You asked
How do I play?
Answered counted as answeredAsked with: Parisbg-282954-en-1e
That settles it — whose turn was it?
🔧 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 93 ms · ask 4284 ms · total 22927 ms
- single-flight (PR-5)
- queued 18548 ms · generation 4379 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048916, "snippet": "In 'Paris', players take on the roles of real estate investors trying to purchase the most exquisite buildings in late 19th century Paris. Players score Victory Points (VP) by purchasing buildings and obtaining Bonus Tiles. The game is played over a variable number of rounds. Once the end of the gam", "headingPath": "GAME OVERVIEW · GAMEPLAY · 1. Place a Building on the Board · 2. Perform an action · 1. Place a Key", "sharpsignalDocId": 1217}, {"page": 2, "score": 0.048652, "snippet": "Note: This is the basic setup for a game of 'Paris'. If you wish to play with a more randomized setup of the game, please check the 'Variant Setup' chapter on the next page. Assemble the Board as shown here. If you prefer to play without the 3D Arc, you can flip the central Tile to the side where th", "headingPath": "GAME SETUP", "sharpsignalDocId": 1217}, {"page": 7, "score": 0.046642, "snippet": "Example: Charlotte may collect a Bonus Tile as she purchased a value 2 Building. She moves her Bonus Meeple onto Bonus Tile number 18 and places it behind her Screen. A few turns later, when she has Keys on three different value 4 Buildings, she decides to activate the Bonus Tile, which immediately ", "headingPath": "Bonus Tiles · 3. Take an End Game Tile · END OF THE GAME", "sharpsignalDocId": 1217}, {"page": 3, "score": 0.045928, "snippet": "Once you have played a few games of Paris, you may spice things up by randomizing the Setup: E Instead of placing Resource Tokens and Prestige Tokens according to the basic setup scheme, first place the 6 Gold Resource Tokens next to the value 8 Building spaces. Then mix the 12 remaining Resource To", "headingPath": "Variant Setup", "sharpsignalDocId": 1217}, {"page": 8, "score": 0.044796, "snippet": "17: You may take any Bonus Tile off the Board and place it behind your Player Screen. Do not move your Bonus Meeple from its current location. 19: This Tile counts as 2 Prestige Tokens of your choice. You may use them (one or both) to earn VP when you purchase a Landmark or sell them (one or both) f", "headingPath": "APPENDIX: BONUS TILES", "sharpsignalDocId": 1217}, {"page": 4, "score": 0.031746, "snippet": "Move one of your Keys on the Game Board to an unoccupied Building or Landmark and pay the applicable costs (Francs and Resources, see 'Costs' on the next page). You are then considered the owner of this Building or Landmark, and you may take its available benefits (Resource Token, Bonus Tile and/or ", "headingPath": "2. Move a Key", "sharpsignalDocId": 1217}, {"page": 6, "score": 0.03125, "snippet": "Bonus Tiles can be earned by acquiring Buildings of values 1, 2, or 3. To obtain a Bonus Tile, move your Bonus Meeple forward as many spaces as you wish along the Bonus Track, onto an available Bonus Tile. Then take the Tile and place it behind your Player Screen. If you land on a stack of Tiles, yo", "headingPath": "Bonus Tiles", "sharpsignalDocId": 1217}, {"page": 5, "score": 0.029851, "snippet": "VP Tiles As soon as a District has a total of 4 Keys on Buildings and Landmarks (not in- cluding the Bank), the active player may immediately place one of the available VP Tiles on an available VP Tile spot in a District of their choice. These Tiles will offer bonus VP at the end of the game to the ", "headingPath": "", "sharpsignalDocId": 1217}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "GAME OVERVIEW · GAMEPLAY · 1. Place a Building on the Board · 2. Perform an action · 1. Place a Key", "sharpsignalDocId": 1217}, {"page": 4, "quote": null, "headingPath": "2. Move a Key", "sharpsignalDocId": 1217}, {"page": 7, "quote": null, "headingPath": "Bonus Tiles · 3. Take an End Game Tile · END OF THE GAME", "sharpsignalDocId": 1217}, {"page": 6, "quote": null, "headingPath": "Bonus Tiles", "sharpsignalDocId": 1217}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1217 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1217 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 0.92509 of 1989 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 03:09 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 Paris — Rulebook (corpus doc 1217) | GAME OVERVIEW · GAMEPLAY · 1. Place a Building on the Board · 2. Perform an action · 1. Place a Key | p.4 | 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 Paris — Rulebook (corpus doc 1217) | GAME SETUP | 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 Paris — Rulebook (corpus doc 1217) | Bonus Tiles · 3. Take an End Game Tile · END OF THE GAME | p.7 | 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 |
| #4 | RULEBOOK Paris — Rulebook (corpus doc 1217) | Variant Setup | p.3 | 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 Paris — Rulebook (corpus doc 1217) | APPENDIX: BONUS TILES | p.8 | 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 |
| #6 | RULEBOOK Paris — Rulebook (corpus doc 1217) | 2. Move a Key | p.4 | 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 |
| #7 | RULEBOOK Paris — Rulebook (corpus doc 1217) | Bonus Tiles | 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 |
| #8 | RULEBOOK Paris — Rulebook (corpus doc 1217) | p.5 | 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 |
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 16 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 Paris — Rulebook (corpus doc 1217) | GAME SETUP | 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 Paris — Rulebook (corpus doc 1217) | Variant Setup | p.3 | #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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Paris — Rulebook (corpus doc 1217) | Bonus Tiles | p.6 | #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 |
| #4 | RULEBOOK Paris — Rulebook (corpus doc 1217) | Bonus Tiles · 3. Take an End Game Tile · END OF THE GAME | p.7 | #3 | 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 |
| #5 | RULEBOOK Paris — Rulebook (corpus doc 1217) | End Scoring | p.7 | #13 | 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 |
| #6 | RULEBOOK Paris — Rulebook (corpus doc 1217) | APPENDIX: BONUS TILES | p.8 | #5 | 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 |
| #7 | RULEBOOK Paris — Rulebook (corpus doc 1217) | 2. Move a Key | p.4 | #6 | 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 |
| #8 | RULEBOOK Paris — Rulebook (corpus doc 1217) | GAME OVERVIEW · GAMEPLAY · 1. Place a Building on the Board · 2. Perform an action · 1. Place a Key | p.4 | #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 Paris — Rulebook (corpus doc 1217) | GAME OVERVIEW · GAMEPLAY · 1. Place a Building on the Board · 2. Perform an action · 1. Place a Key | p.4 | no quote on the wire |
| [2] | RULEBOOK Paris — Rulebook (corpus doc 1217) | 2. Move a Key | p.4 | no quote on the wire |
| [3] | RULEBOOK Paris — Rulebook (corpus doc 1217) | Bonus Tiles · 3. Take an End Game Tile · END OF THE GAME | p.7 | no quote on the wire |
| [4] | RULEBOOK Paris — Rulebook (corpus doc 1217) | Bonus Tiles | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 93 ms · first delta 1447 ms · total 22927 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 18548 ms · retrieval 93 ms · ask 4284 ms · gateway work 4379 ms · total 22927 ms
- tokens in (the prompt the answerer read)
- 3377
- tokens out (what the answerer generated)
- 579
- tok/sec
- 201.0 tok/sec — 579 output tokens in 2.881 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 21s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 0s 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 1147), 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.