You asked
How do I play?
Answered counted as answeredAsked with: Grand Austria Hotelbg-182874-en-1e
So says the rulebook. So plays the table.
🔧 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 156 ms · ask 17263 ms · total 17421 ms
- single-flight (PR-5)
- queued 0 ms · generation 17421 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.047493, "snippet": "Then, play will go around the table as indicated by the turn order tiles , in increasing numerical order. When play comes around to you, you can either take a turn or pass . The following sections explain what either of these options mean. If you decide to take a turn, immediately carry out the foll", "headingPath": "Personal Play Area · Taking a Turn · 1. Taking a Guest", "sharpsignalDocId": 288}, {"page": 4, "score": 0.046239, "snippet": "Select the turn order tiles for the appropriate number of players and return the rest to the game box. Randomly select a start player , who gets the tile showing '1'. The next player clockwise gets the tile showing '2', and so on. Take a hotel board and the six markers in a color of your choice. Dec", "headingPath": "Personal Play Area", "sharpsignalDocId": 288}, {"page": 5, "score": 0.044854, "snippet": "Draw 6 staff cards from the deck into your hand, keeping them hidden from the other players. Introductory Variant: On your first play, instead of drawing from the shuffled deck, deal each player a starting set of staff cards: the start player gets the 'A' set, the next player clockwise gets the 'B' ", "headingPath": "Personal Play Area", "sharpsignalDocId": 288}, {"page": 10, "score": 0.044758, "snippet": "Instead of taking a turn, you can simply pass . By doing so, you do not forfeit your turn, you just postpone it until later, when the dice have been re-rolled. When you pass, you must wait until all other players have also passed or taken both of their turns. When that happens, take the remaining di", "headingPath": "Passing", "sharpsignalDocId": 288}, {"page": 4, "score": 0.044408, "snippet": "Place the game board in the middle of the play area. The game board features spaces for objective cards, guest cards, and Emperor tiles; also, the Round, Emperor, and score tracks. Place the Round marker on the first space of the Round track. Sort the Emperor tiles by letter (A, B, and C) ; shuffle ", "headingPath": "4 hotel boards (double-sided)", "sharpsignalDocId": 288}, {"page": 12, "score": 0.04207, "snippet": "After the Emperor scoring of round 7, there is a final scoring: Score your staff cards with the symbol. (For details on what each card does, see the appendix, pages 13-15.) Score the occupied rooms in your hotel: Occupied rooms on the first, second, third, and fourth floor each score 1, 2, 3, or 4 v", "headingPath": "Game End and Final Scoring", "sharpsignalDocId": 288}, {"page": 11, "score": 0.030303, "snippet": "As indicated on the Round track, at the end of the 3rd, 5th, and 7th round, an Emperor scoring takes place, in which you will be rewarded or punished based on your progress on the Emperor track. During an Emperor scoring, all players must carry out the following steps: Score victory points based on ", "headingPath": "Emperor Scoring", "sharpsignalDocId": 288}, {"page": 13, "score": 0.030092, "snippet": "Staff cards provide useful effects throughout the game, e.g., bending the rules for you, or providing victory points at the end of the game. There are four types of staff, indicated by a symbol above the effect box: These staff activate only once : immediately after you play them. You can ignore the", "headingPath": "Staff Cards", "sharpsignalDocId": 288}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 5, "quote": null, "headingPath": "Personal Play Area", "sharpsignalDocId": 288}, {"page": 6, "quote": null, "headingPath": "Personal Play Area · Taking a Turn · 1. Taking a Guest", "sharpsignalDocId": 288}, {"page": 8, "quote": null, "headingPath": "· Playing a Staff Card · · Imitating a Main Action · Additional Actions · · Serving Items", "sharpsignalDocId": 288}, {"page": 10, "quote": null, "headingPath": "Passing", "sharpsignalDocId": 288}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 288 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 288 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 0.93042 of 1581 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 27, 2026 02:34 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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area · Taking a Turn · 1. Taking a Guest | p.6 | 0.047493 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area | p.4 | 0.046239 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area | p.5 | 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 |
| #4 | RULEBOOK Grand Austria Hotel — Rulebook (corpus doc 288) | Passing | p.10 | 0.044758 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | 4 hotel boards (double-sided) | p.4 | 0.044408 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Game End and Final Scoring | p.12 | 0.04207 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Emperor Scoring | p.11 | 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 |
| #8 | RULEBOOK Grand Austria Hotel — Rulebook (corpus doc 288) | Staff Cards | p.13 | 0.030092 (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 38 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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area | p.4 | #2 | 0.046239 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area | p.5 | #3 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Grand Austria Hotel — Rulebook (corpus doc 288) | 4 hotel boards (double-sided) | p.4 | #5 | 0.044408 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Guest Cards | p.16 | #11 | 0.029116 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Guest Cards | p.17 | #12 | 0.026989 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Passing | p.10 | #4 | 0.044758 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | · Playing a Staff Card · · Imitating a Main Action · Additional Actions · · Serving Items | p.8 | #10 | 0.029387 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area · Taking a Turn · 1. Taking a Guest | p.6 | #1 | 0.047493 (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 Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area | p.5 | no quote on the wire |
| [2] | RULEBOOK Grand Austria Hotel — Rulebook (corpus doc 288) | Personal Play Area · Taking a Turn · 1. Taking a Guest | p.6 | no quote on the wire |
| [3] | RULEBOOK Grand Austria Hotel — Rulebook (corpus doc 288) | · Playing a Staff Card · · Imitating a Main Action · Additional Actions · · Serving Items | p.8 | no quote on the wire |
| [4] | RULEBOOK Grand Austria Hotel — Rulebook (corpus doc 288) | Passing | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 156 ms · first delta 2256 ms · total 17421 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 156 ms · ask 17263 ms · gateway work 17421 ms · total 17421 ms
- tokens in (the prompt the answerer read)
- 3455
- tokens out (what the answerer generated)
- 457
- tok/sec
- 30.3 tok/sec — 457 output tokens in 15.094 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 32s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 1s 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 217), 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.