You asked
What needs to be placed on the table before the first round begins?
Abstained — no grounded answer; closest passages below counted as honest abstainAsked with: Stockpilebg-161614-en-1e
The answerer couldn't ground a confident answer in the rulebook. The closest rulebook passages are below — check them before ruling.
Stockpile is played over several rounds based on the number of players (see Figure 2). Play begins with the player with the First Player Token and continues clockwise. At the end of each round, pass the First Player Token to the next player on the left. Each round consists of six phases: Information
Each player is randomly dealt two pairs of Company Cards and Forecast Cards. Note: Keep them in separate piles. These cards may not be swapped or substituted with each other. The remaining two pairs of Company Cards and Forecast Cards are both placed face-down next to the game board. These pairs wil
Note: The cards can either be placed in the same Stockpile or different Stockpiles. Cards may not be placed in the 4 or 5 player Stockpiles if there are not enough players in the game. Be sure to fan the cards out so everyone can see how many cards are in each Stockpile. Once all players have added
Flip one card from the Market Deck face-up to start building each Stockpile. Stockpiles are formed under the calculators at the bottom of the board. The number of Stockpiles in each game is equal to the number of players. Deal two cards from the Market Deck to each player. Players must keep these ca
In turn order, each player places his/her Bidding Meeple on an open number of any Bidding Track they choose, including those tracks with bids already on them so long as the bid increases. Note: A player may not bid more money than they currently have. How much money a player has is public knowledge.
🔧 debug — where this ruling came from
- outcome
- ABSTAINED — Abstained — no grounded answer; closest passages below
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 234 ms · ask 4213 ms · total 65862 ms
- single-flight (PR-5)
- queued 61403 ms · generation 4459 ms
- retrieval refs (raw)
- [{"page": 4, "score": 0.032787, "snippet": "Stockpile is played over several rounds based on the number of players (see Figure 2). Play begins with the player with the First Player Token and continues clockwise. At the end of each round, pass the First Player Token to the next player on the left. Each round consists of six phases: Information", "headingPath": "The Round · 1. Information Phase · Information Phase Steps · 2. Supply Phase", "sharpsignalDocId": 539}, {"page": 7, "score": 0.032258, "snippet": "Each player is randomly dealt two pairs of Company Cards and Forecast Cards. Note: Keep them in separate piles. These cards may not be swapped or substituted with each other. The remaining two pairs of Company Cards and Forecast Cards are both placed face-down next to the game board. These pairs wil", "headingPath": "Information Phase · Supply Phase · Demand Phase", "sharpsignalDocId": 539}, {"page": 5, "score": 0.031746, "snippet": "Note: The cards can either be placed in the same Stockpile or different Stockpiles. Cards may not be placed in the 4 or 5 player Stockpiles if there are not enough players in the game. Be sure to fan the cards out so everyone can see how many cards are in each Stockpile. Once all players have added ", "headingPath": "Supply Phase Steps · 3. Demand Phase", "sharpsignalDocId": 539}, {"page": 4, "score": 0.03125, "snippet": "Flip one card from the Market Deck face-up to start building each Stockpile. Stockpiles are formed under the calculators at the bottom of the board. The number of Stockpiles in each game is equal to the number of players. Deal two cards from the Market Deck to each player. Players must keep these ca", "headingPath": "Supply Phase Steps", "sharpsignalDocId": 539}, {"page": 5, "score": 0.030769, "snippet": "In turn order, each player places his/her Bidding Meeple on an open number of any Bidding Track they choose, including those tracks with bids already on them so long as the bid increases. Note: A player may not bid more money than they currently have. How much money a player has is public knowledge.", "headingPath": "Demand Phase Steps", "sharpsignalDocId": 539}, {"page": 8, "score": 0.030303, "snippet": "Players continue to alternate re-bidding until all Bidding Meeples are on a separate Bidding Track, but it is possible for a player to bid twice in a row. If both of a player's Bidding Meeples have been out-bid, then that player may choose either Bidding Meeple to re-bid with first. Note: The combin", "headingPath": "Demand Phase · Expansions · Advanced Board Expansion · Investor Expansion", "sharpsignalDocId": 539}, {"page": 10, "score": 0.029851, "snippet": "Figure 14 - Box insert organisation. Raise the Bid - Most players tend not to be aggressive enough during bidding in their first few games of Stockpile. Stockpiles that contain more cards in them can often be worth surprisingly more than other stockpiles with fewer cards. While it is possible to pay", "headingPath": "Secretive Stuart · Tips for New Players", "sharpsignalDocId": 539}, {"page": 12, "score": 0.029412, "snippet": "-Each player starts with $20,000 and one randomly dealt stock. -Pass out the First Player Token. -Shuffle Market Deck (Action Cards, Trading Fee Cards, and remaining Stock Cards). -Each player receives one Company Card and one Forecast Card. -Flip one pair (Company Card and Forecast Card) face-up. -", "headingPath": "Setup · 1. Information Phase · 2. Supply Phase · 3. Demand Phase · 4. Action Phase · 5. Selling Phase · …", "sharpsignalDocId": 539}]
- citations (raw)
- []
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 539 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 539 boosted
- answered-before recall
-
no past answered ruling for this game matched closely enough
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 08:03
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 Stockpile — Rulebook (corpus doc 539) | The Round · 1. Information Phase · Information Phase Steps · 2. Supply Phase | 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 |
| #2 | RULEBOOK Stockpile — Rulebook (corpus doc 539) | Information Phase · Supply Phase · Demand Phase | 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 |
| #3 | RULEBOOK Stockpile — Rulebook (corpus doc 539) | Supply Phase Steps · 3. Demand Phase | 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 |
| #4 | RULEBOOK Stockpile — Rulebook (corpus doc 539) | Supply Phase Steps | p.4 | 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 Stockpile — Rulebook (corpus doc 539) | Demand Phase Steps | p.5 | 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 Stockpile — Rulebook (corpus doc 539) | Demand Phase · Expansions · Advanced Board Expansion · Investor Expansion | p.8 | 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 Stockpile — Rulebook (corpus doc 539) | Secretive Stuart · Tips for New Players | p.10 | 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 Stockpile — Rulebook (corpus doc 539) | Setup · 1. Information Phase · 2. Supply Phase · 3. Demand Phase · 4. Action Phase · 5. Selling Phase · … | p.12 | 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 |
|---|
generation — timing and the path taken
- timing split
- retrieval 234 ms · first delta 4364 ms · total 65862 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 61403 ms · retrieval 234 ms · ask 4213 ms · gateway work 4459 ms · total 65862 ms
- tokens in (the prompt the answerer read)
- 3456
- tokens out (what the answerer generated)
- 9
- tok/sec
- 152.5 tok/sec — 9 output tokens in 0.059 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s 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
- ABSTAINED — Abstained — no grounded answer; closest passages below
- abstain rationale
-
I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped
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 471), 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.