You asked
How do I play?
Answered counted as answeredAsked with: Genoabg-1345-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 137 ms · ask 2980 ms · total 3119 ms
- single-flight (PR-5)
- queued 0 ms · generation 3119 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.046751, "snippet": "Place the game board in the middle of the ta b l e. Place the parts shown below on the 10 unnamed buildings on the left and rights sides of the board as shown in the figure below : 8 sets of 5 wa re marke rs 7 special cards (the '1:1 T ra d e ' c a rd s ) 14 - 35 owner marke rs (each player chooses ", "headingPath": "PREPARATION · Each player ta kes: · The youngest player ta ke s · place on unnamed buildings: · per player: · the youngest player takes:", "sharpsignalDocId": 1026}, {"page": 8, "score": 0.046642, "snippet": "When a player takes the action for the Palace, he takes 1 of this special card from the supply. When a player plays the card (by placing it back on the supply stack), he may take the action of any building that he has an owner marker on (see 'The owner markers' below) . The timing of playing this ca", "headingPath": "1 Building action · Note:", "sharpsignalDocId": 1026}, {"page": 6, "score": 0.0463, "snippet": "The starting player begins; players take turns in clockwise order around the board. A player, on his turn, is called the tower player. When a player finishes his turn, the next player, in clockwise order, takes his turn, and so on. When every player has taken a turn in a round, the round ends. As th", "headingPath": "PLAYING THE GAME · Placing the trader tower", "sharpsignalDocId": 1026}, {"page": 4, "score": 0.045928, "snippet": "The number of rounds in the game varies depending on the number of players: with 2 players, the game lasts at most 12 rounds, with 3 players, the game lasts at most 10 rounds, with 4 players, at most 8 rounds, and with 5 players, at most 7 rounds. The Market rule (moving the round marker when the fi", "headingPath": "GAME END", "sharpsignalDocId": 1026}, {"page": 2, "score": 0.045635, "snippet": "The players take the roles of traders in Genoa. They fulfill orders, deliver messages, and take ownership of important buildings in the city. Of course, this is not possible without the help of the other traders. And that can cost money... and other valuable goods! When reading the rules for the fir", "headingPath": "THE GAME OF TRADING, WARES, & NEGOTIATION", "sharpsignalDocId": 1026}, {"page": 4, "score": 0.044118, "snippet": "Should a chosen building already have an opponent's owner marker on it, the player may re m ove it, but at a cost. To re m ove the opponent's ow n e r m a r ke r , the player must sacrifice one of his own owner marke rs from his p l ay area and place both his and the opponent's back in the common s ", "headingPath": "the youngest player takes:", "sharpsignalDocId": 1026}, {"page": 5, "score": 0.043549, "snippet": "After the tower player declares his turn has ended, players may place owner markers on buildings that are orthogonally adjacent to any street spaces the tower moved to or through this turn. The tower player starts and then the others follow in clockwise order once around the table. On a player's tur", "headingPath": "How are they placed?", "sharpsignalDocId": 1026}, {"page": 7, "score": 0.03125, "snippet": "When the tower is in a building without one of the players having paid the tower player to move it there (e.g. the first tower field), the tower player asks if anyone is interested in taking the action available in the tower building (the building where the tower now stands). When at least one oppon", "headingPath": "§ 1.1 Tower building", "sharpsignalDocId": 1026}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "PLAYING THE GAME · Placing the trader tower", "sharpsignalDocId": 1026}, {"page": 5, "quote": null, "headingPath": "How are they placed?", "sharpsignalDocId": 1026}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1026 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1026 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 0.92986 of 941 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 15:11 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 Genoa — Rulebook (corpus doc 1026) | PREPARATION · Each player ta kes: · The youngest player ta ke s · place on unnamed buildings: · per player: · the youngest player takes: | p.3 | 0.046751 (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 Genoa — Rulebook (corpus doc 1026) | 1 Building action · Note: | p.8 | 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 Genoa — Rulebook (corpus doc 1026) | PLAYING THE GAME · Placing the trader tower | p.6 | 0.0463 (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 Genoa — Rulebook (corpus doc 1026) | GAME END | p.4 | 0.045928 (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 Genoa — Rulebook (corpus doc 1026) | THE GAME OF TRADING, WARES, & NEGOTIATION | p.2 | 0.045635 (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 Genoa — Rulebook (corpus doc 1026) | the youngest player takes: | p.4 | 0.044118 (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 Genoa — Rulebook (corpus doc 1026) | How are they placed? | p.5 | 0.043549 (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 Genoa — Rulebook (corpus doc 1026) | § 1.1 Tower building | p.7 | 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 23 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 Genoa — Rulebook (corpus doc 1026) | How are they placed? | p.5 | #7 | 0.043549 (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 Genoa — Rulebook (corpus doc 1026) | Example of the use of special cards: · What are they good for? | p.5 | #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 |
| #3 | RULEBOOK Genoa — Rulebook (corpus doc 1026) | 1 further action · Note: · 1 of any ware · 1:1 trade · examples: | p.8 | #9 | 0.030282 (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 Genoa — Rulebook (corpus doc 1026) | THE GAME OF TRADING, WARES, & NEGOTIATION | p.2 | #5 | 0.045635 (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 Genoa — Rulebook (corpus doc 1026) | § 1.1 Tower building | p.7 | #8 | 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 |
| #6 | RULEBOOK Genoa — Rulebook (corpus doc 1026) | the youngest player takes: | p.4 | #6 | 0.044118 (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 Genoa — Rulebook (corpus doc 1026) | 1 Building action · Note: | p.8 | #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 Genoa — Rulebook (corpus doc 1026) | PLAYING THE GAME · Placing the trader tower | p.6 | #3 | 0.0463 (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 Genoa — Rulebook (corpus doc 1026) | PLAYING THE GAME · Placing the trader tower | p.6 | no quote on the wire |
| [2] | RULEBOOK Genoa — Rulebook (corpus doc 1026) | How are they placed? | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 137 ms · first delta 1682 ms · total 3119 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 137 ms · ask 2980 ms · gateway work 3119 ms · total 3119 ms
- tokens in (the prompt the answerer read)
- 2880
- tokens out (what the answerer generated)
- 277
- tok/sec
- 201.6 tok/sec — 277 output tokens in 1.374 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 22s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, 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 956), 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.