You asked
How do I set up the game?
Answered counted as answeredAsked with: Marvel Champions: The Card Gamebg-285774-en-1e
🔧 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 269 ms · ask 20155 ms · total 1231583 ms
- single-flight (PR-5)
- queued 1211150 ms · generation 20433 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 40, "score": 0.046751, "snippet": "A card with the setup keyword begins the game in play. Cards with the setup keyword are put into play during the 'Put Setup Cards Into Play' step of setup. See also : Keywords, Reminder Text, Appendix II: Setup ' Setup ' is a type of triggered ability that is resolved during setup. Setup abilities a", "headingPath": "SETUP (KEYWORD) · SETUP (TRIGGERED ABILITY) · SKIRMISH MODE · SPECIAL · STALWART · SHUFFLE · …", "sharpsignalDocId": 263}, {"page": 51, "score": 0.046676, "snippet": "To set up a game, perform the following steps in order: Select Identities. Each player selects one identity, placing their alter-ego side face up. Set Hit Points. Each player sets their hit point dial equal to the starting hit points of their character, found at the bottom of their identity card. Se", "headingPath": "APPENDIX II: SETUP", "sharpsignalDocId": 263}, {"page": 19, "score": 0.043596, "snippet": "When instructed to find a card, a player searches each game area where that card could be found (play area, set-aside area, player deck, discard pile, encounter deck, etc.) . Players should not unnecessarily search game areas if they know where the card they are looking for can be found. All game ar", "headingPath": "FIND · FIRST PLAYER", "sharpsignalDocId": 263}, {"page": 4, "score": 0.042263, "snippet": "This document is intended as the definitive source for rules information, but does not teach players how to play the game. Players should first read the Learn to Play book in its entirety and use this Rules Reference as needed while playing the game. The majority of this book consists of a glossary,", "headingPath": "OVERVIEW · THE GOLDEN RULES · THE GRIM RULE · COMPONENT LIMITATIONS · ROUND OVERVIEW", "sharpsignalDocId": 263}, {"page": 24, "score": 0.031746, "snippet": "When a player wishes to play a card or initiate a triggered ability, that player first declares their intent. Then, the player checks the following conditions in order: If playing a card, the player places that card faceup on the table in front of them. (This card is not in play.) Check play restric", "headingPath": "INITIATING ABILITIES", "sharpsignalDocId": 263}, {"page": 35, "score": 0.030303, "snippet": "Use their alter-ego's basic recovery (if in alter-ego form) or their hero's basic attack or thwart power (if in hero form) . Use an ally card they control in play to attack an enemy or thwart a scheme. Trigger an ' Action ' ability on: A card in play they control. An encounter card in play. Any card", "headingPath": "PLAYER TURN · PLAYER'S PLAY AREA · PLAYING CARDS", "sharpsignalDocId": 263}, {"page": 38, "score": 0.029851, "snippet": "During step four of the villain phase, each player (in player order) reveals and resolves all facedown encounter cards that have been dealt to them, one card at a time in the order in which they were dealt. To reveal an encounter card, follow these steps: Turn the encounter card faceup. If the encou", "headingPath": "REVEAL", "sharpsignalDocId": 263}, {"page": 4, "score": 0.029644, "snippet": "An ability is game text on a card that explains what the card does (or can do) . Several examples can be seen in Appendix III of this Rules Reference. Card abilities only interact with cards that are in play, unless the ability specifically refers to an out-of-play area or element. Card abilities on", "headingPath": "ABILITY", "sharpsignalDocId": 263}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 51, "quote": null, "headingPath": "APPENDIX II: SETUP", "sharpsignalDocId": 263}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 263 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 263 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 6, 2026 14:29
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. How much wider that pool was is set gateway-side and is NOT REPORTED for this ruling, and neither are the answerer's final rows — so rulesage has nothing of its own to show beside these.
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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | SETUP (KEYWORD) · SETUP (TRIGGERED ABILITY) · SKIRMISH MODE · SPECIAL · STALWART · SHUFFLE · … | p.40 | 0.046751 (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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | APPENDIX II: SETUP | p.51 | 0.046676 (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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | FIND · FIRST PLAYER | p.19 | 0.043596 (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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | OVERVIEW · THE GOLDEN RULES · THE GRIM RULE · COMPONENT LIMITATIONS · ROUND OVERVIEW | p.4 | 0.042263 (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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | INITIATING ABILITIES | p.24 | 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 |
| #6 | RULEBOOK Marvel Champions: The Card Game — Rulebook (corpus doc 263) | PLAYER TURN · PLAYER'S PLAY AREA · PLAYING CARDS | p.35 | 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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | REVEAL | p.38 | 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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | ABILITY | p.4 | 0.029644 (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.
the passages the answerer read: NOT RECORDED for this ruling. Any of three things leaves this empty, and they are all different from the answerer having had nothing to read: this ask may never have reached a gateway at all; a multi-book ask keeps each book's own context on that book's own page rather than here; or the gateway build that answered may simply not report it. What this NEVER means is that the answerer read nothing — an answer was composed from passages either way, and their absence here is a gap in what we were told, not in what it read.
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 Marvel Champions: The Card Game — Rulebook (corpus doc 263) | APPENDIX II: SETUP | p.51 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 269 ms · first delta 16385 ms · total 1231583 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1211150 ms · retrieval 269 ms · ask 20155 ms · gateway work 20433 ms · total 1231583 ms
- tokens in (the prompt the answerer read)
- 4172
- tokens out (what the answerer generated)
- 546
- tok/sec
- 136.5 tok/sec — 546 output tokens in 4.001 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 191), 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.