Ruling — Mysterium

You asked

How do I play?

Answered counted as answered

Asked with: Mysteriumbg-181304-en-1e

Mysterium is a cooperative game where the goal is to solve the mystery of the ghost's death.[1] One player is the ghost, who communicates through Vision cards.[1] The remaining players are psychics who must work together to interpret these cards and reconstruct their "Trail" (a series of a Character, a Location, and an Object).[1][2]

Setup

1. Assign roles: one player is the ghost, and the others are psychics.[1]

2. The ghost sets up a game screen so psychics cannot see what is behind it.[1]

3. The ghost places the Vision card draw pile face-down behind the screen and places 3 Candle markers on top of the screen.[1]

4. The psychics place the Character, Location, and Object Progress boards in the center of the table.[1]

5. Each psychic chooses a color and takes the corresponding envelope and Psychic token, then places their color's Intuition pawn on the Character Progress board.[1]

6. A psychic is chosen to be in charge of counting rounds using the Pocket Watch, starting at the first hour.[1]

7. Select 16 Character cards; psychics spread 8 Character psychic cards face-up, and the ghost takes the 8 matching Character ghost cards.[1]

8. For each psychic, the ghost places 1 random Character ghost card in a slot on the game screen.[1]

9. Repeat the card selection process for Location cards and Object cards.[1]

1 and 10. The ghost places the psychics' envelopes behind the screen and draws a hand of 7 Vision cards.[1]

The Ghost's Turn

1. The ghost draws Vision cards to complete a 7-card hand.[3][2]

2. The ghost chooses a psychic who has not yet received a card this round and gives them a Vision.[3][2]

3. To give a Vision, the ghost selects up to 7 cards from their hand, puts them in the psychic's envelope, and gives them the envelope.[2]

4. If the ghost has difficulty, they may discard a Candle marker to discard up to 7 cards and draw new ones.[3]

5. The ghost's turn is over once each psychic has been given a Vision.[3]

The Psychics' Turn

1. Psychics discuss the Visions and try to deduce which card is meant for them.[4]

2. A psychic indicates their choice by placing their Intuition pawn on a card.[4]

3. Psychics can move their pawns if they change their minds.[4]

4. Once everyone is confident in their choices, the psychics' turn is over.[4]

Resolution Phase

1. One by one, each psychic asks the ghost if they selected the correct card.[5]

2. The ghost responds by knocking under the table: 1 knock for yes, 2 knocks for no.[5]

3. If the card is correct: the psychic moves their Intuition pawn to the next Progress board (Character > Location > Object > Final), places the card in their envelope, returns all Vision cards to their envelope, and returns the envelope to the ghost.[5]

4. If the card is incorrect: the psychic returns their Intuition pawn to its starting position for that round, returns all Vision cards to their envelope, and returns the envelope to the ghost.[6]

Next Round or Ending the Game

1. The psychic with the Pocket Watch moves the hand up 1 hour.[6]

2. If the hand reaches the seventh hour, all players lose.[6]

3. If the game continues, a new round begins; the ghost gives each psychic a new Vision (or completes a previous one if a psychic failed to guess).[6]

4. If all psychics have reconstructed their Trails (pawns are on the Final Progress board), they proceed to "the revealing of the mystery".[6]

5. For the final mystery: the ghost selects 3 cards (one Character, one Location, one Object), shuffles them, and gives them to the psychics.[7]

6. The psychics discuss and must agree on a common answer (or use a majority decision).[7]

7. The ghost flips a Psychic token to reveal the true culprit's Trail.[7]

8. If the choice is the culprit's Trail, all players win; otherwise, all players lose.[7]

[1] RULEBOOK Mysterium — Rulebook · p.2

[2] RULEBOOK Mysterium — Rulebook · p.3 · 3-Player variant

[3] RULEBOOK Mysterium — Rulebook · p.3 · 3-Player variant

[4] RULEBOOK Mysterium — Rulebook · p.4 · 3-Player variant

[5] RULEBOOK Mysterium — Rulebook · p.4 · 3-Player variant

[6] RULEBOOK Mysterium — Rulebook · p.4 · Preparing for the next round · Otherwise:

[7] RULEBOOK Mysterium — Rulebook · p.5 · Otherwise:

That settles it — whose turn was it?

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live,vps
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 77 ms · ask 9066 ms · total 22330 ms
single-flight (PR-5): queued 13185 ms · generation 9145 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 2, "score": 0.048387, "snippet": "With 3 players, the game is played as usual, with one exception: During setup, each psychic chooses two colors (instead of one) and takes the corresponding components. The game proceeds exactly as if there were 4 psychics at the table. If you want more replayability in future games, use the numbers ", "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 2, "score": 0.046696, "snippet": "Mysterium is a cooperative game whose goal is to solve the mystery surrounding the death of the ghost . Before you begin playing, assign each player one of the following roles: The ghost (one single player) must guide the psychics through the investigation. The ghost knows the suspects, locations, a", "headingPath": "", "sharpsignalDocId": 183}, {"page": 4, "score": 0.032787, "snippet": "6 Once the ghost's turn has been completed, followed by the psychics' turn, players proceed to the resolution phase. One by one, in any order, each psychic asks the ghost if they have selected the correct card. The ghost responds by knocking under the table: 1 knock for yes , 2 for no . If the card ", "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 4, "score": 0.031746, "snippet": "Then check the psychics' progress: if all the psychics have reconstructed their respective Trail (i.e. all the Intuition pawns are on the Final Progress board ), they can immediately proceed to the revealing of the mystery (see next page). The psychic with the Pocket Watch moves the hand up 1 hour. ", "headingPath": "Preparing for the next round · Otherwise:", "sharpsignalDocId": 183}, {"page": 4, "score": 0.03125, "snippet": "Congratulations! You've succeeded in establishing a psychic connection with the ghost. They can't express themself through words: instead, they send you images and memories of the manor and its occupants. Unfortunately, the visions are often imprecise and cryptic... Will you be able to understand th", "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 3, "score": 0.030769, "snippet": "This may not seem easy at first, but as you listen to the psychics' discussions, it will become easier and easier. The ghost draws as many Vision cards as needed to complete their 7-card hand. Then, they choose a psychic who has not received any card this round and give them a Vision , following the", "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 5, "score": 0.029851, "snippet": "Your mind clears, and your memories fall into place as the events of that fateful evening fit together like pieces of a puzzle. You remember who is responsible for your death. Gathering your remaining strength, you give your fellow partners a final vision... Return the Progress boards and any remain", "headingPath": "Otherwise:", "sharpsignalDocId": 183}, {"page": 3, "score": 0.029412, "snippet": "The psychics have managed to communicate with you from the material world! The visions you give them may help them solve the crime, but time is working against you. Let's start by reconstructing the events of the tragic night when you lost your life... The ghost's objective is to get each psychic to", "headingPath": "3-Player variant", "sharpsignalDocId": 183}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "", "sharpsignalDocId": 183}, {"page": 3, "quote": null, "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 3, "quote": null, "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 4, "quote": null, "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 4, "quote": null, "headingPath": "3-Player variant", "sharpsignalDocId": 183}, {"page": 4, "quote": null, "headingPath": "Preparing for the next round · Otherwise:", "sharpsignalDocId": 183}, {"page": 5, "quote": null, "headingPath": "Otherwise:", "sharpsignalDocId": 183}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 183 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 183 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)
answer fence: passed — letter density 0.89962 of 3128 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Aug 25, 2026 10:27 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 Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.2	0.048387 (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 Mysterium — Rulebook (corpus doc 183)		p.2	0.046696 (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 Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.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))	300
#4	RULEBOOK Mysterium — Rulebook (corpus doc 183)	Preparing for the next round · Otherwise:	p.4	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
#5	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.4	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
#6	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.3	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
#7	RULEBOOK Mysterium — Rulebook (corpus doc 183)	Otherwise:	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 Mysterium — Rulebook (corpus doc 183)	3-Player variant	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 9 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 Mysterium — Rulebook (corpus doc 183)		p.2	#2	0.046696 (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 Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.3	#6	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))	vector + the doc-priority boost arm	the re-ranker chose it
#3	RULEBOOK Mysterium — Rulebook (corpus doc 183)	Preparing for the next round · Otherwise:	p.4	#4	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
#4	RULEBOOK Mysterium — Rulebook (corpus doc 183)	Otherwise:	p.5	#7	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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	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
#6	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.4	#5	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
#7	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.4	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.2	#1	0.048387 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Mysterium — Rulebook (corpus doc 183)		p.2	no quote on the wire
[2]	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.3	no quote on the wire
[3]	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.3	no quote on the wire
[4]	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.4	no quote on the wire
[5]	RULEBOOK Mysterium — Rulebook (corpus doc 183)	3-Player variant	p.4	no quote on the wire
[6]	RULEBOOK Mysterium — Rulebook (corpus doc 183)	Preparing for the next round · Otherwise:	p.4	no quote on the wire
[7]	RULEBOOK Mysterium — Rulebook (corpus doc 183)	Otherwise:	p.5	no quote on the wire

generation — timing and the path taken

timing split: retrieval 77 ms · first delta 1916 ms · total 22330 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 13185 ms · retrieval 77 ms · ask 9066 ms · gateway work 9145 ms · total 22330 ms
tokens in (the prompt the answerer read): 3073
tokens out (what the answerer generated): 956
tok/sec: 133.0 tok/sec — 956 output tokens in 7.187 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 44s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 3s 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: 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 101), 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.