You asked
How do I play?
Answered counted as answeredAsked with: Bruxelles 1893bg-144592-en-1e
That's the page. Back to 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 76 ms · ask 4966 ms · total 5464 ms
- single-flight (PR-5)
- queued 420 ms · generation 5044 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.048172, "snippet": "THE ACTIONS OF THE ART NOUVEAU BOARD In order to take an action on this board, the player must place an Assistant pawn on an action space in the available area (the area defined in the Stock Exchange phase). He must accompany his assistant with a bid of his choice of at least 1 BF (we suggest that y", "headingPath": "HOW TO PLAY · Workshop Action", "sharpsignalDocId": 559}, {"page": 6, "score": 0.048139, "snippet": "The player constructs a Building tile from his personal board on the Art Nouveau board. This allows him to finance the construction of the Masterpiece shown on his personal board (the tile depicts a portion of the masterpiece). T o perform this action, the player must proceed step by step: He must p", "headingPath": "Construction Action", "sharpsignalDocId": 559}, {"page": 7, "score": 0.046402, "snippet": "The player meets Public Figures on the Grand Plaza, and employs their services. He can immediately activate Public Figure cards from those in front of him and utilize their effects. Only the upright cards (not rotated 90°) can be activated. The maximum number of cards that the player can activate wi", "headingPath": "Grand Plaza Action", "sharpsignalDocId": 559}, {"page": 4, "score": 0.046176, "snippet": "Each line of the Stock Exchange card corresponds to a different number of players, indicated by these icons. Read only the line that corresponds to the number of players participating in the game. On the Art Nouveau board, there are shields for the City of Brussels at the intersections of the 25 act", "headingPath": "CONCEPT OF THE GAME · HOW TO PLAY", "sharpsignalDocId": 559}, {"page": 3, "score": 0.04598, "snippet": "A game of Bruxelles 1893 is played over five rounds. At the beginning of a round, the first player begins by defining the available area of the Art Nouveau board. Then the players take turns choosing an action on one of the two game boards: the Art Nouveau board or the Brussels board. Taking an acti", "headingPath": "CONCEPT OF THE GAME", "sharpsignalDocId": 559}, {"page": 12, "score": 0.045037, "snippet": "The 2-player game takes place in exactly the same way, with one exception: Each player starts the game with an Assistant pawn of a neutral color (selected from the unplayed colors). At the start of the Action phase, starting with the first player, each player must play a neutral Assistant pawn on an", "headingPath": "APPENDIX 3 : 2-PLAYER GAME · Thanks:", "sharpsignalDocId": 559}, {"page": 6, "score": 0.032258, "snippet": "The player approaches a Public Figure of Brussels during a theatrical perfor- mance in order to enlist his services. The player chooses a Public Figure card from the 4 cards of the display. The card on the right is free, while the second costs 1 BF, the third costs 2 BF, and the fourth costs 3 BF. T", "headingPath": "Royal Theater Action · Two options are then available to him: · Materials Action · Compass rules", "sharpsignalDocId": 559}, {"page": 5, "score": 0.030769, "snippet": "The player sells one of his works of art and exhibits it in the shop window. He must proceed step by step: 1. The player can move the Workshop cursor, horizontally and/or vertically, a number of spaces equal to the total number of works he has in front of him. From among his Work of Art tiles, he ch", "headingPath": "Sale Action", "sharpsignalDocId": 559}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "CONCEPT OF THE GAME · HOW TO PLAY", "sharpsignalDocId": 559}, {"page": 3, "quote": null, "headingPath": "CONCEPT OF THE GAME", "sharpsignalDocId": 559}, {"page": 5, "quote": null, "headingPath": "HOW TO PLAY · Workshop Action", "sharpsignalDocId": 559}, {"page": 5, "quote": null, "headingPath": "Sale Action", "sharpsignalDocId": 559}, {"page": 6, "quote": null, "headingPath": "Construction Action", "sharpsignalDocId": 559}, {"page": 10, "quote": null, "headingPath": "5. Majority on the Brussels board", "sharpsignalDocId": 559}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 559 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 559 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 0.92826 of 2551 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 28, 2026 02:29 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 Bruxelles 1893 — Rulebook (corpus doc 559) | HOW TO PLAY · Workshop Action | p.5 | 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 |
| #2 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | Construction Action | p.6 | 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 |
| #3 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | Grand Plaza Action | p.7 | 0.046402 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | CONCEPT OF THE GAME · HOW TO PLAY | p.4 | 0.046176 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | CONCEPT OF THE GAME | p.3 | 0.04598 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | APPENDIX 3 : 2-PLAYER GAME · Thanks: | p.12 | 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 |
| #7 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | Royal Theater Action · Two options are then available to him: · Materials Action · Compass rules | p.6 | 0.032258 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | Sale Action | p.5 | 0.030769 (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 20 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 Bruxelles 1893 — Rulebook (corpus doc 559) | HOW TO PLAY · Workshop Action | p.5 | #1 | 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 |
| #2 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | CONCEPT OF THE GAME · HOW TO PLAY | p.4 | #4 | 0.046176 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | CONCEPT OF THE GAME | p.3 | #5 | 0.04598 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | 5. Majority on the Brussels board | p.10 | #9 | 0.029211 (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 Bruxelles 1893 — Rulebook (corpus doc 559) | Construction Action | p.6 | #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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | Sale Action | p.5 | #8 | 0.030769 (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 + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | APPENDIX 3 : 2-PLAYER GAME · Thanks: | p.12 | #6 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | SETUP | p.2 | #10 | 0.029199 (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 |
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 Bruxelles 1893 — Rulebook (corpus doc 559) | CONCEPT OF THE GAME · HOW TO PLAY | p.4 | no quote on the wire |
| [2] | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | CONCEPT OF THE GAME | p.3 | no quote on the wire |
| [3] | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | HOW TO PLAY · Workshop Action | p.5 | no quote on the wire |
| [4] | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | Sale Action | p.5 | no quote on the wire |
| [5] | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | Construction Action | p.6 | no quote on the wire |
| [6] | RULEBOOK Bruxelles 1893 — Rulebook (corpus doc 559) | 5. Majority on the Brussels board | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 76 ms · first delta 1491 ms · total 5464 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 420 ms · retrieval 76 ms · ask 4966 ms · gateway work 5044 ms · total 5464 ms
- tokens in (the prompt the answerer read)
- 3816
- tokens out (what the answerer generated)
- 701
- tok/sec
- 201.5 tok/sec — 701 output tokens in 3.479 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 38s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 7s 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 491), 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.