You asked
How do I play?
Answered counted as answeredAsked with: Copenhagenbg-269595-en-1e
Answer in hand — your move.
🔧 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 81 ms · ask 6016 ms · total 62231 ms
- single-flight (PR-5)
- queued 56131 ms · generation 6100 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.048916, "snippet": "Beginning with the first player (we recommend the oldest player goes first) , and con tinuing clockwise, each player draws their starting hand from the card supply. Draw the following number of cards depending on the number of players: | | Initial starting hand | Initial starting hand | Initial star", "headingPath": "Start of the game · A) Take cards · Maximum Hand Size · End of Game card", "sharpsignalDocId": 1300}, {"page": 2, "score": 0.048652, "snippet": "Place the harbor and the scoring track in the center of the playing area, as shown in the illustration. Stack the facade tiles by color and shape within reach of all players. Shuffle the facade cards and stack them face down on the harbor. This is the card supply. In a game with 3 players, remove 2 ", "headingPath": "Game Set-up · Red facade card", "sharpsignalDocId": 1300}, {"page": 5, "score": 0.031746, "snippet": "After placing the tile, the player performs one of the three special actions for each coat of arms covered or row marked with a coat of arms completed: Special tiles The player takes one special tile, placing it immediately according to the construction rules. These tiles are like all other tiles, e", "headingPath": "Coat of arms actions · 3. Score points · Row: · Column: · Ending the Game", "sharpsignalDocId": 1300}, {"page": 6, "score": 0.03125, "snippet": "The ability tiles provide special actions that can be used in combination with the actions and . Players may use as many of their active ability tiles during their turn as they would like. Used ability tiles are flipped from their active side to their inactive side. By performing a coat of arms acti", "headingPath": "Ability Tiles · Any cards · Additional card · Construction discount · Change of colors · 2 nd case:", "sharpsignalDocId": 1300}, {"page": 1, "score": 0.030769, "snippet": "1 Scoring track 1 Harbor 4 Houses (1 per player colour (dark-red, -blue, -yellow, -green)) Note: The colors of the houses do not correspond to the colors of the facade cards or the facade tiles. 20 Ability tiles - 5 types x 4 tiles Front sides (active side) Any cards Additional card Construction dis", "headingPath": "Components · Object of the Game · Number x squares", "sharpsignalDocId": 1300}, {"page": 4, "score": 0.030303, "snippet": "The player exchanges cards from their hand for a facade tile and attaches it to their house. They then gain points for any rows or columns completed this turn. The active player discards cards from their hand in exchange for a facade tile, following two rules: The number of cards must match the numb", "headingPath": "B) Construct facade · 1. Pick a facade tile · Exception: · 2. Placing a Facade Tile (Construction Rules)", "sharpsignalDocId": 1300}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "Game Set-up · Red facade card", "sharpsignalDocId": 1300}, {"page": 3, "quote": null, "headingPath": "Start of the game · A) Take cards · Maximum Hand Size · End of Game card", "sharpsignalDocId": 1300}, {"page": 4, "quote": null, "headingPath": "B) Construct facade · 1. Pick a facade tile · Exception: · 2. Placing a Facade Tile (Construction Rules)", "sharpsignalDocId": 1300}, {"page": 6, "quote": null, "headingPath": "Ability Tiles · Any cards · Additional card · Construction discount · Change of colors · 2 nd case:", "sharpsignalDocId": 1300}, {"page": 5, "quote": null, "headingPath": "Coat of arms actions · 3. Score points · Row: · Column: · Ending the Game", "sharpsignalDocId": 1300}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1300 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1300 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 0.91011 of 3293 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 03:14 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 Copenhagen — Rulebook (corpus doc 1300) | Start of the game · A) Take cards · Maximum Hand Size · End of Game card | p.3 | 0.048916 (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 Copenhagen — Rulebook (corpus doc 1300) | Game Set-up · Red facade card | p.2 | 0.048652 (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 Copenhagen — Rulebook (corpus doc 1300) | Coat of arms actions · 3. Score points · Row: · Column: · Ending the Game | p.5 | 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 |
| #4 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Ability Tiles · Any cards · Additional card · Construction discount · Change of colors · 2 nd case: | p.6 | 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 |
| #5 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Components · Object of the Game · Number x squares | p.1 | 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 |
| #6 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | B) Construct facade · 1. Pick a facade tile · Exception: · 2. Placing a Facade Tile (Construction Rules) | p.4 | 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 |
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 6 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 Copenhagen — Rulebook (corpus doc 1300) | Game Set-up · Red facade card | p.2 | #2 | 0.048652 (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 Copenhagen — Rulebook (corpus doc 1300) | B) Construct facade · 1. Pick a facade tile · Exception: · 2. Placing a Facade Tile (Construction Rules) | p.4 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Ability Tiles · Any cards · Additional card · Construction discount · Change of colors · 2 nd case: | p.6 | #4 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Components · Object of the Game · Number x squares | p.1 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Coat of arms actions · 3. Score points · Row: · Column: · Ending the Game | p.5 | #3 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Start of the game · A) Take cards · Maximum Hand Size · End of Game card | p.3 | #1 | 0.048916 (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 Copenhagen — Rulebook (corpus doc 1300) | Game Set-up · Red facade card | p.2 | no quote on the wire |
| [2] | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Start of the game · A) Take cards · Maximum Hand Size · End of Game card | p.3 | no quote on the wire |
| [3] | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | B) Construct facade · 1. Pick a facade tile · Exception: · 2. Placing a Facade Tile (Construction Rules) | p.4 | no quote on the wire |
| [4] | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Ability Tiles · Any cards · Additional card · Construction discount · Change of colors · 2 nd case: | p.6 | no quote on the wire |
| [5] | RULEBOOK Copenhagen — Rulebook (corpus doc 1300) | Coat of arms actions · 3. Score points · Row: · Column: · Ending the Game | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 81 ms · first delta 1086 ms · total 62231 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 56131 ms · retrieval 81 ms · ask 6016 ms · gateway work 6100 ms · total 62231 ms
- tokens in (the prompt the answerer read)
- 3015
- tokens out (what the answerer generated)
- 990
- tok/sec
- 201.1 tok/sec — 990 output tokens in 4.922 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 23s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 4s 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 1230), 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.