You asked
How do I play?
Answered counted as answeredAsked with: Spadesbg-592-en-1e
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 99 ms · ask 3121 ms · total 3221 ms
- single-flight (PR-5)
- queued 0 ms · generation 3221 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 10, "score": 0.04866, "snippet": "Certain rounds of play allow the top two (2) players to advance and other rounds of play allow one (1) player to advance. Please see Schedule for additional details. Ties and Tie Breakers: Rounds 1 and 2 (the top two players at each table will advance): There will be no tie breaker for 3rd Place as ", "headingPath": "Spades Play:", "sharpsignalDocId": 168}, {"page": 9, "score": 0.047627, "snippet": "deducted from the bidding player's score. There is no difference between bidding zero (0) and bidding nil. Blind nil is not allowed at the Event. Once a bid is made it cannot be changed. Any book(s) collected over the bid amount will be scored as +1 point. Sandbags Sandbags will be in effect at the ", "headingPath": "Spades Play:", "sharpsignalDocId": 168}, {"page": 9, "score": 0.047387, "snippet": "If multiple spades are played in a round, the winner of the round is the player with the highest-ranking spade. (See Rule 57(b) for additional information about card rankings.) The contents of each completed book cannot be viewed once the dealer has picked them up, except to determine if a player re", "headingPath": "Spades Play:", "sharpsignalDocId": 168}, {"page": 5, "score": 0.04647, "snippet": "The World Spades Championship® is a single player Spades tournament. Players that collude will not be permitted. Assisted play will not be permitted. Participants who abuse this rule may be subject to exclusion from present and future World Spades Championship® and Parent Company Events by sole and ", "headingPath": "Tournament Play:", "sharpsignalDocId": 168}, {"page": 8, "score": 0.045715, "snippet": "Players The World Spades Championship® will be a single-player Spades tournament. There will be four (4) players per table. All players will be assigned to a table and a seat by Event staff before the start of play. Players are required to sit in their assigned seat at their assigned table. Dealers ", "headingPath": "Spades Play:", "sharpsignalDocId": 168}, {"page": 11, "score": 0.044235, "snippet": "iii) Rounds 5 and 6 ( all players will advance from Round 5 to Round 6): If there is a tie between any players at the table during Round 5 (Semifinal Round) or Round 6 (Championship Round), the determining factor to break the tie between the players involved will be (in order): (a) The player with t", "headingPath": "Rankings and Prizes:", "sharpsignalDocId": 168}, {"page": 6, "score": 0.043716, "snippet": "Cheating is defined as any such act engaged in by a Participant to break the established rules of play to gain an advantage. Cheating includes, but is not limited to, acts such as: collusion; assisted play; card marking; card substitution; interacting with the electronic scoring system; reneging; or", "headingPath": "Tournament Play:", "sharpsignalDocId": 168}, {"page": 4, "score": 0.043691, "snippet": "Participants will be assigned to a table and seat through random selection in Round 1. Table assignments in subsequent rounds will be based on the Participant's scores from the previous round(s), in that a Participant with the highest score will play the Participant with the lowest score from the pr", "headingPath": "Tournament Play:", "sharpsignalDocId": 168}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "Rules of Play", "sharpsignalDocId": 169}, {"page": 8, "quote": null, "headingPath": "Spades Play:", "sharpsignalDocId": 168}, {"page": 9, "quote": null, "headingPath": "Spades Play:", "sharpsignalDocId": 168}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 168 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 168 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 0.88533 of 968 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 28, 2026 11:52 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 Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.10 | 0.04866 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.9 | 0.047627 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.9 | 0.047387 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Tournament Play: | p.5 | 0.04647 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.8 | 0.045715 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Rankings and Prizes: | p.11 | 0.044235 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Tournament Play: | p.6 | 0.043716 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Tournament Play: | p.4 | 0.043691 (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 24 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 Spades — Event Registration Notice (corpus doc 169) | Rules of Play | p.2 | #9 | 0.031281 (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 |
| #2 | RULEBOOK Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.10 | #1 | 0.04866 (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 |
| #3 | RULEBOOK Spades — WSC Official Tournament Rules (corpus doc 168) | Tournament Play: | p.4 | #8 | 0.043691 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Tournament Play: | p.6 | #7 | 0.043716 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Registration: | p.3 | #15 | 0.026905 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Tournament Play: | p.7 | #12 | 0.027984 (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 |
| #7 | RULEBOOK Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.8 | #5 | 0.045715 (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 Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.9 | #3 | 0.047387 (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 Spades — Event Registration Notice (corpus doc 169) | Rules of Play | p.2 | no quote on the wire |
| [2] | RULEBOOK Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.8 | no quote on the wire |
| [3] | RULEBOOK Spades — WSC Official Tournament Rules (corpus doc 168) | Spades Play: | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 99 ms · first delta 1557 ms · total 3221 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 99 ms · ask 3121 ms · gateway work 3221 ms · total 3221 ms
- tokens in (the prompt the answerer read)
- 3029
- tokens out (what the answerer generated)
- 322
- tok/sec
- 200.9 tok/sec — 322 output tokens in 1.603 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 54s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 6s 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 91), 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.