You asked
How do you score the game
Answered counted as answeredAsked with: Orleansbg-164928-en-1e
To score the game, follow these steps: 1. Before proceeding with scoring, the player who has built the most Trading Stations receives the remaining Citizen Tile (if there is a tie, no player receives the tile) [1]. 2. Determine final scores by awarding victory points (VP) for Coins at a rate of 1 VP per coin [1]. 3. Your Development Status affects the victory point value of your Citizen Tiles and Trading Stations at the end of the game [2].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 271 ms · ask 7634 ms · total 7916 ms
- single-flight (PR-5)
- queued 0 ms · generation 7916 ms
- retrieval refs (raw)
- [{"page": 19, "score": 0.04918, "snippet": "The game ends after 18 rounds. Before you proceed with the scoring, the player who has built the most Trading Stations receives the remaining Citizen Tile. If there is a tie, no player receives the tile. Then determine your fi nal scores. You score victory points (VP) for: Coins: 1 VP per coin", "headingPath": "End of the Game and Scoring", "sharpsignalDocId": 89}, {"page": 17, "score": 0.032258, "snippet": "Take a Scholar Tile from the game board and put it into your Followers Bag. Then advance one space on the Scholars Track and receive the depicted number of Development Points. For each Development Point you receive during the game, advance your marker one space on the Development Track.", "headingPath": "University", "sharpsignalDocId": 89}, {"page": 16, "score": 0.031746, "snippet": "Take a Farmer Tile from the Farm House on the game board and put the Farmer into your bag. Then advance your marker one space on the Farmers Track and receive the depicted good . The position of your marker on this track also plays a role during Phase 2: 'Census'.", "headingPath": "Farm House", "sharpsignalDocId": 89}, {"page": 14, "score": 0.03125, "snippet": "Hour Glass: The Start Player draws the topmost Hour Glass Tile from the stack and turns it face up. The Hour Glass Tiles determine the length of the game. The game ends at the end of the round in which the 18th and last tile is drawn. Each Hour Glass Tile also introduces an event that will affect th", "headingPath": "Phase 1", "sharpsignalDocId": 89}, {"page": 14, "score": 0.030769, "snippet": "You are trying to achieve dominance in various areas in medieval France. You will get goods, coins, and victory points via production, trade, development, and by committing to the common good.", "headingPath": "Goal of the Game", "sharpsignalDocId": 89}, {"page": 17, "score": 0.030303, "snippet": "Take a Knight Tile from the game board and put it into your Followers Bag. Then advance one space on the Knights Track. The Knights Track indicates how many Followers you may draw from your bag and place on your Market in Phase 3. At the beginning of the game, you may draw 4 Followers each round. Yo", "headingPath": "Castle", "sharpsignalDocId": 89}, {"page": 14, "score": 0.029851, "snippet": "Census: Determine who has the most and who has the least Farmers. The player whose marker is furthest ahead on the Farmers Track receives 1 coin from the supply. If there is a tie, no player receives the coin. The player whose marker is furthest behind on the track must pay 1 coin to the supply. If ", "headingPath": "Phase 2", "sharpsignalDocId": 89}, {"page": 14, "score": 0.029412, "snippet": "The youngest player receives the Start Player Token. The game is played over 18 rounds, with each round being comprised of 7 phases.", "headingPath": "Course of Play", "sharpsignalDocId": 89}]
- citations (raw)
- [{"page": 19, "quote": null, "headingPath": "End of the Game and Scoring", "sharpsignalDocId": 89}, {"page": 19, "quote": null, "headingPath": "The Development Track", "sharpsignalDocId": 89}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 89 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 89 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)
- debug row retained until
- Nov 5, 2026 14:23
retrieval — what the search arm returned
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 Orleans — Rulebook (corpus doc 89) | End of the Game and Scoring | p.19 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 294 |
| #2 | RULEBOOK Orleans — Rulebook (corpus doc 89) | University | p.17 | 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)) | 287 |
| #3 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Farm House | p.16 | 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)) | 264 |
| #4 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Phase 1 | 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 |
| #5 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Goal of the Game | p.14 | 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)) | 192 |
| #6 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Castle | p.17 | 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 |
| #7 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Phase 2 | p.14 | 0.029851 (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 Orleans — Rulebook (corpus doc 89) | Course of Play | p.14 | 0.029412 (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)) | 132 |
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 Orleans — Rulebook (corpus doc 89) | End of the Game and Scoring | p.19 | no quote on the wire |
| [2] | RULEBOOK Orleans — Rulebook (corpus doc 89) | The Development Track | p.19 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 271 ms · first delta 7102 ms · total 7916 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 271 ms · ask 7634 ms · gateway work 7916 ms · total 7916 ms
- tokens in (the prompt the answerer read)
- 1316
- tokens out (what the answerer generated)
- 102
- tok/sec
- 136.7 tok/sec — 102 output tokens in 0.746 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 58s ago)
- 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 20), 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.