You asked
What does each player take, and what goes in the middle, before we begin?
Answered counted as answeredAsked with: Distilledbg-295895-en-1e
Each player takes the following: * A distillery board and a matching color score modifier token [1]. * A recipe clipboard with a chosen tasting flight card placed in it [1]. * One starting Metal Barrel card and one starting Glass Bottle card, which are placed in their storeroom on their distillery board [1]. * Three distillery goal cards (which are private) [1]. * Two random distiller identities from those paired with their chosen tasting flight; the player then selects one identity and returns the other to the box [1]. * The ingredients and money listed on the reverse side of their selected distiller identity card, placing the ingredients in their pantry [1]. * The signature recipe label and signature ingredient stated on their distiller identity card, placing the label on their clipboard recipe-side up and the ingredient out of play next to their distillery board [1]. * Their distiller identity card is placed face-up on the office space on their distillery board [1]. Regarding what goes in the middle: I don't have enough information.
🔧 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 335 ms · ask 9773 ms · total 10119 ms
- single-flight (PR-5)
- queued 0 ms · generation 10119 ms
- retrieval refs (raw)
- [{"page": 13, "score": 0.032787, "snippet": "Start of Round perform effects Market Phase (in player order) T ake turns in clockwise order to purchase 1 card or cube per turn, until all pass Limit of 2 basic market purchases per player, per round Market Clean Up: Discard last card of each premium market row to truck and replenish; last 2 cards ", "headingPath": "SEQUENCE OF A ROUND · End of Round · INDEX · END GAME SCORING · ICON GLOSSARY", "sharpsignalDocId": 376}, {"page": 7, "score": 0.032258, "snippet": "At the beginning of the Distill Phase, the player plans to make Rum. They have purchased its recipe cube, have bought a wood barrel, and their washback contains one Alcohol, two Mixed Plants, and one Water, so they add two Alcohol to it, for the two sugars. They then shuffle these six cards together", "headingPath": "DISTILL PHASE EXAMPLE: RUM", "sharpsignalDocId": 376}, {"page": 12, "score": 0.031746, "snippet": "The solo game plays over 7 rounds as normal, but with one modification to the market phase. At the end of each market phase, instead of the market clean up, discard the top card from the leftover B goal stack to reveal the back of the next card. The chart on the back of the revealed card shows which", "headingPath": "SOLO GAMEPLAY", "sharpsignalDocId": 376}, {"page": 2, "score": 0.03125, "snippet": "Over the course of seven rounds you will acquire ingredients, items, recipes, and upgrades to create the world's most renowned spirits. Whoever has the most spirit points at the end of the game earns the title of Master Distiller. BEGINNER GUIDE: If this is your first time playing Distilled, we reco", "headingPath": "", "sharpsignalDocId": 376}, {"page": 8, "score": 0.030769, "snippet": "After everyone has either sold or aged each of their spirits, the round is over. Before starting the next round, do the following: Check for fulfilled spirit awards. If you meet the stated goal, you earn the amount of SP shown. Advance your scoring token that many spaces on the SP track. If more tha", "headingPath": "END OF ROUND", "sharpsignalDocId": 376}, {"page": 6, "score": 0.030303, "snippet": "Once all players have passed, discard the rightmost face-up card from each premium market row (or two rightmost in two player games), placing them face-up on the truck. Shift all cards to the right and lay out the top card of each deck to fill the leftmost space so there are always four cards availa", "headingPath": "MARKET CLEAN UP", "sharpsignalDocId": 376}, {"page": 3, "score": 0.029851, "snippet": "GAME SETUP Shelf Board: Place the shelf board on the table. It holds spirit labels and tracks rounds and spirit points. Place a scoring token for each player in a color of their choice next to it and the round marker (brown barrel) on the '1' space of the round track. Basic Market: Place the basic m", "headingPath": "", "sharpsignalDocId": 376}, {"page": 13, "score": 0.029412, "snippet": "Market Phase (in player order) • Take turns in clockwise order to purchase 1 card or cube per turn, until all pass • Limit of 2 basic market purchases per player, per round Market Clean Up: Discard last card of each premium market row to truck and replenish; last 2 cards for 2P game 2. Distill Phase", "headingPath": "", "sharpsignalDocId": 376}]
- citations (raw)
- [{"page": 4, "quote": null, "headingPath": "PLAYER SETUP · GAME OVERVIEW · ROUND OVERVIEW · Each round is made up of four phases: · 2. Distill Phase · 3. Sell Phase · …", "sharpsignalDocId": 376}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 376 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 376 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 18:22
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 Distilled — Rulebook (corpus doc 376) | SEQUENCE OF A ROUND · End of Round · INDEX · END GAME SCORING · ICON GLOSSARY | p.13 | 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 Distilled — Rulebook (corpus doc 376) | DISTILL PHASE EXAMPLE: RUM | 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 Distilled — Rulebook (corpus doc 376) | SOLO GAMEPLAY | p.12 | 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 Distilled — Rulebook (corpus doc 376) | p.2 | 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 Distilled — Rulebook (corpus doc 376) | END OF ROUND | 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)) | 300 |
| #6 | RULEBOOK Distilled — Rulebook (corpus doc 376) | MARKET CLEAN UP | p.6 | 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 Distilled — Rulebook (corpus doc 376) | p.3 | 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 Distilled — Rulebook (corpus doc 376) | p.13 | 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 Distilled — Rulebook (corpus doc 376) | PLAYER SETUP · GAME OVERVIEW · ROUND OVERVIEW · Each round is made up of four phases: · 2. Distill Phase · 3. Sell Phase · … | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 335 ms · first delta 8457 ms · total 10119 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 335 ms · ask 9773 ms · gateway work 10119 ms · total 10119 ms
- tokens in (the prompt the answerer read)
- 3725
- tokens out (what the answerer generated)
- 218
- tok/sec
- 136.8 tok/sec — 218 output tokens in 1.593 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- BEGIN — "begin" / "beginning"
- matched words (in the normalized question)
-
begin
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 305), 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.