You asked
How do I play?
Answered counted as answeredAsked with: Euchrebg-6901-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 77 ms · ask 8857 ms · total 28286 ms
- single-flight (PR-5)
- queued 19351 ms · generation 8935 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.04866, "snippet": "Rubber or game scores must be kept on a whist marker, or on a sheet of paper. PLAYERS. Euchre may be played by any number of persons from two to seven; but in the seven-handed game the full pack of fifty-three cards is used. Whatever the number of players, they cut for positions at the table, for pa", "headingPath": "EUCHRE.", "sharpsignalDocId": 224}, {"page": 3, "score": 0.045635, "snippet": "Some persons imagine that the adversaries can prevent an exposed card from being played; but such is not the case in Euchre. A person playing a lone hand is not liable to any penalty for exposing his cards, nor for leading out of turn, for he has no partner to derive any benefit from the information", "headingPath": "EUCHRE.", "sharpsignalDocId": 224}, {"page": 6, "score": 0.045009, "snippet": "If one player orders up the trump, neither his partner nor his adversary can play alone; and if the dealer’s partner assists, that prevents the dealer from playing a lone hand. In many clubs the mistake is made of allowing the dealer to play alone on his partner’s assist; or letting the pone play al", "headingPath": "", "sharpsignalDocId": 224}, {"page": 14, "score": 0.044854, "snippet": "It is considered imperative for a player holding the Joker, or the right bower guarded, to play alone against the lone hand, taking his partner's best; for as it is evident that the lone hand cannot succeed, there is a better chance to euchre it with all the strength in one hand than divided. If any", "headingPath": "RAILROAD EUCHRE.", "sharpsignalDocId": 224}, {"page": 7, "score": 0.044764, "snippet": "Euchre — Foster's Complete Hoyle (1914) 7 for he has no partner to derive any benefit from the information conveyed. Leading Out of Turn. Should any person, not playing alone, lead out of turn, the adversaries may call a suit from the player in error, or from his partner, when it is next the turn of", "headingPath": "", "sharpsignalDocId": 224}, {"page": 13, "score": 0.044023, "snippet": "Playing. All being seated, the deal is cut for at each table, and play begins. There is no cutting for partners, that being settled in the original drawing. Five points is a game, and after that number is reached by either side at the head table, the bell is struck. Lone hands are usually barred at ", "headingPath": "PROGRESSIVE EUCHRE.", "sharpsignalDocId": 224}, {"page": 4, "score": 0.042046, "snippet": "Euchre — Foster's Complete Hoyle (1914) 4 partners, and they play against the others without any change in their positions at the table. When six play, three are partners against the other three, and the opposing players sit alternately round the table. STAKES. If there is any stake upon the game, i", "headingPath": "", "sharpsignalDocId": 224}, {"page": 3, "score": 0.039938, "snippet": "Any person who is tempted to bet on any game in the Euchre family should remember the advice of the worldly-wise Parisian to his son: 'Until you have four eyes in your head, risk not your gold at Écarté.' SUGGESTIONS FOR GOOD PLAY. The chief points for the beginner to understand are. When to order u", "headingPath": "EUCHRE.", "sharpsignalDocId": 224}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "EUCHRE.", "sharpsignalDocId": 224}, {"page": 4, "quote": null, "headingPath": "", "sharpsignalDocId": 224}, {"page": 19, "quote": null, "headingPath": "EUCHRE LAWS.", "sharpsignalDocId": 224}, {"page": 3, "quote": null, "headingPath": "EUCHRE.", "sharpsignalDocId": 224}, {"page": 3, "quote": null, "headingPath": "EUCHRE.", "sharpsignalDocId": 224}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 224 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 224 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 0.90715 of 1777 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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | 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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | 0.045635 (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 Euchre — Rulebook (corpus doc 224) | p.6 | 0.045009 (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 Euchre — Rulebook (corpus doc 224) | RAILROAD EUCHRE. | p.14 | 0.044854 (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 Euchre — Rulebook (corpus doc 224) | p.7 | 0.044764 (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 Euchre — Rulebook (corpus doc 224) | PROGRESSIVE EUCHRE. | p.13 | 0.044023 (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 Euchre — Rulebook (corpus doc 224) | p.4 | 0.042046 (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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | 0.039938 (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 60 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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | #9 | 0.030886 (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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | #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 Euchre — Rulebook (corpus doc 224) | p.4 | #7 | 0.042046 (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 Euchre — Rulebook (corpus doc 224) | CUT-THROAT EUCHRE. · SET-BACK EUCHRE. | p.11 | #39 | 0.020101 (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 |
| #5 | RULEBOOK Euchre — Rulebook (corpus doc 224) | EUCHRE LAWS. | p.19 | #36 | 0.020619 (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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | #17 | 0.025482 (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 Euchre — Rulebook (corpus doc 224) | EUCHRE LAWS. | p.21 | #22 | 0.024749 (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 Euchre — Rulebook (corpus doc 224) | PROGRESSIVE EUCHRE. | p.13 | #6 | 0.044023 (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 Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | no quote on the wire |
| [2] | RULEBOOK Euchre — Rulebook (corpus doc 224) | p.4 | no quote on the wire | |
| [3] | RULEBOOK Euchre — Rulebook (corpus doc 224) | EUCHRE LAWS. | p.19 | no quote on the wire |
| [4] | RULEBOOK Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | no quote on the wire |
| [5] | RULEBOOK Euchre — Rulebook (corpus doc 224) | EUCHRE. | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 77 ms · first delta 4513 ms · total 28286 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 19351 ms · retrieval 77 ms · ask 8857 ms · gateway work 8935 ms · total 28286 ms
- tokens in (the prompt the answerer read)
- 4123
- tokens out (what the answerer generated)
- 571
- tok/sec
- 131.4 tok/sec — 571 output tokens in 4.345 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 37s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, 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 150), 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.