You asked
How should we prepare everything before the first turn?
Answered counted as answeredAsked with: Marvel Unitedbg-298047-en-1e
1. Shuffle the Villain's Threat cards and place 1 faceup on the slots at the bottom of each Location (covering the 'End of Turn' effect) [1]. 2. Add a Threat token to the slots next to those Threat cards [1]. 3. For any Threat cards containing Henchmen, place the indicated number of Health tokens on them [1]. 4. Place all remaining tokens into pools within reach of all players [1]. 5. Shuffle the Villain's Master Plan deck and place it facedown next to a random Location [1]. 6. Place the Villain's game piece in that Location [1]. 7. Each player chooses a Hero and places their game piece on the Location opposite of the Villain [1]. 8. Each player shuffles their corresponding Hero deck and places it facedown next to them [1]. 9. Each player draws 3 cards from the top of their deck into their hand [1].
🔧 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 210 ms · ask 7063 ms · total 7282 ms
- single-flight (PR-5)
- queued 0 ms · generation 7282 ms
- retrieval refs (raw)
- [{"page": 7, "score": 0.032787, "snippet": "Once the Master Plan card is fully resolved, it's time for the Heroes to act! Players collectively choose which Hero will start the game. Then, they will take their turns in clockwise order until the end of the game. During their turn, players follow these steps in order: DRAW A CARD PLAY A CARD RES", "headingPath": "Hero Turn · 1. DRAW A CARD · 2. PLAY A CARD · 3. RESOLVE ACTIONS", "sharpsignalDocId": 438}, {"page": 5, "score": 0.032258, "snippet": "Shuffle the Villain's Threat cards and place 1 faceup on the slots at the bottom of each Location (covering the 'End of Turn' effect), adding a Threat token to the slots next to them. Some Threat cards contain Henchmen, characters in the service of the Villain. Each of their cards indicate the numbe", "headingPath": "components · WINNING & LOSING · Villain Turn · MOVE VILLAIN", "sharpsignalDocId": 438}, {"page": 9, "score": 0.031746, "snippet": "Once the active player has completed all the steps of their turn, the next player in clockwise order becomes the active player, performing their turn. Each time 3 Hero cards have been added to the Storyline, a new Master Plan card is drawn from the deck, added to the end of the Storyline, and resolv", "headingPath": "Turn Sequence · UNDER PRESSURE · Rescue Civilians · Defeat Thugs", "sharpsignalDocId": 438}, {"page": 10, "score": 0.03125, "snippet": "Remember that Missions can be completed in any order. Once all slots of a Mission card are filled, the Mission is complete! Remove its card from the game, returning its tokens to the pool. If necessary, move the remaining Missions to the right so that the leftmost slots are left empty, unlocking the", "headingPath": "Completing Missions · KO", "sharpsignalDocId": 438}, {"page": 12, "score": 0.030769, "snippet": "1 Villain Turn, then 3 clockwise Hero Turns. Continue until first Mission is completed, then 1 Villain Turn every 2 Hero Turns. Add 1 Master Plan card to the Storyline. Resolve effects in order, from top to bottom. Move clockwise this number of Locations . Trigger final Location. effect on Resolve B", "headingPath": "RULES SUMMARY · VILLAIN TURN · HERO TURN · HERO DAMAGE · WINNING & LOSING", "sharpsignalDocId": 438}, {"page": 11, "score": 0.030303, "snippet": "Turns are resolved in the normal sequence, with you playing every Hero turn. Each turn, you may play the card of any Hero in your hand, even if it's the same Hero as the last card played. You always benefit normally from the symbols on the previously played card (but not from their Special Effect, e", "headingPath": "SPECIAL RULES:", "sharpsignalDocId": 438}, {"page": 9, "score": 0.029851, "snippet": "The Threat cards that the Villain places on the Locations, covering their End of Turn effect, may have all sorts of different effects, from constant effects at that Location or the entire game, to effects triggered by a Master Plan's BAM! ( see 'Activate BAM!' on page 6 ), to effects triggered by th", "headingPath": "Clear Threats", "sharpsignalDocId": 438}, {"page": 4, "score": 0.029412, "snippet": "Place the Mission Guide at the center of the table and the 3 Mission Cards on the slots at its bottom (in any order). 1 Choose a Villain to face and place its Villain Dashboard on the slot at the top of the Mission Guide (we recommend new players start with Red Skull). The Villain Dashboard indicate", "headingPath": "components", "sharpsignalDocId": 438}]
- citations (raw)
- [{"page": 5, "quote": null, "headingPath": "components · WINNING & LOSING · Villain Turn · MOVE VILLAIN", "sharpsignalDocId": 438}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 438 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 438 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 7, 2026 05:06
retrieval — what the search arm returned
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 United — Rulebook (corpus doc 438) | Hero Turn · 1. DRAW A CARD · 2. PLAY A CARD · 3. RESOLVE ACTIONS | p.7 | 0.032787 (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 United — Rulebook (corpus doc 438) | components · WINNING & LOSING · Villain Turn · MOVE VILLAIN | p.5 | 0.032258 (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 United — Rulebook (corpus doc 438) | Turn Sequence · UNDER PRESSURE · Rescue Civilians · Defeat Thugs | p.9 | 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 |
| #4 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | Completing Missions · KO | p.10 | 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 |
| #5 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | RULES SUMMARY · VILLAIN TURN · HERO TURN · HERO DAMAGE · WINNING & LOSING | p.12 | 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 |
| #6 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | SPECIAL RULES: | p.11 | 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 United — Rulebook (corpus doc 438) | Clear Threats | p.9 | 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 United — Rulebook (corpus doc 438) | components | p.4 | 0.029412 (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 |
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 United — Rulebook (corpus doc 438) | components · WINNING & LOSING · Villain Turn · MOVE VILLAIN | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 210 ms · first delta 4788 ms · total 7282 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 210 ms · ask 7063 ms · gateway work 7282 ms · total 7282 ms
- tokens in (the prompt the answerer read)
- 3505
- tokens out (what the answerer generated)
- 203
- tok/sec
- 83.3 tok/sec — 203 output tokens in 2.436 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 57s 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
- 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 369), 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.