You asked
How do I play?
Answered counted as answeredAsked with: Qwixxbg-131260-en-1e
One rule clearer, zero feelings hurt.
🔧 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 132 ms · ask 5295 ms · total 5428 ms
- single-flight (PR-5)
- queued 0 ms · generation 5428 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 2, "score": 0.04866, "snippet": "Each player takes a sheet and a pen. Take turns to roll a die to decide which player will start the game. That player should roll once with all 6 dice , and then carry out the following 2 actions in this order : First action: Add up the pips on the 2 white dice and announce the total so that all the", "headingPath": "How to play", "sharpsignalDocId": 787}, {"page": 3, "score": 0.048652, "snippet": "If you want to cross out the number on the far right of a row on your sheet (red or yellow 12, green or blue 2), you first need to make sure you have already crossed out at least 5 numbers of a row, you also on that row. When you cross out the final number on the far right need to cross out the padl", "headingPath": "How to play · Finishing a row · End of the game", "sharpsignalDocId": 787}, {"page": 1, "score": 0.047875, "snippet": "2-5 A game by Steffen Benndorf Ages: 8+ Duration: approx. 15 min. The aim of the game is to cross out as many numbers as you can on the 4 rows of your sheet. Each row is in a different colour. The more numbers you manage to cross out on a given row, the more points you will score. The player with th", "headingPath": "Crossing out numbers · Example:", "sharpsignalDocId": 787}, {"page": 4, "score": 0.03125, "snippet": "In the area below the rows, you can see how many points you score depending on how many numbers you cross off on each row. You lose 5 points for each skipped turn. Use the boxes at the bottom of your sheet to enter your points for the four rows and then the number of minus points for your skipped tu", "headingPath": "Scoring", "sharpsignalDocId": 787}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "How to play", "sharpsignalDocId": 787}, {"page": 1, "quote": null, "headingPath": "Crossing out numbers · Example:", "sharpsignalDocId": 787}, {"page": 3, "quote": null, "headingPath": "How to play · Finishing a row · End of the game", "sharpsignalDocId": 787}, {"page": 4, "quote": null, "headingPath": "Scoring", "sharpsignalDocId": 787}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 787 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 787 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 0.90975 of 1662 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 23, 2026 17:01 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 Qwixx — Rulebook (corpus doc 787) | How to play | p.2 | 0.04866 (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 Qwixx — Rulebook (corpus doc 787) | How to play · Finishing a row · End of the game | p.3 | 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 Qwixx — Rulebook (corpus doc 787) | Crossing out numbers · Example: | p.1 | 0.047875 (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 Qwixx — Rulebook (corpus doc 787) | Scoring | p.4 | 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 4 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 Qwixx — Rulebook (corpus doc 787) | How to play | p.2 | #1 | 0.04866 (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 Qwixx — Rulebook (corpus doc 787) | Crossing out numbers · Example: | p.1 | #3 | 0.047875 (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 Qwixx — Rulebook (corpus doc 787) | Scoring | p.4 | #4 | 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 Qwixx — Rulebook (corpus doc 787) | How to play · Finishing a row · End of the game | p.3 | #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 |
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 Qwixx — Rulebook (corpus doc 787) | How to play | p.2 | no quote on the wire |
| [2] | RULEBOOK Qwixx — Rulebook (corpus doc 787) | Crossing out numbers · Example: | p.1 | no quote on the wire |
| [3] | RULEBOOK Qwixx — Rulebook (corpus doc 787) | How to play · Finishing a row · End of the game | p.3 | no quote on the wire |
| [4] | RULEBOOK Qwixx — Rulebook (corpus doc 787) | Scoring | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 132 ms · first delta 1465 ms · total 5428 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 132 ms · ask 5295 ms · gateway work 5428 ms · total 5428 ms
- tokens in (the prompt the answerer read)
- 1690
- tokens out (what the answerer generated)
- 524
- tok/sec
- 133.4 tok/sec — 524 output tokens in 3.929 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, checked 2s 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 722), 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.