You asked
How do I play?
Answered counted as answeredAsked with: Final Girlbg-277659-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 98 ms · ask 10340 ms · total 10818 ms
- single-flight (PR-5)
- queued 377 ms · generation 10441 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.048387, "snippet": "GAMEPL AY The game is played in turns, each consisting of five phases. You will play until either you or the Killer are dead! The Game Turn A turn in Final Girl has 5 phases: 1. The Action phase 2. The Planning phase 3. The Killer phase 4. The Panic phase 5. The Upkeep phase The Action Phase During ", "headingPath": "", "sharpsignalDocId": 959}, {"page": 6, "score": 0.046642, "snippet": "The game is played in turns, each consisting of five phases. You will play until either you or the Killer are dead! A turn in Final Girl has 5 phases: The Action phase The Planning phase The Killer phase The Panic phase The Upkeep phase During this phase you play Action cards to move, attack, rest, ", "headingPath": "GAMEPLAY · The Game Turn · The Action Phase · ACTION CARDS · Horror Rolls", "sharpsignalDocId": 959}, {"page": 10, "score": 0.046244, "snippet": "You can continue playing Action cards until either: You decide to stop. An Action card results in You run out of cards to play. The Time marker goes BELOW zero (if it is on zero you may still continue). Do not be afraid to end the Action phase while you still have some cards in your hand. Sometimes ", "headingPath": "Ending the Action Phase · The Planning Phase · You may NOT:", "sharpsignalDocId": 959}, {"page": 5, "score": 0.045287, "snippet": "Choose a Killer and a Location from among the Feature Films you have. Remove the Killer and Location boards (remember, these are on the reverse side of the box covers!) and their associated component trays in preparation for setup. Open the Core Box and choose a Final Girl card or pick one randomly.", "headingPath": "The location board · Core box", "sharpsignalDocId": 959}, {"page": 10, "score": 0.045037, "snippet": "Zero Cost Cards Unless doing so would put you over the hand limit of 10 cards, you may ALWAYS purchase all Zero Cost Action cards from the Action Tableau because doing so does not require you to spend Time (remember, this doesn’t apply to cards in the discard pile!). You may purchase Zero Cost cards", "headingPath": "", "sharpsignalDocId": 959}, {"page": 3, "score": 0.042961, "snippet": "Health Track. The left side of the board has the Final Health token space and the health track. Horror Track. In the middle of the board is the Horror track. When Horror increases or decreases you will move the Horror marker (one of the Killer meeples) accordingly. This is called the Horror Level, a", "headingPath": "THE PLAYER BOARD", "sharpsignalDocId": 959}, {"page": 14, "score": 0.031746, "snippet": "Items can be found by searching while you are on a Search space . Many items must be held in your hands to be used. These items have one or two hand icons on the card. Other, smaller items can be used from your backpack and thus do not have any hand icons on them. Whenever you gain an item after a s", "headingPath": "Items", "sharpsignalDocId": 959}, {"page": 14, "score": 0.03125, "snippet": "Game End The game ends as soon as you have killed the Killer (victory) or you are dead (defeat). In the rare case that both happen at the same time, you are still victorious because you accomplished your goal, even if it required the ultimate sacrifice. ADDITIONAL RULE S Items Items can be found by ", "headingPath": "", "sharpsignalDocId": 959}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "GAMEPLAY · The Game Turn · The Action Phase · ACTION CARDS · Horror Rolls", "sharpsignalDocId": 959}, {"page": 6, "quote": null, "headingPath": "", "sharpsignalDocId": 959}, {"page": 9, "quote": null, "headingPath": "Attacking · Gaining/Losing Time · Discarding action cards to gain time", "sharpsignalDocId": 959}, {"page": 10, "quote": null, "headingPath": "Ending the Action Phase · The Planning Phase · You may NOT:", "sharpsignalDocId": 959}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 959 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 959 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 0.88242 of 1786 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 24, 2026 14:57 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 Final Girl — Rulebook (corpus doc 959) | p.6 | 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 Final Girl — Rulebook (corpus doc 959) | GAMEPLAY · The Game Turn · The Action Phase · ACTION CARDS · Horror Rolls | p.6 | 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 |
| #3 | RULEBOOK Final Girl — Rulebook (corpus doc 959) | Ending the Action Phase · The Planning Phase · You may NOT: | p.10 | 0.046244 (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 Final Girl — Rulebook (corpus doc 959) | The location board · Core box | p.5 | 0.045287 (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 Final Girl — Rulebook (corpus doc 959) | p.10 | 0.045037 (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 Final Girl — Rulebook (corpus doc 959) | THE PLAYER BOARD | p.3 | 0.042961 (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 Final Girl — Rulebook (corpus doc 959) | Items | p.14 | 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 |
| #8 | RULEBOOK Final Girl — Rulebook (corpus doc 959) | p.14 | 0.03125 (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 75 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 Final Girl — Rulebook (corpus doc 959) | The location board · Core box | p.5 | #4 | 0.045287 (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 Final Girl — Rulebook (corpus doc 959) | Defending Against an Attack with a reaction card | p.12 | #22 | 0.024501 (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 Final Girl — Rulebook (corpus doc 959) | Attacking · Gaining/Losing Time · Discarding action cards to gain time | p.9 | #16 | 0.025894 (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 Final Girl — Rulebook (corpus doc 959) | THE PLAYER BOARD | p.3 | #6 | 0.042961 (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 Final Girl — Rulebook (corpus doc 959) | p.10 | #12 | 0.028259 (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 Final Girl — Rulebook (corpus doc 959) | Ending the Action Phase · The Planning Phase · You may NOT: | p.10 | #3 | 0.046244 (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 Final Girl — Rulebook (corpus doc 959) | GAMEPLAY · The Game Turn · The Action Phase · ACTION CARDS · Horror Rolls | p.6 | #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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Final Girl — Rulebook (corpus doc 959) | p.6 | #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 Final Girl — Rulebook (corpus doc 959) | GAMEPLAY · The Game Turn · The Action Phase · ACTION CARDS · Horror Rolls | p.6 | no quote on the wire |
| [2] | RULEBOOK Final Girl — Rulebook (corpus doc 959) | p.6 | no quote on the wire | |
| [3] | RULEBOOK Final Girl — Rulebook (corpus doc 959) | Attacking · Gaining/Losing Time · Discarding action cards to gain time | p.9 | no quote on the wire |
| [4] | RULEBOOK Final Girl — Rulebook (corpus doc 959) | Ending the Action Phase · The Planning Phase · You may NOT: | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 98 ms · first delta 5928 ms · total 10818 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 377 ms · retrieval 98 ms · ask 10340 ms · gateway work 10441 ms · total 10818 ms
- tokens in (the prompt the answerer read)
- 3796
- tokens out (what the answerer generated)
- 585
- tok/sec
- 132.7 tok/sec — 585 output tokens in 4.409 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 21s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 10s 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 213), 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.