You asked
How do I setup the game?
Answered counted as answeredAsked with: Marvel Unitedbg-298047-en-1e
That's the page. Back to the table.
🔧 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 107 ms · ask 3738 ms · total 3847 ms
- single-flight (PR-5)
- queued 0 ms · generation 3847 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 10, "score": 0.047379, "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": 11, "score": 0.046696, "snippet": "INVULNERABLE: If a Hero card states that the Hero cannot take any damage until their next turn, place an Invulnerable token on the Hero as a reminder, removing it at start of their next turn. CRISIS: Crisis tokens are used by certain Villains to represent their various nefarious influences. Simply u", "headingPath": "Additional Rules · S.H.I.E.L.D. Solo Mode · SPECIAL SETUP:", "sharpsignalDocId": 438}, {"page": 4, "score": 0.032787, "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}, {"page": 7, "score": 0.032258, "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": 0.031746, "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": 0.030769, "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": 2, "score": 0.029851, "snippet": "In Marvel United , 2 to 4 players take the role of Heroes working together to thwart the master plan of a Villain. You'll build a Storyline by drawing the Villain's cards and playing your own Hero cards to counter the Villain's schemes. Your cards allow you to move your Hero around, rescue Civilians", "headingPath": "overview", "sharpsignalDocId": 438}, {"page": 6, "score": 0.029412, "snippet": "Activate the BaM! effect detailed on the Villain Dashboard, as well as any BaM! effects shown on Threat cards. These effects complicate the Heroes' lives in all sorts of different ways, often dealing damage to them ( see Hero Damage on page 10 ). Add the indicated number of Thug and/or Civilian toke", "headingPath": "ACTIVATE BAM! · ADD THUGS/CIVILIANS · SPECIAL EFFECT", "sharpsignalDocId": 438}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "components", "sharpsignalDocId": 438}, {"page": 5, "quote": null, "headingPath": "components · WINNING & LOSING · Villain Turn · MOVE VILLAIN", "sharpsignalDocId": 438}, {"page": 11, "quote": null, "headingPath": "Additional Rules · S.H.I.E.L.D. Solo Mode · SPECIAL SETUP:", "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)
- answer fence
- passed — letter density 0.89533 of 1156 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 9, 2026 14:27 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 Marvel United — Rulebook (corpus doc 438) | Completing Missions · KO | p.10 | 0.047379 (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) | Additional Rules · S.H.I.E.L.D. Solo Mode · SPECIAL SETUP: | p.11 | 0.046696 (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) | components | p.4 | 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 |
| #4 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | Hero Turn · 1. DRAW A CARD · 2. PLAY A CARD · 3. RESOLVE ACTIONS | p.7 | 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 |
| #5 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | components · WINNING & LOSING · Villain Turn · MOVE VILLAIN | p.5 | 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 United — Rulebook (corpus doc 438) | Turn Sequence · UNDER PRESSURE · Rescue Civilians · Defeat Thugs | p.9 | 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 Marvel United — Rulebook (corpus doc 438) | overview | p.2 | 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) | ACTIVATE BAM! · ADD THUGS/CIVILIANS · SPECIAL EFFECT | p.6 | 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 |
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 22 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 Marvel United — Rulebook (corpus doc 438) | Additional Rules · S.H.I.E.L.D. Solo Mode · SPECIAL SETUP: | p.11 | #2 | 0.046696 (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 Marvel United — Rulebook (corpus doc 438) | Hero Turn · 1. DRAW A CARD · 2. PLAY A CARD · 3. RESOLVE ACTIONS | p.7 | #4 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | RULES SUMMARY · VILLAIN TURN · HERO TURN · HERO DAMAGE · WINNING & LOSING | p.12 | #10 | 0.014286 (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 |
| #4 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | components | p.4 | #3 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | overview | p.2 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | Completing Missions · KO | p.10 | #1 | 0.047379 (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 Marvel United — Rulebook (corpus doc 438) | p.2 | #18 | 0.012821 (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 | |
| #8 | RULEBOOK Marvel United — Rulebook (corpus doc 438) | components · WINNING & LOSING · Villain Turn · MOVE VILLAIN | p.5 | #5 | 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)) | vector + 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 Marvel United — Rulebook (corpus doc 438) | components | p.4 | no quote on the wire |
| [2] | RULEBOOK Marvel United — Rulebook (corpus doc 438) | components · WINNING & LOSING · Villain Turn · MOVE VILLAIN | p.5 | no quote on the wire |
| [3] | RULEBOOK Marvel United — Rulebook (corpus doc 438) | Additional Rules · S.H.I.E.L.D. Solo Mode · SPECIAL SETUP: | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 107 ms · first delta 1954 ms · total 3847 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 107 ms · ask 3738 ms · gateway work 3847 ms · total 3847 ms
- tokens in (the prompt the answerer read)
- 2776
- tokens out (what the answerer generated)
- 367
- tok/sec
- 200.9 tok/sec — 367 output tokens in 1.827 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 1s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 0s 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
- 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)
-
setup
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.