You asked
How do I play?
Answered counted as answeredAsked with: Downforcebg-215311-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 198 ms · ask 6338 ms · total 6538 ms
- single-flight (PR-5)
- queued 0 ms · generation 6538 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 7, "score": 0.04918, "snippet": "For a simpler game for younger players, make the following changes: Do not auction off the cars. Instead, randomly deal the Speed-8 cards (and their matching driver plaques) to each player so that everyone has the same number of cars. Any leftover cards remain out of play, and their corresponding ca", "headingPath": "Beginner's Game · Two Player Game · Long Distance Races · World Tour Game", "sharpsignalDocId": 558}, {"page": 4, "score": 0.048387, "snippet": "The player who controls the car on the space takes the first turn. During the race, each player will play one speed card from their hand and resolve it. Then the player to their left takes the next turn. Play continues until all the cars have finished the race or no more cards can be played. Each ca", "headingPath": "THE RACE · PLAYING SPEED CARDS: · WILDS:", "sharpsignalDocId": 558}, {"page": 3, "score": 0.046898, "snippet": "A game of Downforce has three parts: The Auction: The cars are auctioned off to the highest bidder. The Race: The cars race around the track. The Betting, which takes place during the race, when players bet on who the winning car is going to be. After the race is over, players add up all their money", "headingPath": "PLAYING THE GAME · THE AUCTION", "sharpsignalDocId": 558}, {"page": 4, "score": 0.045928, "snippet": "Cars move forward on the track to the next adjacent space, either straight or diagonally. A car may not move sideways or backwards. Cars may not move through other cars, though they may move diagonally between two cars that are adjacent diagonally. A space is considered 'forward' if the front end of", "headingPath": "MOVING CARS ON THE TRACK:", "sharpsignalDocId": 558}, {"page": 2, "score": 0.03125, "snippet": "1 3 5 4 6 2 1 Double-Sided Game Board River Station and Marina Bay tracks 6 Race Car Pawns 42 Regular Speed Cards COMPONENTS SET-UP 6 Speed-8 Speed Cards 6 Power Cards 6 Driver Plaques 1 Pad of Score Sheets Place the game board in the center of the table on either side. (Each side has a unique track", "headingPath": "", "sharpsignalDocId": 558}, {"page": 6, "score": 0.030769, "snippet": "After all cars have finished the race, players mark on their score sheets how much money they earn for each of their cars based on how they finished. They then circle any money they won through betting. This money is added up, and the initial bid money is subtracted from it. The money remaining is t", "headingPath": "WINNING THE GAME", "sharpsignalDocId": 558}, {"page": 6, "score": 0.030159, "snippet": "Each player has a power card that can affect movement or one of the other rules. When a power contradicts a rule, the power takes precedent over the rule. Example: If you control the red car and play this card, you can move the red car 7 spaces instead of 6. Note: This power does not work if a wild ", "headingPath": "POWER CARDS: · AGGRESSIVE · CUNNING · DETERMINED · STRATEGIC · TRICKY · …", "sharpsignalDocId": 558}, {"page": 5, "score": 0.029851, "snippet": "Yellow moves 5 spaces. It's only option for its first move is to move to space 1 , which works because the front end lies ahead of the front end of the space where it started. Likewise, the rest of the path shows the only possible movement options for yellow . Green may not move into space 2 or spac", "headingPath": "MOVING CARS ON THE TRACK: · THE BETTING", "sharpsignalDocId": 558}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "PLAYING THE GAME · THE AUCTION", "sharpsignalDocId": 558}, {"page": 4, "quote": null, "headingPath": "THE RACE · PLAYING SPEED CARDS: · WILDS:", "sharpsignalDocId": 558}, {"page": 4, "quote": null, "headingPath": "MOVING CARS ON THE TRACK:", "sharpsignalDocId": 558}, {"page": 6, "quote": null, "headingPath": "POWER CARDS: · AGGRESSIVE · CUNNING · DETERMINED · STRATEGIC · TRICKY · …", "sharpsignalDocId": 558}, {"page": 6, "quote": null, "headingPath": "WINNING THE GAME", "sharpsignalDocId": 558}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 558 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 558 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 0.90868 of 3088 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 26, 2026 03:41 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 Downforce — Rulebook (corpus doc 558) | Beginner's Game · Two Player Game · Long Distance Races · World Tour Game | p.7 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Downforce — Rulebook (corpus doc 558) | THE RACE · PLAYING SPEED CARDS: · WILDS: | p.4 | 0.048387 (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 Downforce — Rulebook (corpus doc 558) | PLAYING THE GAME · THE AUCTION | p.3 | 0.046898 (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 Downforce — Rulebook (corpus doc 558) | MOVING CARS ON THE TRACK: | 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 Downforce — Rulebook (corpus doc 558) | p.2 | 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 | |
| #6 | RULEBOOK Downforce — Rulebook (corpus doc 558) | WINNING THE GAME | p.6 | 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 |
| #7 | RULEBOOK Downforce — Rulebook (corpus doc 558) | POWER CARDS: · AGGRESSIVE · CUNNING · DETERMINED · STRATEGIC · TRICKY · … | p.6 | 0.030159 (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 Downforce — Rulebook (corpus doc 558) | MOVING CARS ON THE TRACK: · THE BETTING | 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 Downforce — Rulebook (corpus doc 558) | THE RACE · PLAYING SPEED CARDS: · WILDS: | p.4 | #2 | 0.048387 (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 Downforce — Rulebook (corpus doc 558) | MOVING CARS ON THE TRACK: | p.4 | #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 Downforce — Rulebook (corpus doc 558) | POWER CARDS: · AGGRESSIVE · CUNNING · DETERMINED · STRATEGIC · TRICKY · … | p.6 | #7 | 0.030159 (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 Downforce — Rulebook (corpus doc 558) | p.2 | #5 | 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 | |
| #5 | RULEBOOK Downforce — Rulebook (corpus doc 558) | AUCTION EXAMPLE | p.3 | #11 | 0.014493 (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 Downforce — Rulebook (corpus doc 558) | WINNING THE GAME | p.6 | #6 | 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 |
| #7 | RULEBOOK Downforce — Rulebook (corpus doc 558) | PLAYING THE GAME · THE AUCTION | p.3 | #3 | 0.046898 (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 Downforce — Rulebook (corpus doc 558) | Beginner's Game · Two Player Game · Long Distance Races · World Tour Game | p.7 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 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 Downforce — Rulebook (corpus doc 558) | PLAYING THE GAME · THE AUCTION | p.3 | no quote on the wire |
| [2] | RULEBOOK Downforce — Rulebook (corpus doc 558) | THE RACE · PLAYING SPEED CARDS: · WILDS: | p.4 | no quote on the wire |
| [3] | RULEBOOK Downforce — Rulebook (corpus doc 558) | MOVING CARS ON THE TRACK: | p.4 | no quote on the wire |
| [4] | RULEBOOK Downforce — Rulebook (corpus doc 558) | POWER CARDS: · AGGRESSIVE · CUNNING · DETERMINED · STRATEGIC · TRICKY · … | p.6 | no quote on the wire |
| [5] | RULEBOOK Downforce — Rulebook (corpus doc 558) | WINNING THE GAME | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 198 ms · first delta 1742 ms · total 6538 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 198 ms · ask 6338 ms · gateway work 6538 ms · total 6538 ms
- tokens in (the prompt the answerer read)
- 2759
- tokens out (what the answerer generated)
- 961
- tok/sec
- 202.1 tok/sec — 961 output tokens in 4.755 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 9s 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 490), 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.