You asked
How do I setup the game?
Answered counted as answeredAsked with: Arcsbg-359871-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 383 ms · ask 13094 ms · total 13487 ms
- single-flight (PR-5)
- queued 0 ms · generation 13487 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 19, "score": 0.047619, "snippet": "During setup with 2 players, 6 resources matching the planets with out-of-play markers are placed on the ambition boxes. For scoring, count these resources as if a third player had them. Weapons on the Warlord box count as Trophies. Otherwise, these resources are out of play. If Warlord was scored, ", "headingPath": "Two-Player Scoring · Step 2: Clean Up & Flip Ambition · Step 3: End Game or Advance Chapter · Step 4: Draw Cards · Two-Player Mulligans", "sharpsignalDocId": 286}, {"page": 3, "score": 0.04598, "snippet": "ADMINISTRATION Tax /o.smcp/r.smcp Repair /o.smcp/r.smcp Infl uence 7 Pivot Play any action card that does not match the lead suit. You may take one action on your played card. (Not on the lead card!) Copy Play any action card face down. You may take one action of the lead card. Third, see if initiati", "headingPath": "", "sharpsignalDocId": 286}, {"page": 21, "score": 0.045037, "snippet": "Lore Card The Mystic starts with a Psionic and a Relic. They have initiative, so they place 3 ships and a city in 1A, 3 ships and a starport in 1B, and 2 ships in 1C. You can set up with as many lore cards as you want, but you run the risk of overwhelming everyone. Be careful! After playing a game o", "headingPath": "Modifiers · Leaders & Lore · Replace Steps N-O of setup (page 5) with the following: 02", "sharpsignalDocId": 286}, {"page": 5, "score": 0.032787, "snippet": "Each player chooses a color, collects the matching player board , 5 cities , 5 starports , 15 ships , and 10 agents , and places the cities in the triangle slots along the top of their player board. Each player puts their Power marker on the '0' Power track space on the map. Players simultaneously p", "headingPath": "2. Set Up Players", "sharpsignalDocId": 286}, {"page": 4, "score": 0.032258, "snippet": "Place the map and collect the 18 battle dice and 25 resource tokens . Give the initiative marker to a random player. Shuffle all 6 Vox and 25 Guild cards to make the Court deck . Draw 3 cards (2 players) or 4 cards (3-4 players) from this deck to make a face-up Court row . Shuffle the 20 action card", "headingPath": "1. Set Up Table", "sharpsignalDocId": 286}, {"page": 11, "score": 0.03125, "snippet": "Lotus played the highest Construction card to Surpass this round. Nobody seized the initiative, so Lotus takes the initiative marker. After everyone has taken a turn, check whether the initiative marker goes to a new player. If no one seized the initiative this round, give the initiative to the play", "headingPath": "Seizing the Initiative · Step 3: Check Initiative · Step 4: Discard Cards & Check for New Round", "sharpsignalDocId": 286}, {"page": 10, "score": 0.030769, "snippet": "After the player with initiative takes their turn, each other player in clockwise order takes a turn. Players with no cards in their hand skip their turn. On your turn, you must play an action card in one of three ways: Surpass: Play an action card face up of the lead card's suit. Its card number mu", "headingPath": "Step 2: Other Players Take Turns · Seizing the Initiative", "sharpsignalDocId": 286}, {"page": 14, "score": 0.030303, "snippet": "Choose Battle System: Choose 1 system that has any Loyal ships. This is the battle system. These are your attacking ships . Choose Defender: Choose 1 Rival whose pieces are in the battle system. These are their defending pieces . Collect Dice: For each attacking ship, you may collect 1 assault, skir", "headingPath": "Battle (Aggression)", "sharpsignalDocId": 286}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "1. Set Up Table", "sharpsignalDocId": 286}, {"page": 5, "quote": null, "headingPath": "2. Set Up Players", "sharpsignalDocId": 286}, {"page": 21, "quote": null, "headingPath": "Modifiers · Leaders & Lore · Replace Steps N-O of setup (page 5) with the following: 02", "sharpsignalDocId": 286}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 286 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 286 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 17:24
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 Arcs — Rulebook (corpus doc 286) | Two-Player Scoring · Step 2: Clean Up & Flip Ambition · Step 3: End Game or Advance Chapter · Step 4: Draw Cards · Two-Player Mulligans | p.19 | 0.047619 (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 Arcs — Rulebook (corpus doc 286) | p.3 | 0.04598 (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 Arcs — Rulebook (corpus doc 286) | Modifiers · Leaders & Lore · Replace Steps N-O of setup (page 5) with the following: 02 | p.21 | 0.045037 (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 Arcs — Rulebook (corpus doc 286) | 2. Set Up Players | p.5 | 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 |
| #5 | RULEBOOK Arcs — Rulebook (corpus doc 286) | 1. Set Up Table | p.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)) | 300 |
| #6 | RULEBOOK Arcs — Rulebook (corpus doc 286) | Seizing the Initiative · Step 3: Check Initiative · Step 4: Discard Cards & Check for New Round | p.11 | 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 |
| #7 | RULEBOOK Arcs — Rulebook (corpus doc 286) | Step 2: Other Players Take Turns · Seizing the Initiative | p.10 | 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 |
| #8 | RULEBOOK Arcs — Rulebook (corpus doc 286) | Battle (Aggression) | p.14 | 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 |
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 Arcs — Rulebook (corpus doc 286) | 1. Set Up Table | p.4 | no quote on the wire |
| [2] | RULEBOOK Arcs — Rulebook (corpus doc 286) | 2. Set Up Players | p.5 | no quote on the wire |
| [3] | RULEBOOK Arcs — Rulebook (corpus doc 286) | Modifiers · Leaders & Lore · Replace Steps N-O of setup (page 5) with the following: 02 | p.21 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 383 ms · first delta 6682 ms · total 13487 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 383 ms · ask 13094 ms · gateway work 13487 ms · total 13487 ms
- tokens in (the prompt the answerer read)
- 3350
- tokens out (what the answerer generated)
- 935
- tok/sec
- 138.5 tok/sec — 935 output tokens in 6.750 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 54s 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)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 215), 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.