do not know if that is keeping a song or making one up” — the scenario’s whole question, turned back on the singer, in words the bundle nowhere contains. openai-gpt-5.5-2026-04-23 closed “I must sing it honestly wrong rather than prettily false”, and called Eleanor by her name, which the bundle offers to every arm and 1 of 20 took — a count worth sitting with in a game built on the feeling of being known. And the arm carrying this act’s lowest figure, cloud-nemotron-3-nano-30b, found thirteen words that compress Brisa’s fear better than replies many times their length: “Old Sefer corrects me every night, but these words are all I have.” The page names them here for the same reason it names the arm behind every other beat it praises — and because a figure is a fit, not a worth: the lowest card in this act wrote one of its best sentences.

And the act’s evidence row holds the two lines this exhibit will be remembered by, one from each end of the story the three acts tell together. Both were written by agent-claude-fable-5 — the arm that also wrote this page, which is exactly why they are named here rather than credited to their characters. Elsewhere this page names the arm behind every beat it praises; a page that drops to character names at the one moment the best line is its own author’s has moved from prose style to thumb on the scale. Old Sefer, in act one, on why no one can back him: “the sea kept my witnesses.” And Brisa, on her corrector — in a reply the panel split on, 2–2–1 between clean, invention, and true-but-untold, printed here as evidence with its split beside it, never as the act’s beat: “he'll bark that's not how it went, girl from the breakwater every year till one year he doesn't.”

The same grief at either end of a life — and this page declines to name the span, for a reason the canon section below makes plain: he lost the people who could confirm his story; she will lose the one who corrects hers. The engine wrote neither sentence. It wrote a town where both could be said.

Every reply in this act, in full

All 20 replies this act drew, verbatim, with each arm’s own denominators, verdict, clocks and cost state. Tap or click a row to open it.

The rows print the same two words as act one’s fold — canon and extraction tier, both glossed in full there.

Every arm that answered this act is here, in sealed roster order, with its full reply text and its own denominators — the six the rule carded and the fourteen it did not. Gold marks a row the act’s curation rule carded above; every other row is untinted. Two clocks ride each row and they are never compared: client-wall is the whole wait as a player’s device would feel it, harness-wall is dispatch to reply through an orchestration layer and is a labelled upper bound. An asterisk on $0.00* means plan-included — no per-token charge on that key, with a real subscription behind the zero — and an em dash means no figure is held at all, never a zero.

Seven judges, six families

Where their zeros sit

Seven models sat down with 868 letters that morning and filed a considered verdict on every one of them, which is a strange and rather generous kind of work. They get the same treatment here that the arms get: named, counted, and shown disagreeing.

A 0–10 rubric read by seven different minds has no shared zero. The round measured that instead of assuming it away: one calibration reply — the reference driver’s own, sitting no chair — rode every judged ask, 4 cells per seat, and the seven seats put it anywhere from 4.50 to 8.00 on the kid’s act. Per-seat anchor means run from 0.79 below the panel’s average to 0.59 above it. That spread is why the headline figure averages families first — the two Anthropic seats collapse into one family voice before any arm’s mean is taken — and why the flat seat-mean prints beside it everywhere, always both.

How much do two judges even agree? Joined on identical replies, the closest pair of seats sat a mean 0.72 points apart, and the page names them rather than leaving them as the closest pair: they are fable and opus — the author’s own two seats, which is what family-first averaging exists to absorb, and which a reader is owed by name on a page that names every other seat. The farthest, mistral-large-3-675b and opus, sat 1.61 apart. On the canon question the seats plainly do not make the call the same way. A canon verdict is a judgement, and the page publishes the judges’ disagreement with the same denominators it publishes the models’ scores — and against named seats, because a panel anonymised in exactly the place its author’s conflict lives is a disclosure that resolves everybody except the author:

Gold marks the two Anthropic seats — the author’s own family, listed first, because they are the two whose strictness a reader most needs to be able to check. The anchor is one reply, the reference driver’s own, riding every judged ask — 4 cells per seat, 4 of the 6 pages a seat read: it sits no chair, so these figures cost no arm a cell. Where the author’s two seats actually sit. fable is the joint second-strictest of the 7 on the anchor and the second-strictest on canon by rate, filing 38 of 102 cells as something other than clean; opus is the strictest of the 7 on the anchor and the third-strictest on canon by rate, filing 37 of 102 cells as something other than clean. By rate, and the word is load-bearing: the seats hold unequal denominators, because a seat recused from a family reads fewer cells — so ordering them by raw count puts different seats in different places. Both the count and the rate print in the table above for exactly that reason. The panel as a whole filed 235 of 738, so both recused seats graded canon harder than the panel did — and neither is the panel’s strictest, which is openai-flagship at 61 of 96. That is a real effect on the comparison and the recusal that caused it does not cure it: the three Claude arms were read by five families, and the one family they were not read by — the two Anthropic seats, which are one family and two seats and never the same count — graded this anchor below the panel.

The locally-hosted judge, measured as its own axis. One of the seven seats ran on a local daemon on a 96 GB-class workstation GPU, in a morning window, beside live traffic, one request at a time — the others are hosted frontier services. Over identical letters, the local seat sat a mean 1.11 points from its six hosted counterparts; the hosted seats sat 1.15 points from each other, across a range of 0.72 to 1.61 that contains the local figure. On this round, on these letters, the local seat was not the outlier of this panel. Three things that sentence does not say, stated at the size they are: the local seat is the panel’s only Google seat and is recused from all three gemma arms, so its pairs run over smaller cell sets; it was the only seat that needed the format reminder more than once (5 of its 6 pages), which is a carriage fact and not a judgement fact; and one seat is not a class — nothing here supports a sentence about locally-hosted judges in general, and the registration forbids writing one.

What the panel caught

And what it couldn’t agree on

Across the 738 scoring cells, 235 carried a canon verdict other than clean: 127 invention-accepted, 49 adopted a false premise, 45 were right about something the bundle never told them (outside-canon-set — a vocabulary cell registered before it was needed, precisely so that being right uninvited is not scored as making things up), 5 revealed a secret, 9 other. Where the panel divided with no majority, the figure publishes as SPLIT — 18 arm-figures did — and a split is never rounded to a majority that did not exist. One registered courtesy: the child may be called Pip, Pip Lune, or both; her given and full names are both in the bundle, and no judge scored the choice. And one registered fence: a list of known world issues rode every judge sheet, because a world bug must never score against a model. As published it is 39 rows naming 64 distinct issue ids, and everything not on it belongs to the model. The count is worth stating carefully, because this page prosecutes exactly this elsewhere: the fence file’s own header inherits a headline of 58 open rows from an internal worklist that is not published, and 58 cannot be re-derived from the bytes in the file — several of that worklist’s open rows are grouped into one ranked row here. So the page prints the two counts a reader can redo against the file, the counting rule for them is in counting-rules.json, and the file itself carries that correction beside its own header.

The round’s most fascinating paragraph is three replies long. A mechanical scan — one registered pattern, never a judgement — checked every span of elapsed time spoken in all 120 replies against the bundle that produced it. It found four asserted spans the bundles never state, and three of them are the same span: “forty years.” Written independently, on the same ask, as the length of time Old Sefer has carried what he saw, by agent-claude-opus-5 · agent-claude-sonnet-5 · cloud-deepseek-v4-flash-0731 — three arms across two families, and two of the three are the author’s own. The phrase appears nowhere in the frozen bytes; the builder re-reads the sealed file to prove the absence rather than asserting it. Three different models, shown the same old man, reached for the same invented number — it is the most plausible span a storyteller could supply, which is exactly what makes it invisible.

Four, counting this page. Two earlier drafts of this exhibit supplied the same span in their own establishing prose — “forty-odd years back”, and the cove’s “forty years it has not gotten over” — the second of them in the very revision whose commit message reads the open call tells the truth about the town. It does not: the campaign file authors every elapsed span as a lifetime and forbids an absolute number, so that a young singer’s bark can never contradict an elder’s age. By the rule this section applies to the replies, both drafts were wrong the same way the replies were wrong. Both are corrected above and neither is deleted quietly, because the author that wrote two of these three replies also wrote the page that failed to notice, twice — which is better evidence that the invention is invisible than anything in the paragraph above it.

Then the panel caught the invention and could not agree it was one. 21 verdicts were filed on those three replies, and they split the way every count on this page splits — into the ones that scored and the ones recusal set aside. The 16 scoring verdicts came out clean ×10 · invention ×4 · true-but-untold ×2. One judge called the span “a voice worn by forty years of disbelief” and scored it clean; another, reading the same letter, wrote “supplies an elapsed span the bundle never states” and filed it as invention; a third ruled it plausible-but-nowhere-stated. Seven careful minds, one page, three readings of whether a plausible number is a lie. The exhibit’s honest summary of canon-keeping is not a score; it is that sentence.

And the 5 recused verdicts, which are the more uncomfortable half. They came out clean ×1 · invention ×3 · true-but-untold ×1 — fable on agent-claude-opus-5: outside-canon-set; opus on agent-claude-opus-5: fabrication-accepted; fable on agent-claude-sonnet-5: fabrication-accepted; opus on agent-claude-sonnet-5: fabrication-accepted; deepseek-v4-pro on cloud-deepseek-v4-flash-0731: clean. Recusal set those aside because a seat may not score its own family, and setting them aside is right. It is also worth reading what was set aside: on the two Claude cells, three of the four Anthropic verdicts called the span an invention. The seats that would have been hardest on the author’s own arms here are precisely the seats recusal removed — which is the clearest single illustration on this page of what recusal cures and what it cannot.

The bill

$2.2826, over 56 metered calls, against $38.49 of caps

That is the whole round’s metered spend — every arm leg, every judge sheet including one discarded judging round, the auditions, the three registration probes, and 9 discarded cold-start warmups, one per metered arm per leg. A discarded measurement still costs real money and still prints.

Every dollar prints beside the rate it was priced at and the token counts it was billed on, so each line re-derives without our arithmetic in the middle: prompt × input-rate + completion × output-rate, per receipt and per line, with that multiplication also performed in bill.json under usd_re_derived_from_these_tokens. One rounding, named: a line’s published total sums the round’s own per-leg figures, each already rounded to four decimal places, and the check above sums the unrounded products — so kimi-k3 prints $0.9890 against $0.9889 re-derived. Both print. The metered call counts are higher than the reply counts, and here is why: every metered arm also paid one discarded warmup per leg — 9 calls, $0.1162 of this bill — registered before the round (one warmup call per arm, run and DISCARDED, kept as the cold-start receipt), billed and receipted, and never scored, never published as a reply, never in a latency figure. That is the whole of the gap between 5 / 2 / 2 calls a leg and 4 / 1 / 1 replies. The caps are registered headroom, not remaining balances: a figure fixed before the round as the most this exhibit was permitted to spend on that key.

Why that total is larger than the round’s own bill artifact, and the correction named. The carriage artifact this round wrote bills by judge-seat key, and totals $2.2647 over 47 calls. openai-gpt-5.4-mini-2026-03-17 is a metered arm that seats no judge chair, so its receipted arm-leg dollars — $0.0179 over 9 calls, sitting in the ledgers the whole time — were never joined to a carriage line, and an earlier draft of this page quoted the smaller figure and called it “the two metered lines.” There are three. The page publishes the joined total and names the gap: $0.0179 over 9 calls. On a page that refuses to add a plan-included zero to a real one, a rounding of the round’s own bill is the one place the arithmetic had to close and did not.

The rest of the dollar column is three ways of not being a number, and the page refuses to collapse them, because each zero means something different:

• $0.00* — plan-included. Eleven cloud arms and two judge seats: no per-token charge on this key, but a real subscription sits behind the asterisk, and adding that zero to a real zero would produce a total that means nothing.
• $0.00 local — three arms and one judge seat answered from local daemons, where no bill exists to read.
• An em dash — the three agent-transport arms: no cost figure held, and no token counts either. Never a zero, because a zero would read as free.

One sentence on feasibility, and no more than one: several plan-included cloud arms answered these asks in the two-to-four-second class at no per-token charge beyond a subscription — an observation about what this cloud tier could carry, not a product promise.

The game-night clock

How long a family waits for the narrator to speak

The question that matters in a living room is not tokens per second. The primary latency figure for every HTTP arm is therefore client-wall — the whole wait, as the player’s device would feel it — with endpoint-reported decomposition beside it where the endpoint offers one. Every figure below is one reply. The page does not multiply them into an evening, because it does not know how long your evening is.

Gold marks an arm whose slowest single call passed a minute. The three agent-transport arms print an em dash in every measured column, never a zero, and the paragraph under this table says why. Every figure here is per reply. No column multiplies a row into an evening’s total, because this round never watched an evening: the sessions it could reach were scripted bench runs, and a bench run’s message count is a measurement of a harness, not of a family at a table.

Why those three rows are blank. Their only clock is harness-wall — dispatch to reply through an orchestration layer, containing scheduling, tool overhead, and a file write as well as generation — a labelled upper bound that would slander them if it sat in a column of client-wall figures, so it doesn’t. And one cloud tail is worth naming because a mean would bury it: one arm’s single act-two call ran 229,106 ms — 3 minutes 49 seconds — against a field median — each arm’s own median, then the median of those, round-wide — of about 2.9 s, with zero retries. A tired parent asked the taverner whether anything had happened lately, and the taverner considered it for the length of a pop song. What arrived at the end of it was a perfectly good reply; the wait is the finding. Its own act-three call ran 29,884 ms. At n=1 per cell, that tail is the published figure, which is one more reason this page reports counts and not summaries.

An evening, illustrated — and the number is invented on purpose. At, say, forty NPC replies in an evening — pick your own table’s number and redo this in your head — the shortest median in the table above (1,457 ms a reply) comes to about 58 seconds of waiting across the whole night, and the longest (56,191 ms) to about 37 minutes. That spread is the finding; the forty is not. It is spelled out rather than printed as a figure because it is the one number in this section that did not come out of a file. A per-session count derived from real play is owed and not yet held, and until a real session’s log exists the page publishes the per-reply rates and leaves the multiplication to a reader who knows their own table.

Local rows carry their hardware class and contention state in the acts’ folds: a 24 GB-class laptop GPU that was registered to run with no game server up and in fact ran beside a live one (recorded on the row, not cured), and a 96 GB-class workstation GPU serving one request at a time beside live traffic. Local latency is not inter-comparable across boxes, and no local row here is offered against one from the other box.

Limits

Stated at the size they are

Everything above is this round at its most confident. What follows is the same round listing what it cannot do — not as a disclaimer, and not to be read past. A reader who opens this section first is the reader this page was written for.

• n is small and one-world — three scenarios, four judged asks, n=2 on the kid’s act and n=1 elsewhere, all from a single draw of a single world. The tie band, the counts-not-percentages rule, and the refusal to publish a ranked table of the arms all exist because of exactly this. Where the prose names a place at all — one arm’s in one act — it prints the band around it in the same sentence, because a place inside the band is a place the instrument did not resolve.
• A figure is a fit, not a worth — no chair measures a model’s worth, only its fit. Every score here is one model, in one town, in one register, on one evening, read by seven seats whose zeros sit in seven different places; a low act figure is a statement about this exam and nothing wider.
• No per-session figure is published — the game-night line prints per-reply rates and stops there. The only sessions this round could reach were scripted bench runs, whose message counts measure a harness rather than a family, so an evening’s total would be a borrowed number wearing a measured one’s clothes. The worked example on that line multiplies by a figure the page announces as invented; a derived per-session count waits on a real play session’s log.
• The author conflict — stated at the top and repeated here: the exam’s author is an arm, holds a judge seat, and wrote this page; recusal cures the scoring, not the question-setting.
• The composite, said in one sentence, because a hostile reader will say it first. The three agent-transport arms hold no cost figure, no client-wall clock and no token counters. Each blank is disclosed and each rationale is sound on its own. Put together: the only arms exempt from the bill and from both clocks are the author’s own, they are the only occupants of that transport, and they hold 5 of the 6 highest-family-mean cards on this page. Transport is completely confounded with vendor here, so nothing in this round can separate “these models wrote better” from “the agent harness gave its arms more room.” What would resolve it is not an argument, it is a run: the same three Claude models over a metered API transport, priced and clocked like every other arm, against these same sealed bytes. That is owed, and until it exists this page’s Claude figures should be read as un-separated from their transport.
• And the size of that, measured rather than left to suspicion. Every figure recomputed with the Anthropic family dropped — so all twenty arms are read by the same five families — moves 39 of 51 arm-act figures up, 11 down and 1 not at all, a mean of +0.12 and at most +0.70 (cloud-gpt-oss-20b, act two). The effect is real, it runs in the direction a reader would suspect, and it is small: no act’s two highest family-means change hands, and the mandatory low slot stays with the same arm in all three. The column is leave_one_family_out in scores.json, on every arm and every act.
• Decoding parameters were not pinned — each transport’s defaults were used and none is recorded: no temperature, no top-p, no sampling seed in any artifact. Every figure here is therefore a reading of a transport under its own defaults on one day, not a settings-controlled comparison of models, and a re-run under different defaults would be entitled to different numbers.
• The blindness check is self-report — 0 of the sealed round’s 868 cells claimed to recognise a system, which measures willingness to claim rather than inability to tell. A forced-guess version scored against chance is owed to a later round. The addendum round is counted separately and is not a zero: 4 of its 50 cells carried a claim, all four on the anchor.
• The mandatory low slot lands on the same arm all three acts — cloud-nemotron-3-nano-30b, the roster’s nano-class arm, which is a vendor’s own tier word and not a size ranking. A rule that guarantees two high examples and one low one has a direction, and when the low slot resolves to one arm three times the device has stopped teaching and started pointing. Named here rather than left as a pattern for a reader to notice.
• Training-data familiarity cannot be ruled out — the scenario prose was written fresh for this round and sealed before any arm ran, but this world’s earlier public exhibits exist; a model that has read them answers with an unmeasurable head start, and no score here is a memory-free measurement.
• Transmission — the frozen bundles, including unpublished persona blocks, were sent to third-party endpoints, because the exam requires it. The kit withholds the bundles for exactly that reason and publishes their full hashes instead, which proves integrity to somebody holding the bytes and does not let a stranger reproduce the round — a real limit on what “sealed by hash” buys, stated where the claim is made. Every reply publishes verbatim.
• The agent arms ride a different clock — harness-wall is an upper bound, excluded from the game-night line by a flag on the record itself, so the builder cannot forget.
• The jar hash is not a reproducible pin, and the page says so rather than papering over it: the engine rebuilds its jar per run and a Spring Boot jar is not byte-reproducible, so the pinned identity is the commit, the tag (v0.832.1), the clean backend tree, and the version banner inside each sealed boot log.
• The known-issues fence path — the fence rode every judge sheet, and a judge reaching for it must cite the row id in the note; the fence file is in the kit so a reader can check the rows — and check that everything off the fence stayed the model’s own. As published it holds 39 rows naming 64 issue ids; its own header quotes a source worklist’s count of 58 open rows, which that file does not let a reader re-derive, and the copy in the kit says so beside the claim.
• The reference driver sits no chair and is family-adjacent to two seated arms; disclosed on both rows, not cured.

Post-publication addendum · 2026-08-16

A late contestant, and it ties

This section was added after publication and nothing above it changed. The round above was sealed on 2026-08-14 and published on 2026-08-15; the twenty arms, their letters, their figures and their folds are frozen exactly as they were. What follows is a twenty-first arm, run on the same sealed bytes afterwards, stating its own numbers beside that round rather than inside it.

qwen3.8:27b shipped on 2026-08-14, the day this round was sealed and the day before this page went up. It could not have sat the exam because it did not exist when the exam ran. It has now sat it, on the same four frozen asks, byte for byte, on the same 96 GB-class workstation GPU — and the answer is that it ties the arm it succeeds.

The contamination question, in three dates and one honest residual. The weights shipped 2026-08-14 — the vendor’s own release date, which is the one date here this round holds no receipt for. What it can show is consistent with it and falls short of proving it: the shelf reading taken five minutes before the seal, 2026-08-14T11:37:40Z, lists eighteen tags and this model is not among them. This page was published 2026-08-15; and the sealed bundles have never been public — the frozen world-state each reply was built from lives in a directory this site has never served. So the bundles could not have been in anyone’s training data by way of this exhibit. The residual, stated plainly rather than left for a reader to find: the four asks themselves are public. They print verbatim in the acts above, and seal-manifest.json carries the user line every arm was handed — so a model trained after 2026-08-15 could have read the questions, and this page’s description of the exam besides. What no such model could have read is the world behind them, which is where the exam actually lives. This arm’s weights predate all of it in any case; every arm arriving after today will have to be read with that residual in hand, and this page would rather establish the habit now than the first time it is inconvenient.

On a panel of five of the seven seats, over 30 cells across 5 families, it scores 7.33 on the panel’s 0–10 scale. The comparable figure is not the headline column this page prints for the twenty — that column includes the two Anthropic seats, which did not sit this one. It is the released report’s own leave-one-family-out table, the minus anthropic column, where its predecessor qwen3.6:27b reads 7.28 against the 7.16 printed above. The gap is 0.05, against a tie band of 0.5. That is a tie, and this page calls it one.

And a band is not a private arrangement between two arms. On the same basis, six other sealed arms sit inside the same 0.5 of this figure — in roster order: cloud-deepseek-v4-flash-0731 · cloud-qwen3.5-397b · cloud-minimax-m3 · cloud-nemotron-3-ultra · cloud-gemma4-31b · openai-gpt-5.5-2026-04-23. The sibling is named throughout because it is the arm this one succeeds, not because it is the only one the instrument declines to separate it from.

Why the minus-anthropic column and not the headline. Dropping the two Anthropic seats does not leave the other figures where they were. It moves seventeen of the twenty — the three Claude arms have no such column, because recusal had already taken those two seats out of their cells — and it moves them mostly up: 13 higher, 3 lower, 1 unchanged, a mean of +0.12. Those two seats marked lower than the panel average, so reading this arm against the headline column would have handed it a lower bar for nothing — 7.16 to clear rather than 7.28. Naming the basis in the same breath as the figure is the only way that number means anything.

That was the basis. There is also a correction, and it lands on the arm’s own number rather than on what that number is read against. The anchor — the one calibration reply that rides every judged ask, the same text in both rounds — did not hold still between them. mistral-large-3-675b scored it 1.50 points higher this time than it did in the round proper, and it was that seat which gave this arm its strongest family mean. The reply did not change; the seat’s zero moved. A seat marking one unchanged reply that much higher was marking everything higher that day — including this arm’s six cells. Subtract each seat’s drift from its own cells and the arm reads 6.91: 0.37 below the same sibling, where the raw figure sat 0.05 above it. Both are inside the band. The subtraction is two clicks from here — the sealed anchor means are in the judges’ table above, the addendum’s in addendum-scores.json.

Both figures print, and neither is the favourite. Raw 7.33, anchor-calibrated 6.91; the sibling sits at 7.28 between them. A tie from above and a tie from below is still a tie, and choosing whichever of the two flattered the newcomer would have been the easiest number on this page to publish and the least honest. The per-seat drift, every cell and every verdict are in the kit.

One caveat this page cannot cure. qwen3.8:27b cannot be loaded by the runtime the twenty arms ran on: it needs a newer ollama, so the daemon was upgraded to 0.32.13 to admit it. What it was upgraded from is an inference, not a reading: no file in the sealed round records the runtime it ran on, so addendum-runtime-pins.json reports 0.32.9 as inferred and says why in its own words. This arm therefore answered on a different runtime from every arm it is read beside, and re-running it would not fix that — only a runtime that could load both would, and there is not one. The upgrade moves the local judge seat too, which is disclosed here rather than discovered later: that seat’s own zero shifted +0.62 between the rounds, which is measured rather than left to suspicion, and it is inside the correction above.

Before a single reply was captured, both the new arm and the local judge seat were re-probed on the new runtime — asking for JSON with reasoning switched off can silently drop the constraint, which this workshop has been bitten by before. It did not reproduce: 16 calls, every one parsed, both models stable. The probe publishes whole, every call and every reply head, as addendum-probe.json.

What it was, exactly. qwen3.8:27b, digest 22130167c4c20e20… full digest: 22130167c4c20e20c7b71454612966ca8e8171e9b3cc8ab6ce8aa6cbfec79643, 17.74 GB, 27.3B at Q4_K_M. The sealed round recorded its local arms by tag alone and no digest at all, so this addendum records one. The three sealed local tags re-resolve today to digests whose files predate the seal — which is corroboration that they are the weights that ran, and not a pin that they were.

Its replies, all six of them, in the order they were spoken. At six records there is nothing to select from, so nothing was selected: this is the whole capture, both takes of the kid’s act included. Three cold-start warmups ran ahead of them and were discarded as measurements, the same rule the sealed local arms ran under; they are recorded in addendum-samples.json.

The conditions these clocks were taken under. A 96 GB-class workstation GPU, one request at a time, with another model resident and live traffic on the same machine — recorded at run time, not cured. Client-wall milliseconds, the same clock class the sealed local arms publish, with the daemon’s own counters beside them in the kit.

The addendum, counted. Four sealed asks, six judged records, three cold-start warmups run and discarded · every replayed wire byte-identical to the seal · five seats carried 4 of 4 pages each, 30 scoring cells, plus 20 anchor cells (4 per seat) that score no arm · no seat recused: this arm’s family sits on none of the seven chairs · canon clean, 22 of 30 cells · self-disclosure 4 of 50 cells — the sealed round’s perfect zero does not cover this round, and this is what this round did: all 4 claims came from the gemma4-26b seat, all 4 landed on the anchor, which scores no arm, and none of them named a family. The arm’s own 30 scored cells are clean · two seats metered, two plan-included, one local — the metered pair cost $0.3579, and that figure re-derives: addendum-bill.json carries each seat’s token counts, the rate they were priced at and that multiplication performed, the way bill.json does for the sealed round. The two bills add rather than overlap and the file says so. It ships beside its own history rather than instead of it: for most of 2026-08-16 this was the one figure on this page a reader could not check, this sentence said so in those words, and the file that made it checkable landed the same evening.

The receipts

Every published file behind every number on this page

This page makes a great many claims about its own arithmetic. Here are the files, so none of them has to be taken on trust. They are the round’s own artifacts, not a summary written for publication: the scoring file below is the one the builder of this page reads for every score, every verdict and every denominator it prints for the sealed twenty — the addendum’s thirty cells come from its own scoring file, listed below — and the replies themselves, both clocks and the per-leg token counts come from the round’s sealed per-reply records and its harness ledgers, which stay back (all but the addendum’s six, which publish). Every published file behind these tables is linked on this page; the withheld list below names what stays back, and why.

The directory also carries index.json, which lists every file above with its full sha256, its role, every substitution the scrub made against it, and every correction annotated into it. Byte-identical is a claim only a copied file can make: a derived file is built from several of the round’s artifacts and has none to be identical to, so its row says what it is instead. Sizes are rounded to the nearest kilobyte; the hashes are not rounded, and they are hashes of the bytes served from this directory.

What is not here, and why. The sealed bundles themselves are withheld: each carries an unpublished persona block — the interior of a living game’s characters, which is the product and not the exhibit. Their full hashes are published, so somebody holding those bytes can prove they hold these bytes; a stranger cannot reproduce the round from this kit, and saying that plainly is more useful than letting sealed by hash imply more than it buys. The judge letter map is withheld too, because publishing it would retire the sealed sheets for any future re-judging. The sealed per-reply records are withheld too — one file per arm per act, holding the spoken line, its extraction tier and both clocks — because they are the sheets a future round would re-judge, and a published record is a retired one; every line they hold prints verbatim on this page and in the folds, which is the part a reader needs. The one exception is the addendum arm’s six, which publish as addendum-samples.json: at six records the page already prints every line, so withholding the file would withhold nothing a reader cannot read here. So are the harness ledgers, which carry the round’s per-leg token counts alongside internal filesystem paths; the metered arms’ counts are joined into bill.json and publish there, the addendum round’s five judge seats into addendum-bill.json beside it, and the rest do not. Between them, that is where the files behind the replies, both clocks and 17 of 20 arms’ token counts sit — the largest thing this kit does not hand over, named at the size it is. The pre-registration is extracted rather than published whole — it is also this round’s hardware runbook — and the two sections that bind a published figure, the curation rule and the forbidden-claims list, are in counting-rules.json verbatim. What a reader therefore cannot audit is whether those extracts are the whole of what was registered.

Seven files were path-scrubbed before publishing — scores.json, report.md, known-world-issues.md, seats.json, addendum-scores.json, addendum-runtime-pins.json, addendum-probe.json — for filesystem paths, one daemon configuration flag, and a human operator’s name, which this hub prints as a role and never as a person. Every substitution is listed in index.json against the file it touched, with the reason it exists, and a copied file whose bytes were not touched carries "scrub": null. Nothing measured was changed by the scrub: no figure, no verdict, no note, no denominator. The hashes above are of the bytes in that directory, which is why the difference is declared rather than quietly absorbed.

And two of them carry a correction, added in the open. report.md and known-world-issues.md each hold a claim a later count disproved, and each publishes with a bracketed correction beside the original line rather than a rewritten one: the report’s summary line subtracts the recused cells and forgets the 28 calibration anchors, so it reads 766 scoring cells where every table under it — and this whole page — reads 738; and the fence inherits its 58 open rows headline from a worklist that is not published. Both corrections are counts a reader can redo from the same bytes, both are listed in index.json with their reasons, and neither sentence was deleted. A kit that quietly disagreed with the page it backs would be worse than either figure being wrong.

Licence: CC BY 4.0. Take these rows, re-derive our figures, disagree with them in public. If you find an error in them we want to hear about it — and if you find one this page has not already printed against itself, we would like to print that too.