Ruling — Decrypto

You asked

How do I play?

Abstained — no grounded answer; closest passages below counted as honest abstain

Asked with: Decryptobg-225694-en-1e

Answered before

This question didn't get an answer just now — but Decrypto has been asked something like it before. The corpus may have changed since, so check the date and the answerer on each one before you rule from it.

How do I play? →

Answered Sep 25, 2026 gemma4:26b read Decrypto

I looked through Decrypto's rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.

The closest rulebook passages are below — check them before ruling.

RULEBOOK Decrypto — Rulebook · p.1 · Game Principles and Goal

DECRYPTO pits two teams of 2 to 4 players against each other.* The general idea of the game is to transmit information to your own team without the other team understanding. To win you have to walk a fine line: The instructions you give need to be clear enough for your teammates to understand, while

RULEBOOK Decrypto — Rulebook · p.6 · Gameplay

The game follows the standard rules for Steps 1 through 7, except for the distribution of Tokens. If the Interceptor manages an Interception, they receive 1 Interception Token, as usual. If the Encryptors fail a communication, however, they do not receive a Miscommunication Token. Instead, the Inter

RULEBOOK Decrypto — Rulebook · p.6 · Overview

A single player, called the 'Interceptor' , plays against a team made up of 2 Encryptors. Each Round, an Encryptor draws 1 Code Card and comes up with 3 clues, like in the standard game. To win, the Interceptor must collect 2 Interception Tokens in 5 Rounds or less.

RULEBOOK Decrypto — Rulebook · p.3 · Record the clues for this Round in the spaces at the bottom of the Note Sheet.

Repeat Steps 3-7 with the opposite team. The Black team's Encryptor reads their clues out loud, the players from both teams try to work out the code, etc. You must finish the Round even if one (or both!) of the teams have met one of the victory conditions. There is a very good chance that your under

RULEBOOK Decrypto — Rulebook · p.2 · gameplay

The game takes place over a number of Rounds (to a maximum of 8), with most games usually lasting between 4 and 6 Rounds. If neither team has won by the end of the 8th Round, the game automatically ends. At the beginning of each Round, each team names their Encryptor. This role will be held by each

🔧 debug — where this ruling came from

outcome

ABSTAINED — Abstained — no grounded answer; closest passages below

warm abstain

this ruling — W1 — generic warm abstain · receipt: none (generic)

corpus profile

live,vps

answerer pin (deploy-frozen, attribution only)

gemma4:26b think:false 5571076f3d70

timings

search 101 ms · ask 1430 ms · total 10708 ms

single-flight (PR-5)

queued 9176 ms · generation 1532 ms

retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read

[{"page": 1, "score": 0.047163, "snippet": "DECRYPTO pits two teams of 2 to 4 players against each other.* The general idea of the game is to transmit information to your own team without the other team understanding. To win you have to walk a fine line: The instructions you give need to be clear enough for your teammates to understand, while", "headingPath": "Game Principles and Goal", "sharpsignalDocId": 101}, {"page": 6, "score": 0.046176, "snippet": "The game follows the standard rules for Steps 1 through 7, except for the distribution of Tokens. If the Interceptor manages an Interception, they receive 1 Interception Token, as usual. If the Encryptors fail a communication, however, they do not receive a Miscommunication Token. Instead, the Inter", "headingPath": "Gameplay", "sharpsignalDocId": 101}, {"page": 6, "score": 0.04598, "snippet": "A single player, called the 'Interceptor' , plays against a team made up of 2 Encryptors. Each Round, an Encryptor draws 1 Code Card and comes up with 3 clues, like in the standard game. To win, the Interceptor must collect 2 Interception Tokens in 5 Rounds or less.", "headingPath": "Overview", "sharpsignalDocId": 101}, {"page": 3, "score": 0.032787, "snippet": "Repeat Steps 3-7 with the opposite team. The Black team's Encryptor reads their clues out loud, the players from both teams try to work out the code, etc. You must finish the Round even if one (or both!) of the teams have met one of the victory conditions. There is a very good chance that your under", "headingPath": "Record the clues for this Round in the spaces at the bottom of the Note Sheet.", "sharpsignalDocId": 101}, {"page": 2, "score": 0.032258, "snippet": "The game takes place over a number of Rounds (to a maximum of 8), with most games usually lasting between 4 and 6 Rounds. If neither team has won by the end of the 8th Round, the game automatically ends. At the beginning of each Round, each team names their Encryptor. This role will be held by each ", "headingPath": "gameplay", "sharpsignalDocId": 101}, {"page": 3, "score": 0.031746, "snippet": "When the Round has ended, check to see if one of the teams has either won or lost the game. If at least one of the following conditions has been met, the game ends. Otherwise begin a new Round. If a team has 2 Interception Tokens, they've won the game. If a team has 2 Miscommunication Tokens, they'v", "headingPath": "End of Round and End of Game", "sharpsignalDocId": 101}, {"page": 2, "score": 0.03125, "snippet": "Split into 2 teams as evenly as possible. Seat all the members of the same team on the same side of the table , facing the opposing team. Each team takes 1 Screen and draws 4 Keyword Cards from the top of the deck, which they place in the Screen's slots without showing them to the opposing team. Eac", "headingPath": "Setup and Components", "sharpsignalDocId": 101}, {"page": 3, "score": 0.029412, "snippet": "In every Round, the Encryptor will have to come up with clues . Here are some important rules to keep in mind. You may choose whatever form you like for your clue : it could be a word or a whole sentence. If your group of players is up for it, you can even hum, dance, or mime! Clearly separate your ", "headingPath": "clues", "sharpsignalDocId": 101}]

citations (raw) — what the answer cited, chosen from a retrieval this page cannot show

[]

boost provenance — errata + base rulebook (E2/E3)

no registered errata card matched this query; base rulebook doc 101 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 101 boosted

answered-before recall

past answered rulings were found and offered

similarity threshold in force: 0.55 (rulesage.answered-before.similarity-threshold; the exact-question tier is not gated by it)

ruling 6571 — matched by the same question (normalized, punctuation folded) — measured similarity 1.0

debug row recorded

Aug 27, 2026 13:31 UTC

retrieval — what the passage search returned

what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.

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 Decrypto — Rulebook (corpus doc 101)	Game Principles and Goal	p.1	0.047163 (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 Decrypto — Rulebook (corpus doc 101)	Gameplay	p.6	0.046176 (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 Decrypto — Rulebook (corpus doc 101)	Overview	p.6	0.04598 (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))	266
#4	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Record the clues for this Round in the spaces at the bottom of the Note Sheet.	p.3	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
#5	RULEBOOK Decrypto — Rulebook (corpus doc 101)	gameplay	p.2	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
#6	RULEBOOK Decrypto — Rulebook (corpus doc 101)	End of Round 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
#7	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Setup and Components	p.2	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
#8	RULEBOOK Decrypto — Rulebook (corpus doc 101)	clues	p.3	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

what the answerer read — the passages it actually had in front of it

what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.

candidate pool: the answering read scored 19 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.

floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.

arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.

read at	document	heading	page	fused rank	fused RRF score	carried by	how it got its slot
#1	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Overview	p.6	#3	0.04598 (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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Setup and Components	p.2	#7	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))	vector + the doc-priority boost arm	the re-ranker chose it
#3	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Gameplay	p.6	#2	0.046176 (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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#4	RULEBOOK Decrypto — Rulebook (corpus doc 101)	clues	p.3	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Record the clues for this Round in the spaces at the bottom of the Note Sheet.	p.3	#4	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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Decrypto — Rulebook (corpus doc 101)	gameplay	p.2	#5	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))	vector + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Decrypto — Rulebook (corpus doc 101)	Game Principles and Goal	p.1	#1	0.047163 (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))	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Decrypto — Rulebook (corpus doc 101)	End of Round and End of Game	p.3	#6	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))	vector + the doc-priority boost arm	the re-ranker chose it

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars

generation — timing and the path taken

timing split: retrieval 101 ms · first delta 1421 ms · total 10708 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 9176 ms · retrieval 101 ms · ask 1430 ms · gateway work 1532 ms · total 10708 ms
tokens in (the prompt the answerer read): 2370
tokens out (what the answerer generated): 9
tok/sec: 191.5 tok/sec — 9 output tokens in 0.047 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 26s ago)
answerer host (measured by rulesage): reachable (for 23h, checked 7s ago)
answerer node (the seat proxy's own header — this probe, not this ask): node1
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: ABSTAINED — Abstained — no grounded answer; closest passages below
abstain rationale: I don't have enough information.
BOILERPLATE, not reasoning: this is the answerer's fixed abstention phrase, the same sentence it emits whenever it declines. It records THAT the answerer declined and never why — no per-ruling reason was captured, because none was sent. Hostile corpus/LLM text, rendered escaped

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 32), 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.