You asked
How do I play?
Answered counted as answeredAsked with: Orleansbg-164928-en-1e
🔧 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 73 ms · ask 3941 ms · total 33962 ms
- single-flight (PR-5)
- queued 29947 ms · generation 4015 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 14, "score": 0.048916, "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}, {"page": 16, "score": 0.048131, "snippet": "Every Place represents a specifi c action. Your Player Board features the most common Places. As the game progresses, you can acquire additional Places (see below, 'Expanding the City'). You can play an action if it is activated (all spaces occupied). After you played an action, you remove the Chara", "headingPath": "The Actions/Places", "sharpsignalDocId": 89}, {"page": 16, "score": 0.046394, "snippet": "Take a Craftsman Tile from the game board and put it into your Followers Bag. Then advance one space on the Craftsmen Track and receive a Technology Tile . Put the Technology Tile next to your Player Board. You may only use it after you pass. Technology: You can place the Technology Tile on an Actio", "headingPath": "Craftsman", "sharpsignalDocId": 89}, {"page": 15, "score": 0.044796, "snippet": "Actions: You may carry out the actions of the Places you activated, i.e. where you placed a Follower (or Technology Tile) on every required space. Beginning with the Start Player and in clockwise order, each player may carry out 1 action or pass. If you pass, you cannot carry out any more actions du", "headingPath": "Phase 5", "sharpsignalDocId": 89}, {"page": 16, "score": 0.044136, "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": 17, "score": 0.031746, "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": 14, "score": 0.03125, "snippet": "Planning: Starting at the same time, all players plan their actions for the current round by placing Character Tiles from their Market to their Action Spaces. You may leave Character Tiles on your Market to use them in subsequent rounds. Once done, you point out the end of your planning; from this p", "headingPath": "Phase 4", "sharpsignalDocId": 89}, {"page": 17, "score": 0.029412, "snippet": "Take a Trader Tile from the game board and put it into your Followers Bag. Then advance one space on the Traders Track and expand your city with a Place Tile . Expanding the City: You may choose a Place Tile. There are two types of Place Tiles, I and II. When you advance on the Traders Track for the", "headingPath": "Trader", "sharpsignalDocId": 89}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 14, "quote": null, "headingPath": "Phase 4", "sharpsignalDocId": 89}, {"page": 15, "quote": null, "headingPath": "Phase 5", "sharpsignalDocId": 89}, {"page": 15, "quote": null, "headingPath": "Phase 4", "sharpsignalDocId": 89}, {"page": 16, "quote": null, "headingPath": "The Actions/Places", "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)
- answer fence
- passed — letter density 0.90995 of 955 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 13, 2026 13:31
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 Orleans — Rulebook (corpus doc 89) | Course of Play | p.14 | 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)) | 132 |
| #2 | RULEBOOK Orleans — Rulebook (corpus doc 89) | The Actions/Places | p.16 | 0.048131 (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 Orleans — Rulebook (corpus doc 89) | Craftsman | p.16 | 0.046394 (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 Orleans — Rulebook (corpus doc 89) | Phase 5 | p.15 | 0.044796 (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) | Farm House | p.16 | 0.044136 (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 |
| #6 | RULEBOOK Orleans — Rulebook (corpus doc 89) | University | p.17 | 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)) | 287 |
| #7 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Phase 4 | 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 |
| #8 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Trader | p.17 | 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)) | 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 80 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 Orleans — Rulebook (corpus doc 89) | The Actions/Places | p.16 | #2 | 0.048131 (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 Orleans — Rulebook (corpus doc 89) | Additional Place Tiles | p.21 | #10 | 0.028205 (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 Orleans — Rulebook (corpus doc 89) | Phase 4 | p.15 | #9 | 0.028439 (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 Orleans — Rulebook (corpus doc 89) | Ship | p.18 | #18 | 0.013699 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #5 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Running Out of Tiles: | p.21 | #11 | 0.027382 (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 Orleans — Rulebook (corpus doc 89) | Craftsman | p.16 | #3 | 0.046394 (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 Orleans — Rulebook (corpus doc 89) | Phase 4 | p.14 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Orleans — Rulebook (corpus doc 89) | Phase 5 | p.15 | #4 | 0.044796 (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 Orleans — Rulebook (corpus doc 89) | Phase 4 | p.14 | no quote on the wire |
| [2] | RULEBOOK Orleans — Rulebook (corpus doc 89) | Phase 5 | p.15 | no quote on the wire |
| [3] | RULEBOOK Orleans — Rulebook (corpus doc 89) | Phase 4 | p.15 | no quote on the wire |
| [4] | RULEBOOK Orleans — Rulebook (corpus doc 89) | The Actions/Places | p.16 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 73 ms · first delta 2048 ms · total 33962 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 29947 ms · retrieval 73 ms · ask 3941 ms · gateway work 4015 ms · total 33962 ms
- tokens in (the prompt the answerer read)
- 1449
- tokens out (what the answerer generated)
- 270
- tok/sec
- 139.4 tok/sec — 270 output tokens in 1.937 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 54s 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.