You asked
How do I play?
Answered counted as answeredAsked with: Hanabibg-98778-en-1e
Question closed. Friendships intact.
🔧 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 86 ms · ask 4332 ms · total 7758 ms
- single-flight (PR-5)
- queued 3338 ms · generation 4420 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 1, "score": 0.048387, "snippet": "A player who is given information can rearrange his hand in order to put the cards concerned in an order which is easier for him to remember (on the left, on the right, further up or down). The players can look at the cards in the discarded pile at any time. If a player discards a card that he has n", "headingPath": "STRATEGIC ADVICE · COMMUNICATING WHILE PLAYING HANABI", "sharpsignalDocId": 194}, {"page": 2, "score": 0.048172, "snippet": "CRUCIAL! : The players MUST NOT look at the cards which are dealt to them! They must pick them up so that the other players can see the fronts of the cards ( colored with numbers) and they only see the backs ( black and white). They are not allowed to look at the fronts of the cards that they hold d", "headingPath": "Getting Feady · 'The Game · 1. GIVING A PIECE OF INFORMATION · 2. DISCARDING A CARD", "sharpsignalDocId": 194}, {"page": 2, "score": 0.048139, "snippet": "The player takes a card from his hand and plays it to the table. Two options are possible: A. The card either begins, adds to, or completes a firework and it is then added to the appropriate color firework. or The card doesn't begin, add to or complete any firework. Discard the card then remove the ", "headingPath": "3. PLAYING A CARD · How the fireworks are built: · BONUS for completing a firework · Eud of the game · SCORE", "sharpsignalDocId": 194}, {"page": 1, "score": 0.046875, "snippet": "Artistic impression is determined by the Artisan League Of Fireworks Technicians reference scale: <=5 horrible, booed by the crowd... 6-10 mediocre, just a hint of scattered applause... 11-15 honorable attempt, but quickly forgotten... 16-20 excellent, crowd pleasing. 21-24 amazing, they will be tal", "headingPath": "POINTS OVERALL IMPRESSION · VARIANT 1 · VARIANT 2 · VARIANT 3 · EXAMPLE: · VARIANT 4", "sharpsignalDocId": 194}, {"page": 1, "score": 0.046642, "snippet": "Hanabi is a cooperative game, i.e. a game where the players do not play against each other but work together towards a common goal. In this case they are absent minded firework manufacturers who accidentally mixed up powders, fuses and rockets from a firework display. The show is about to start and ", "headingPath": "Summary · Getting Feady", "sharpsignalDocId": 194}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 1, "quote": null, "headingPath": "Summary · Getting Feady", "sharpsignalDocId": 194}, {"page": 2, "quote": null, "headingPath": "Getting Feady · 'The Game · 1. GIVING A PIECE OF INFORMATION · 2. DISCARDING A CARD", "sharpsignalDocId": 194}, {"page": 2, "quote": null, "headingPath": "3. PLAYING A CARD · How the fireworks are built: · BONUS for completing a firework · Eud of the game · SCORE", "sharpsignalDocId": 194}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 194 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 194 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 0.91216 of 2220 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 27, 2026 02:22 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 Hanabi — Rulebook (corpus doc 194) | STRATEGIC ADVICE · COMMUNICATING WHILE PLAYING HANABI | p.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)) | 300 |
| #2 | RULEBOOK Hanabi — Rulebook (corpus doc 194) | Getting Feady · 'The Game · 1. GIVING A PIECE OF INFORMATION · 2. DISCARDING A CARD | p.2 | 0.048172 (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 Hanabi — Rulebook (corpus doc 194) | 3. PLAYING A CARD · How the fireworks are built: · BONUS for completing a firework · Eud of the game · SCORE | p.2 | 0.048139 (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 Hanabi — Rulebook (corpus doc 194) | POINTS OVERALL IMPRESSION · VARIANT 1 · VARIANT 2 · VARIANT 3 · EXAMPLE: · VARIANT 4 | p.1 | 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 |
| #5 | RULEBOOK Hanabi — Rulebook (corpus doc 194) | Summary · Getting Feady | p.1 | 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 |
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 5 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 Hanabi — Rulebook (corpus doc 194) | 3. PLAYING A CARD · How the fireworks are built: · BONUS for completing a firework · Eud of the game · SCORE | p.2 | #3 | 0.048139 (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 Hanabi — Rulebook (corpus doc 194) | Summary · Getting Feady | p.1 | #5 | 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 |
| #3 | RULEBOOK Hanabi — Rulebook (corpus doc 194) | POINTS OVERALL IMPRESSION · VARIANT 1 · VARIANT 2 · VARIANT 3 · EXAMPLE: · VARIANT 4 | p.1 | #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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Hanabi — Rulebook (corpus doc 194) | Getting Feady · 'The Game · 1. GIVING A PIECE OF INFORMATION · 2. DISCARDING A CARD | p.2 | #2 | 0.048172 (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 Hanabi — Rulebook (corpus doc 194) | STRATEGIC ADVICE · COMMUNICATING WHILE PLAYING HANABI | p.1 | #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
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 Hanabi — Rulebook (corpus doc 194) | Summary · Getting Feady | p.1 | no quote on the wire |
| [2] | RULEBOOK Hanabi — Rulebook (corpus doc 194) | Getting Feady · 'The Game · 1. GIVING A PIECE OF INFORMATION · 2. DISCARDING A CARD | p.2 | no quote on the wire |
| [3] | RULEBOOK Hanabi — Rulebook (corpus doc 194) | 3. PLAYING A CARD · How the fireworks are built: · BONUS for completing a firework · Eud of the game · SCORE | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 86 ms · first delta 947 ms · total 7758 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 3338 ms · retrieval 86 ms · ask 4332 ms · gateway work 4420 ms · total 7758 ms
- tokens in (the prompt the answerer read)
- 2365
- tokens out (what the answerer generated)
- 696
- tok/sec
- 203.7 tok/sec — 696 output tokens in 3.417 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 4s 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 112), 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.