You asked
How do I play?
Answered counted as answeredAsked with: Sushi Rollbg-271869-en-1e
Settled. Play on.
🔧 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 207 ms · ask 5963 ms · total 6172 ms
- single-flight (PR-5)
- queued 0 ms · generation 6172 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.04918, "snippet": "To start a round, all players pick up all the dice on their conveyor belts and roll them on the table . Then, everyone places their dice back on their conveyor belts without changing their faces. The player who has the red-bordered conveyor belt goes first , then play moves to the left until each pl", "headingPath": "PLAYING A ROUND · EVERYBODY TAKES A TURN · 2 Choose 1 die to keep. [Mandatory]", "sharpsignalDocId": 1234}, {"page": 4, "score": 0.046875, "snippet": "If there are two things we've learned about our fans over our 25 years of publishing games, it's that 1. They love playing Sushi Go! and 2. They really love games with dice. So it should come as no surprise that we would combine these two passions into a game! Sushi Go! inventor Phil Walker-Harding ", "headingPath": "A WORD FROM GAMEWRIGHT · Follow us!", "sharpsignalDocId": 1234}, {"page": 2, "score": 0.046642, "snippet": "40 scoring tokens (18x 1 point, 7x 5 point, 10x 10 point, 5x 20 point) 30 dice (10x appetizer, 6x maki rolls, 5x nigiri, 5x specials, 4x pudding) 20 pudding tokens (14x 1 pudding, 6x 3 pudding) 18 menu tokens 12 chopsticks tokens 5 conveyor belts (1x red-bordered, 4x grey) 5 trays 1 dice bag The gam", "headingPath": "CONTENTS · OVERVIEW · SET UP · TRAYS", "sharpsignalDocId": 1234}, {"page": 1, "score": 0.04598, "snippet": "The Sushi Go! Dice Game SUSHI ROLL RULES OF PLAY 2-5 players · Ages 8+", "headingPath": "", "sharpsignalDocId": 1234}, {"page": 3, "score": 0.032258, "snippet": "Once everyone has taken a turn, if there are any dice left on the conveyor belts, then all players simultaneously slide their conveyor belts (and the dice on them) to the player on their left and re-roll all of the dice just passed to them as they did at the start of the round. The player who now ha", "headingPath": "SLIDE AND ROLL!", "sharpsignalDocId": 1234}, {"page": 4, "score": 0.031746, "snippet": "At the end of each round, all players score the dice they have collected in their trays. Each player looks at all the faces showing on their dice and takes scoring tokens equal to the points they scored. Maki Rolls: Any players with maki rolls compare the number of maki roll icons they have. The pla", "headingPath": "SCORING A ROUND · STARTING A NEW ROUND", "sharpsignalDocId": 1234}, {"page": 4, "score": 0.030303, "snippet": "At the end of the third round, it's time for the final scoring! All players compare the number of pudding tokens they have collected. The player with the most scores 6 points. The player with the fewest (including 0) loses 6 points. If multiple players tie for the most or fewest, they all receive or", "headingPath": "ENDING THE GAME", "sharpsignalDocId": 1234}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "CONTENTS · OVERVIEW · SET UP · TRAYS", "sharpsignalDocId": 1234}, {"page": 3, "quote": null, "headingPath": "PLAYING A ROUND · EVERYBODY TAKES A TURN · 2 Choose 1 die to keep. [Mandatory]", "sharpsignalDocId": 1234}, {"page": 3, "quote": null, "headingPath": "SLIDE AND ROLL!", "sharpsignalDocId": 1234}, {"page": 4, "quote": null, "headingPath": "SCORING A ROUND · STARTING A NEW ROUND", "sharpsignalDocId": 1234}, {"page": 4, "quote": null, "headingPath": "ENDING THE GAME", "sharpsignalDocId": 1234}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1234 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1234 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 0.88762 of 3159 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 6, 2026 08:52 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 Sushi Roll — Rulebook (corpus doc 1234) | PLAYING A ROUND · EVERYBODY TAKES A TURN · 2 Choose 1 die to keep. [Mandatory] | p.3 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | A WORD FROM GAMEWRIGHT · Follow us! | p.4 | 0.046875 (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 Sushi Roll — Rulebook (corpus doc 1234) | CONTENTS · OVERVIEW · SET UP · TRAYS | p.2 | 0.046642 (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 Sushi Roll — Rulebook (corpus doc 1234) | p.1 | 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)) | 70 | |
| #5 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | SLIDE AND ROLL! | p.3 | 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 Sushi Roll — Rulebook (corpus doc 1234) | SCORING A ROUND · STARTING A NEW ROUND | 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 |
| #7 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | ENDING THE GAME | p.4 | 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 |
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 7 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 Sushi Roll — Rulebook (corpus doc 1234) | PLAYING A ROUND · EVERYBODY TAKES A TURN · 2 Choose 1 die to keep. [Mandatory] | p.3 | #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 |
| #2 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | SCORING A ROUND · STARTING A NEW ROUND | p.4 | #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 |
| #3 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | ENDING THE GAME | p.4 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | p.1 | #4 | 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 | |
| #5 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | A WORD FROM GAMEWRIGHT · Follow us! | p.4 | #2 | 0.046875 (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 |
| #6 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | CONTENTS · OVERVIEW · SET UP · TRAYS | p.2 | #3 | 0.046642 (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 |
| #7 | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | SLIDE AND ROLL! | p.3 | #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 |
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 Sushi Roll — Rulebook (corpus doc 1234) | CONTENTS · OVERVIEW · SET UP · TRAYS | p.2 | no quote on the wire |
| [2] | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | PLAYING A ROUND · EVERYBODY TAKES A TURN · 2 Choose 1 die to keep. [Mandatory] | p.3 | no quote on the wire |
| [3] | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | SLIDE AND ROLL! | p.3 | no quote on the wire |
| [4] | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | SCORING A ROUND · STARTING A NEW ROUND | p.4 | no quote on the wire |
| [5] | RULEBOOK Sushi Roll — Rulebook (corpus doc 1234) | ENDING THE GAME | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 207 ms · first delta 1064 ms · total 6172 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 0 ms · retrieval 207 ms · ask 5963 ms · gateway work 6172 ms · total 6172 ms
- tokens in (the prompt the answerer read)
- 2292
- tokens out (what the answerer generated)
- 1024
- tok/sec
- 202.7 tok/sec — 1024 output tokens in 5.053 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 24s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 4s 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 1164), 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.