You asked
How do I set up the game?
Answered counted as answeredAsked with: Dominionbg-36218-en-1e
1. Each player takes 3 Estates and 7 Coppers and shuffles them face down as a starting deck [1]. 2. Place 17 face-up piles of cards on the table: the 7 Base card piles (Copper, Silver, Gold, Estate, Duchy, Province, and Curse) and 10 Kingdom card piles [1]. 3. Use every copy you have of Copper, Silver, and Gold (except Coppers players already have) [1]. 4. Use 8 copies each of Estate, Duchy, and Province for a 2-player game, or 12 copies each for 3-4 players [1]. 5. Use 10 Curses for 2 players, 20 for 3 players, and 30 for 4 players [1]. 6. Choose 10 Kingdom cards to use and get out piles of 10 copies of each card (do not include the randomizer card in the pile) [1]. 7. If a Victory Kingdom card is used, use 8 copies for 2 players or 12 copies for 3-4 players [1]. 8. Put the Trash mat near the piles [1]. 9. Randomly choose a starting player (if you just played a game that was not a tie, the previous winner goes last) [2]. 10. Each player draws an initial hand of 5 cards [2].
🔧 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 262 ms · ask 8877 ms · total 1641816 ms
- single-flight (PR-5)
- queued 1632668 ms · generation 9148 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.046696, "snippet": "Updated kingdom randomizer 2nd.indd 1 Each player takes 3 Estates and 7 Coppers and shuffles them face down as a starting deck. Place 17 face-up piles of cards on the table: the 7 Base card piles, which are always used, and always the same, and 10 Kingdom card piles, which vary from game to game. Th", "headingPath": "", "sharpsignalDocId": 102}, {"page": 4, "score": 0.032787, "snippet": "Randomly choose a starting player. If you have just played a game of Dominion and it was not a tie, have the player who won the previous game go last (the player to their left goes first). Each player draws an initial hand of 5 cards. Dominion is a game of building a deck of cards. Each player has t", "headingPath": "", "sharpsignalDocId": 102}, {"page": 14, "score": 0.032258, "snippet": "For example if you start a turn by playing Throne Room on Village, you would draw a card, get +2 Actions, draw another card, and get +2 Actions again, leaving you with 4 Actions. If you Throne Room a Throne Room, you may play an Action card twice, then may play another Action card twice; you do not ", "headingPath": "1st turn", "sharpsignalDocId": 102}, {"page": 8, "score": 0.031746, "snippet": "When a card tells you to play a card, that does not use up an Action play for the turn. As with playing a card normally, you follow the instructions in order, stopping at a dividing line when there is one. As always, played cards go into play, not directly into the discard pile.", "headingPath": "\"Play a card\" - Put a card into play, and follow the instructions on it.", "sharpsignalDocId": 102}, {"page": 13, "score": 0.03125, "snippet": "Laboratory: You draw 2 cards and get +1 Action. Library: You look at cards one at a time, putting each one into your hand or setting it aside, until you have 7 cards in hand; then you discard the set aside cards. If you shuffle in the middle of doing this, you do not shuffle in the set aside cards. ", "headingPath": "1st turn", "sharpsignalDocId": 102}, {"page": 8, "score": 0.030769, "snippet": "Set aside cards are not \"in play.\" Set aside cards are face up unless otherwise specified. A card that sets a card aside will say when to move it somewhere else.", "headingPath": "\"Set aside a card\" - Put the card on the table, outside of the play area.", "sharpsignalDocId": 102}, {"page": 6, "score": 0.030214, "snippet": "The game ends at the end of a turn, if either the Province pile is empty, or any three or more Supply piles are empty (any piles at all, including Kingdom cards, Curses, Copper, etc.). Take all of your cards - from your hand, deck, discard pile, play area, and even set aside cards - and sort them fo", "headingPath": "treasure_2nd02.indd 1", "sharpsignalDocId": 102}, {"page": 9, "score": 0.029911, "snippet": "You can count the number of cards in your deck at any time (without looking at the card fronts), but cannot look through or count your discard pile or another player's deck or discard pile. The number of cards in each player's hand is public, as is the top card of each discard pile. All cards in pla", "headingPath": "\"Trash a card\" - Put a card into the Trash pile.", "sharpsignalDocId": 102}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "", "sharpsignalDocId": 102}, {"page": 4, "quote": null, "headingPath": "", "sharpsignalDocId": 102}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 102 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 102 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 14:37
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 Dominion — Rulebook (corpus doc 102) | p.3 | 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 | |
| #2 | RULEBOOK Dominion — Rulebook (corpus doc 102) | 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 | |
| #3 | RULEBOOK Dominion — Rulebook (corpus doc 102) | 1st turn | p.14 | 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 |
| #4 | RULEBOOK Dominion — Rulebook (corpus doc 102) | "Play a card" - Put a card into play, and follow the instructions on it. | p.8 | 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)) | 279 |
| #5 | RULEBOOK Dominion — Rulebook (corpus doc 102) | 1st turn | p.13 | 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 |
| #6 | RULEBOOK Dominion — Rulebook (corpus doc 102) | "Set aside a card" - Put the card on the table, outside of the play area. | p.8 | 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)) | 161 |
| #7 | RULEBOOK Dominion — Rulebook (corpus doc 102) | treasure_2nd02.indd 1 | p.6 | 0.030214 (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 Dominion — Rulebook (corpus doc 102) | "Trash a card" - Put a card into the Trash pile. | p.9 | 0.029911 (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 Dominion — Rulebook (corpus doc 102) | p.3 | no quote on the wire | |
| [2] | RULEBOOK Dominion — Rulebook (corpus doc 102) | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 262 ms · first delta 6866 ms · total 1641816 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1632668 ms · retrieval 262 ms · ask 8877 ms · gateway work 9148 ms · total 1641816 ms
- tokens in (the prompt the answerer read)
- 3251
- tokens out (what the answerer generated)
- 307
- tok/sec
- 137.9 tok/sec — 307 output tokens in 2.227 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 55s 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
- SERVED — setup-shaped and this game's approved setup checklist is offered above
- 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 33), 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.