Ruling — Turing Machine

You asked

How should we prepare everything before the first turn?

Answered counted as answered

Asked with: Turing Machinebg-356123-en-1e

To prepare for the first turn, follow these steps: 1. Place the Machine tile in the centre of the table [1]. 2. Assemble the punch-card support [1]. 3. Place the punch cards in the support, with all cards in the front, followed by all others [1]. 4. Choose a Problem to solve [1]. 5. Place the Criteria cards in front of their assigned Verifier [1]. 6. Place the Verification cards face down in front of their assigned Verifier, next to the Criteria card [1]. 7. To avoid mistakes, tick the corresponding letter (A, B, C, or D) on the back of each Verification card [1]. 8. Draw a line through Verifier columns and E, as they will not be used in the game [1]. 9. Give each player a Player Aid (which also serves as a screen) and a note sheet [1]. 10. If playing from the online app, note down the number of the game [1]. 11. At the beginning of every game, take time to discuss and understand the meaning of each Criteria card [2].

[1] RULEBOOK Turing Machine — Rulebook · p.2 · SETUP FOR YOUR FIRST GAME · SOLO AND COOPERATIVE MODES · Verifier:

[2] RULEBOOK Turing Machine — Rulebook · p.4 · CRITERIA CARD EXPLANATIONS · Card 1 · Cards 2 to 4 · Cards 5 to 7 · Cards 8 to 10 · DO YOU THINK THE MACHINE HAS MADE A MISTAKE? · …

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 218 ms · ask 6408 ms · total 16952 ms
single-flight (PR-5): queued 10317 ms · generation 6635 ms
retrieval refs (raw): [{"page": 2, "score": 0.032787, "snippet": "Place the Machine tile in the centre of the table. 2 3 Assemble the punch-card support. Do not take it apart at the end of the game; store it in the box as is. Place the punch cards in the support: all cards in the front, followed by all and so on. Choose a Problem to solve (on the next page). Numbe", "headingPath": "SETUP FOR YOUR FIRST GAME · SOLO AND COOPERATIVE MODES · Verifier:", "sharpsignalDocId": 424}, {"page": 4, "score": 0.032258, "snippet": "Show this example to anyone who is learning the game. Here is a problem with 4 criteria: In the first round, you put together this proposal and you write it on your note sheet. Verifier A verifies one criterion. This criterion could be either \" The number is equal to 1 \" or \" The number is greater t", "headingPath": "EXAMPLE OF PLAY · Game Order: · There aren't enough punch cards: · Don't get mixed up: · Number of Questions per round: · You must keep the same proposal for the entire round: · …", "sharpsignalDocId": 424}, {"page": 3, "score": 0.031746, "snippet": "If one or more players think they have found the code, they should write it secretly (and clearly!) on their note sheet . Each one then checks, in turn, the SOLUTIONS section at the bottom of p. 3 in this booklet, or uses the appropriate button in the application, and verifies if their code is corre", "headingPath": "VERIFICATION AND END OF GAME", "sharpsignalDocId": 424}, {"page": 3, "score": 0.03125, "snippet": "Unlike many deduction games, you won't be questioning the other players, but a machine. This machine consists of 4 to 6 Verifiers, a kind of artificial intelligence. Each verifier checks for one single aspect, one single criterion. Questioning a Verifier consists of asking them if your proposal pass", "headingPath": "GAMEPLAY · ROUND STRUCTURE · 1. COMPOSE · 2. QUESTION · The Verifier's Answer · ADVANCED STRATEGY:", "sharpsignalDocId": 424}, {"page": 1, "score": 0.030769, "snippet": "A game by Yoann Levet and Fabien Gridel British mathematician and cryptanalyst Alan Turing made a significant contribution to the advent of computers. We are offering you a chance to use a proto-computer, working without electricity or electronics, to find secret codes. Be the first to find the only", "headingPath": "GOAL", "sharpsignalDocId": 424}, {"page": 3, "score": 0.030303, "snippet": "Once you have made your 3-digit proposal, you will decide which Verifiers to question. Questioning a Verifier means asking if your proposal respects their criterion or not; if your proposal passes their test or not. The criteria that each Verifier is checking could be as simple as, ' the number is e", "headingPath": "Recap · 3. DEDUCE · 4. END OF ROUND", "sharpsignalDocId": 424}, {"page": 5, "score": 0.029851, "snippet": "The Veri2er veri2es that the number is less than , equal to , or greater than another particular number (that they know). The Veri2er veri2es that the number of 1s or the number of 3s in the code is equal to a particular number (that they know). The Veri2er veri2es that that the number of a particul", "headingPath": "Cards 43 to 44 · Cards 45 to 47 · Card 48 · HANDICAP SYSTEM", "sharpsignalDocId": 424}, {"page": 2, "score": 0.029412, "snippet": "Difficulty Factor / Luck B 9 B B B B fi A B C D A B C 8 12 15 17 4 9 18 356 695 329 618 fi 335 fi 362 fi 421 fi fi fi fi D 20 747 B A Verifier fi 677 217 634 4 9 13 A B C fi fi D 17 528 fi B A B C D A B C D 9 11 16 19 21 23 28 41 48 fi 279 515 770 523 681 244 440 737 fi fi fi fi fi fi fi A B C D A B", "headingPath": "PROBLEMS · ONLINE PROBLEMS · You will also find 2 new , more challenging modes of play .", "sharpsignalDocId": 424}]
citations (raw): [{"page": 2, "quote": null, "headingPath": "SETUP FOR YOUR FIRST GAME · SOLO AND COOPERATIVE MODES · Verifier:", "sharpsignalDocId": 424}, {"page": 4, "quote": null, "headingPath": "CRITERIA CARD EXPLANATIONS · Card 1 · Cards 2 to 4 · Cards 5 to 7 · Cards 8 to 10 · DO YOU THINK THE MACHINE HAS MADE A MISTAKE? · …", "sharpsignalDocId": 424}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 424 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 424 boosted
answered-before recall: this ruling was answered, so past rulings were not offered
similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)
debug row retained until: Nov 7, 2026 05:09

retrieval — what the search arm returned

score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. This ruling ran the THREE-ARM fuse (full-text + vector + the doc-priority boost arm, which carried the base rulebook and/or the errata corrections this query matched), whose arithmetic ceiling is 0.04918 — all three arms ranking the same chunk #1 (ceiling = arms/(k+1) at k=60). The measured healthy band 0.016–0.033 was measured on TWO-arm asks and does not bound this one: its high end is the two-arm ceiling, and a third arm has room above it. A chunk only one arm ranked highly lands near 0.016 (that one arm's #1 vote), so 0.03 here is an excellent hit, not a 3% match.

per-arm ranks (the rank each search arm gave a chunk): NOT DISCLOSED by the gateway. Fusion happens gateway-side and only the FUSED score crosses the wire, so rulesage cannot show them without a gateway change. The rank column below is the FUSED rank (position in the returned list), which is real.

token count per chunk: NOT DISCLOSED — chunk token counts are not reported on the ask path. The character counts below are of the bounded snippet/quote rulesage actually received — a real measurement of what we hold, never an estimate of the chunk.

fused rank	document	heading	page	fused RRF score	snippet chars
#1	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	SETUP FOR YOUR FIRST GAME · SOLO AND COOPERATIVE MODES · Verifier:	p.2	0.032787 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#2	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	EXAMPLE OF PLAY · Game Order: · There aren't enough punch cards: · Don't get mixed up: · Number of Questions per round: · You must keep the same proposal for the entire round: · …	p.4	0.032258 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#3	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	VERIFICATION AND END OF GAME	p.3	0.031746 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#4	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	GAMEPLAY · ROUND STRUCTURE · 1. COMPOSE · 2. QUESTION · The Verifier's Answer · ADVANCED STRATEGY:	p.3	0.03125 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#5	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	GOAL	p.1	0.030769 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#6	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	Recap · 3. DEDUCE · 4. END OF ROUND	p.3	0.030303 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#7	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	Cards 43 to 44 · Cards 45 to 47 · Card 48 · HANDICAP SYSTEM	p.5	0.029851 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300
#8	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	PROBLEMS · ONLINE PROBLEMS · You will also find 2 new , more challenging modes of play .	p.2	0.029412 (healthy, below this ruling's 3-arm ceiling 0.04918 (the measured band 0.016–0.033 was taken on two-arm asks and does not bound a 3-arm one))	300

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	SETUP FOR YOUR FIRST GAME · SOLO AND COOPERATIVE MODES · Verifier:	p.2	no quote on the wire
[2]	RULEBOOK Turing Machine — Rulebook (corpus doc 424)	CRITERIA CARD EXPLANATIONS · Card 1 · Cards 2 to 4 · Cards 5 to 7 · Cards 8 to 10 · DO YOU THINK THE MACHINE HAS MADE A MISTAKE? · …	p.4	no quote on the wire

generation — timing and the path taken

timing split: retrieval 218 ms · first delta 3433 ms · total 16952 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 10317 ms · retrieval 218 ms · ask 6408 ms · gateway work 6635 ms · total 16952 ms
tokens in (the prompt the answerer read): 3485
tokens out (what the answerer generated): 245
tok/sec: 78.0 tok/sec — 245 output tokens in 3.143 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 14s ago)
stream path: streamed — the gateway pushed at least one accumulated draft
watchdog: first-token watchdog: 30s per arming window (rulesage.table.first-token-watchdog-seconds), re-armed once by the passages frame — so the worst case before a reader falls back to polling is 60s. Whether it actually fired is a BROWSER-side decision that never reaches the server, so it is not recorded here. The stream path above is the server's half of that story: whether a delta was emitted at all.
num_ctx · think posture: both are the CHILD's settings, not rulesage's, and no ask reply carries them — an answer never states which context window or think posture produced it. The live-seat line above reads them from the running child instead, where the gateway can answer for itself; it describes the child NOW, not this ask.

disposition

outcome: ANSWERED — Answered
abstain rationale (n/a — this ruling answered): answered — no abstain rationale applies

setup-shape — why the checklist band did or didn't render

decision: NOT_SETUP_SHAPED — no setup-shape pattern matched this question

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 353), so "no registered errata card matched" above could never have matched one

Errata scope: the gate above matched this ruling's own edition only. When an ask also reads an expansion, that expansion's own registered errata cards stay outside the match — a stated phase-1 limitation, not a failed lookup.