You asked
How do I play?
Answered counted as answeredAsked with: The Crew: Mission Deep Seabg-324856-en-1e
🔧 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 78 ms · ask 6634 ms · total 28880 ms
- single-flight (PR-5)
- queued 22166 ms · generation 6714 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04918, "snippet": "In each round, each crew member plays one card in turn. These cards form the trick. The highest card wins the trick. The card played first in each trick has to be followed. This applies to color and submarine cards. If a player doesn't have the opening suit, they can play any card. Only cards of the", "headingPath": "Trick-taking game", "sharpsignalDocId": 195}, {"page": 11, "score": 0.047131, "snippet": "Even if there is only one task that you cannot complete, you immediately lose and have to start the mission over from the beginning. For your next attempt, you first have to shuffle the playing cards and deal them out again. For the task cards, you can choose whether to you want to try the same task", "headingPath": "MISSION SEQUENCE", "sharpsignalDocId": 195}, {"page": 3, "score": 0.04598, "snippet": "The Crew: Mission Deep Sea is a cooperative, missionbased trick-taking game. What does that mean? You win together, or you lose together - only if each of you is successful, and you help each other, will you be able to complete the missions and win the game. Your voyage extends across many different", "headingPath": "GAME MATERIALS · Cooperative · Mission-based · Trick-taking game", "sharpsignalDocId": 195}, {"page": 22, "score": 0.045956, "snippet": "In a two-person game, a double row of 14 cards is used to represent Tonoja as a third crew member. Your Captain selects the tasks for Tonoja and plays her cards for her. In all cases, these decisions are made without any discussion. In a two-person game, the role of the captain is still taken by the", "headingPath": "TWO-PERSON GAME", "sharpsignalDocId": 195}, {"page": 2, "score": 0.043636, "snippet": "Good communication is essential here — but underwater, this can be harder than you might think … GAME MATERIALSGAME MATERIALS 40 Large cards (playing cards) 36 Color cards in four colors with the values 1–9 4 Submarine cards with the values 1–4 5 Large reminder cards 96 Small cards (task cards) 6 To", "headingPath": "", "sharpsignalDocId": 195}, {"page": 21, "score": 0.04359, "snippet": "In each of the four missions, the tasks must be allocated after one round of questions. If there are four players and the first two answer 'No' in mission 26, crew member three and the captain will have to take the tasks. If a mission displays this symbol, you are allowed to talk freely among yourse", "headingPath": "Real-time missions · Free selection of tasks · TWO-PERSON GAME", "sharpsignalDocId": 195}, {"page": 1, "score": 0.04311, "snippet": "11 Game Materials .......................................... 2 Trick-Taking Game ..................................... 3 Communication ......................................... 5 Mission Preparation (Setup) .................... 7 Mission Sequence (Game Play) ................ 8 Let’s Go! ............", "headingPath": "", "sharpsignalDocId": 195}, {"page": 5, "score": 0.032258, "snippet": "In this game, the goal is always to have the right players win the right tricks. To do that, you will really need to coordinate. An important rule in the game is that you cannot share information about the cards in your hand. You are not allowed to show, tell, or indicate to the other crew members w", "headingPath": "Trick-taking game · Communication · Rules of thumb for communication:", "sharpsignalDocId": 195}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 7, "quote": null, "headingPath": "Communication: · MISSION PREPARATION", "sharpsignalDocId": 195}, {"page": 5, "quote": null, "headingPath": "Trick-taking game · Communication · Rules of thumb for communication:", "sharpsignalDocId": 195}, {"page": 11, "quote": null, "headingPath": "MISSION SEQUENCE", "sharpsignalDocId": 195}, {"page": 4, "quote": null, "headingPath": "Trick-taking game", "sharpsignalDocId": 195}, {"page": 3, "quote": null, "headingPath": "GAME MATERIALS · Cooperative · Mission-based · Trick-taking game", "sharpsignalDocId": 195}, {"page": 19, "quote": null, "headingPath": "TASK CARDS · Currents · Rapture of the Deep", "sharpsignalDocId": 195}, {"page": 13, "quote": null, "headingPath": "FEASIBILITY · Rule of thumb for failed attempts:", "sharpsignalDocId": 195}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 195 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 195 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 0.90249 of 2051 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 13, 2026 13:37
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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Trick-taking game | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | MISSION SEQUENCE | p.11 | 0.047131 (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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | GAME MATERIALS · Cooperative · Mission-based · Trick-taking game | p.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)) | 300 |
| #4 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | TWO-PERSON GAME | p.22 | 0.045956 (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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | p.2 | 0.043636 (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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Real-time missions · Free selection of tasks · TWO-PERSON GAME | p.21 | 0.04359 (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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | p.1 | 0.04311 (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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Trick-taking game · Communication · Rules of thumb for communication: | p.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)) | 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 28 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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | MISSION SEQUENCE | p.11 | #2 | 0.047131 (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 The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Communication: · MISSION PREPARATION | p.7 | #12 | 0.028283 (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 re-ranker chose it |
| #3 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | FEASIBILITY · Rule of thumb for failed attempts: | p.13 | #15 | 0.027047 (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 re-ranker chose it |
| #4 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Trick-taking game · Communication · Rules of thumb for communication: | p.5 | #8 | 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 |
| #5 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | TASK CARDS · Currents · Rapture of the Deep | p.19 | #11 | 0.028814 (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 re-ranker chose it |
| #6 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Trick-taking game | p.4 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | TASK CARDS | p.17 | #10 | 0.029437 (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 re-ranker chose it |
| #8 | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | GAME MATERIALS · Cooperative · Mission-based · Trick-taking game | p.3 | #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 |
chosen chunks — what the answer actually cited
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.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Communication: · MISSION PREPARATION | p.7 | no quote on the wire |
| [2] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Trick-taking game · Communication · Rules of thumb for communication: | p.5 | no quote on the wire |
| [3] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | MISSION SEQUENCE | p.11 | no quote on the wire |
| [4] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | Trick-taking game | p.4 | no quote on the wire |
| [5] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | GAME MATERIALS · Cooperative · Mission-based · Trick-taking game | p.3 | no quote on the wire |
| [6] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | TASK CARDS · Currents · Rapture of the Deep | p.19 | no quote on the wire |
| [7] | RULEBOOK The Crew: Mission Deep Sea — Rulebook (corpus doc 195) | FEASIBILITY · Rule of thumb for failed attempts: | p.13 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 78 ms · first delta 2243 ms · total 28880 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 22166 ms · retrieval 78 ms · ask 6634 ms · gateway work 6714 ms · total 28880 ms
- tokens in (the prompt the answerer read)
- 3140
- tokens out (what the answerer generated)
- 614
- tok/sec
- 138.7 tok/sec — 614 output tokens in 4.428 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 16s 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 113), 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.