You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Furnacebg-318084-en-1e
At the beginning of the game, everything is laid out as follows: 1. Each player receives a random Start-up card, a random Capitalist card, and a set of Capital discs with a Player's Color token of one color of their choosing [1]. 2. If any player receives a Capitalist card that provides an additional Capital disc, they also take the neutral-colored disc [1]. 3. Each player gains the resources listed at the top of their Start-up card [1]. 4. The Round counter is placed in the middle of the table and set to '1' [1]. 5. The Company deck is shuffled and placed on the Round counter with the upgraded side up [1]. 6. The 1st player is chosen randomly and given the 1st player token [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 245 ms · ask 4151 ms · total 4405 ms
- single-flight (PR-5)
- queued 0 ms · generation 4405 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.032787, "snippet": "We recommend playing your first few games without Capitalist cards in order to get accustomed to the game. We also recommend resolving the Production Phase (see further) for each player separately in order to oversee each other's actions and prevent possible mistakes. If you wish, you may play 3 rou", "headingPath": "If you're playing for the first time…", "sharpsignalDocId": 466}, {"page": 6, "score": 0.032258, "snippet": "When all players are done with the Production Phase, the round is over. If it was the 4 th round, the players proceed with scoring. Otherwise, the 1 st player token passes to the left, and a new round begins. Advance the Round counter one space. Each player adds up their money, and whoever has the m", "headingPath": "Round End · GAME END · VARIANT RULES · 2-PLAYER GAME", "sharpsignalDocId": 466}, {"page": 2, "score": 0.031746, "snippet": "All Company cards are double-sided: the first side is considered basic and the other one is upgraded. The cards enter the game with the basic side up and can later be upgraded (flipped over) during the game. Unlike Company cards, the Start-up cards are single-sided. Player's starting resources Basic", "headingPath": "Company Card Anatomy", "sharpsignalDocId": 466}, {"page": 4, "score": 0.03125, "snippet": "At the beginning of the round the 1 st player takes the Company deck, randomly cuts it to shuffle the top card in, and then deals a row of cards with the basic side up. These cards will be offered to the players at an auction. The number of cards depends on the number of players: 2 players - 6 cards", "headingPath": "Auction Phase · Compensation", "sharpsignalDocId": 466}, {"page": 5, "score": 0.030769, "snippet": "Example: There are a red '4', a black '2', and a yellow '1' placed on a card with a compensation effect of processing 1 Iron into 1 Oil. The owner of the '4' receives the card, but first, the owner of the '2' may process 1 or 2 of their Iron into 1 or 2 Oil respectively and the owner of the '1' may ", "headingPath": "Compensation · Production Phase", "sharpsignalDocId": 466}, {"page": 3, "score": 0.030303, "snippet": "During the game, the players will gain resources from their companies and use them to obtain other resources and money by resolving the effects of their cards. There are 2 types of effects: extraction and processing. Each effect is shown within its own line. Extraction - the line states the number a", "headingPath": "COMPANY EFFECTS · SETUP", "sharpsignalDocId": 466}, {"page": 2, "score": 0.029851, "snippet": "2 GAME COMPONENTS 36 double-sided Company cards 5 single-sided Start-up cards 5 Capitalist cards 1st player token 4 Players’ C olor tokens 4 different-colored sets of 4 Capital discs Each set contains 4 discs of one color with the values “1”, “2”, “3”, and “4”. 1 neutral-colored Capital disc with th", "headingPath": "", "sharpsignalDocId": 466}, {"page": 5, "score": 0.029412, "snippet": "Start-up cards are resolved in the same way as all Company cards. Its topmost effect allows the player to gain an Upgrade token. Its last effect allows the player to upgrade (flip over) as many of their Company cards as they want at a price of 1 Coal and 1 Upgrade token each. Receiving an Upgrade to", "headingPath": "Start-up cards and Upgrading", "sharpsignalDocId": 466}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "COMPANY EFFECTS · SETUP", "sharpsignalDocId": 466}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 466 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 466 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 05:49
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 Furnace — Rulebook (corpus doc 466) | If you're playing for the first time… | p.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)) | 300 |
| #2 | RULEBOOK Furnace — Rulebook (corpus doc 466) | Round End · GAME END · VARIANT RULES · 2-PLAYER GAME | p.6 | 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 Furnace — Rulebook (corpus doc 466) | Company Card Anatomy | p.2 | 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 Furnace — Rulebook (corpus doc 466) | Auction Phase · Compensation | 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 Furnace — Rulebook (corpus doc 466) | Compensation · Production Phase | 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 Furnace — Rulebook (corpus doc 466) | COMPANY EFFECTS · SETUP | p.3 | 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 Furnace — Rulebook (corpus doc 466) | 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 Furnace — Rulebook (corpus doc 466) | Start-up cards and Upgrading | p.5 | 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 Furnace — Rulebook (corpus doc 466) | COMPANY EFFECTS · SETUP | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 245 ms · first delta 3082 ms · total 4405 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 245 ms · ask 4151 ms · gateway work 4405 ms · total 4405 ms
- tokens in (the prompt the answerer read)
- 2939
- tokens out (what the answerer generated)
- 173
- tok/sec
- 137.6 tok/sec — 173 output tokens in 1.257 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 47s 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 396), 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.