You asked
How do I play?
Answered counted as answeredAsked with: Legendary: A Marvel Deck Building Game – Villainsbg-156689-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 129 ms · ask 11458 ms · total 102439 ms
- single-flight (PR-5)
- queued 90850 ms · generation 11589 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.047131, "snippet": "For your first game, follow the setup rules on the following page, using the specific card stacks listed there instead of choosing card stacks at random. After your first game, every game of Legendary ™ uses different Allies, Adversaries, Commanders and Plots, so there are always new challenges to m", "headingPath": "Your First Game", "sharpsignalDocId": 1098}, {"page": 11, "score": 0.046964, "snippet": "Here’s what you do: • Play the cards in your hand in any order, one at a time. • Each time you play a card, do what that card says. •You also get any Recruit Points listed in the Recruit icon on the card. •You also get any Attack listed in the Attack icon on the card. • Some cards have a number like", "headingPath": "", "sharpsignalDocId": 1098}, {"page": 2, "score": 0.045774, "snippet": "Players must work together to defeat the game's Commander four times. If they do, then the Commander is beaten once and for all, and all the players win the game for the forces of Evil! In addition, defeating Adversaries and kidnapping Bystanders earns each player Victory Points. If the players win ", "headingPath": "How to Win · How the Game's Commander Wins", "sharpsignalDocId": 1098}, {"page": 19, "score": 0.045476, "snippet": "returning them to the Recruit Stack does count, since you are playing those cards. Bindings and Wounds don't count towards this, since you don't 'play' them, you just use their Betrayal or Healing abilities from your hand. The best way to use Eight Arms is to play cards that let you draw extra cards", "headingPath": "Specific Card Clarifications", "sharpsignalDocId": 1098}, {"page": 8, "score": 0.045335, "snippet": "• Shuffle the Ally Deck. Put it face-down on the Allies space. Flip 5 cards from the Ally Deck faceup into the 5 Ally Spaces in the Lair. • Each player shuffles their own personal deck and draws a hand of 6 cards from it. • Choose a player to go first. Players take turns in clockwise order. On Your ", "headingPath": "", "sharpsignalDocId": 1098}, {"page": 13, "score": 0.044002, "snippet": "You can use Attack to fight any number of Adversaries in the city, one at a time. It doesn't matter which city space holds the Adversary. To fight an Adversary, do these steps in order: Spend Attack Points equal to that Adversary's Attack to defeat it. Put the defeated Adversary and any Bystanders i", "headingPath": "How to Fight an Adversary: · Your Victory Pile · Step 3) Discard Your Hand and Draw 6 New Cards", "sharpsignalDocId": 1098}, {"page": 20, "score": 0.042397, "snippet": "You can also play Legendary ™ with a single player, competing to defeat the Commander and get the highest score you can. Here are the adjustments you need: Ally Deck Use the cards for three Allies, 42 cards in total. Commander Ignore the Commander's", "headingPath": "Advanced Solo Mode · Solo Setup", "sharpsignalDocId": 1098}, {"page": 10, "score": 0.040523, "snippet": "If there are no Adversaries in the city, then the Bystander is guarded by the Commander. Make sure the Bystander pokes out a bit so players can see it. • Whenever an Adversary with one or more Bystanders moves to a new city space, those Bystanders all go with that Adversary. • It’s up to the Villain", "headingPath": "", "sharpsignalDocId": 1098}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 8, "quote": null, "headingPath": "To Add Bystanders: · Ally Deck · Starting the Game · On Your Turn: · Step 1) Play the Top Card of the Adversary Deck · If the Adversary Deck Card Is an Adversary: · …", "sharpsignalDocId": 1098}, {"page": 8, "quote": null, "headingPath": "", "sharpsignalDocId": 1098}, {"page": 11, "quote": null, "headingPath": "If the Adversary Deck Card Is a Command Strike: · Step 2) Play Cards from Your Hand, Using Them to Recruit and Fight", "sharpsignalDocId": 1098}, {"page": 11, "quote": null, "headingPath": "", "sharpsignalDocId": 1098}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1098 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1098 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 0.84906 of 1113 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 03:03 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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Your First Game | p.3 | 0.047131 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.11 | 0.046964 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | How to Win · How the Game's Commander Wins | p.2 | 0.045774 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Specific Card Clarifications | p.19 | 0.045476 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.8 | 0.045335 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | How to Fight an Adversary: · Your Victory Pile · Step 3) Discard Your Hand and Draw 6 New Cards | p.13 | 0.044002 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Advanced Solo Mode · Solo Setup | p.20 | 0.042397 (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)) | 249 |
| #8 | RULEBOOK Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.10 | 0.040523 (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 55 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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.8 | #5 | 0.045335 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Specific Card Clarifications | p.19 | #14 | 0.026334 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | If the Adversary Deck Card Is a Command Strike: · Step 2) Play Cards from Your Hand, Using Them to Recruit and Fight | p.11 | #9 | 0.030366 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Your First Game | p.3 | #1 | 0.047131 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | To Add Bystanders: · Ally Deck · Starting the Game · On Your Turn: · Step 1) Play the Top Card of the Adversary Deck · If the Adversary Deck Card Is an Adversary: · … | p.8 | #10 | 0.028778 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Advanced Solo Mode · Solo Setup | p.20 | #7 | 0.042397 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | Specific Card Clarifications | p.19 | #4 | 0.045476 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.11 | #2 | 0.046964 (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 Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | To Add Bystanders: · Ally Deck · Starting the Game · On Your Turn: · Step 1) Play the Top Card of the Adversary Deck · If the Adversary Deck Card Is an Adversary: · … | p.8 | no quote on the wire |
| [2] | RULEBOOK Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.8 | no quote on the wire | |
| [3] | RULEBOOK Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | If the Adversary Deck Card Is a Command Strike: · Step 2) Play Cards from Your Hand, Using Them to Recruit and Fight | p.11 | no quote on the wire |
| [4] | RULEBOOK Legendary: A Marvel Deck Building Game – Villains — Rulebook (corpus doc 1098) | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 129 ms · first delta 3522 ms · total 102439 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 90850 ms · retrieval 129 ms · ask 11458 ms · gateway work 11589 ms · total 102439 ms
- tokens in (the prompt the answerer read)
- 3135
- tokens out (what the answerer generated)
- 424
- tok/sec
- 53.2 tok/sec — 424 output tokens in 7.964 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 23s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 3s 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 1028), 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.