You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Gùgōngbg-250458-en-1e
To set up the table before anyone takes a turn: 1. Place the Game Board in the middle of your playing table, oriented on the side corresponding to the number of players as shown on its lower left corner [1]. 2. Place all players' Travellers next to the board [1]. 3. Place all players' Envoys on the starting location of the Palace of Heavenly Purity Track [1]. 4. Place all players' Ships next to their respective Player Boards [1]. 5. Place the Next Start Player Medal on the appropriate space next to the Intrigue Track card location [1]. 6. Place all players' Intrigue Markers on the starting location of the Intrigue Track, with the starting player's marker at the bottom and continuing in turn order clockwise [1]. 7. Shuffle all Travel Tokens and randomly place 1 faceup on each city on the Travel location, then stack the remaining tokens on 2 facedown draw piles of equal size on the indicated locations [1]. 8. Place the VP Marker on the '0' spot of the Victory Points (VP) Track [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 287 ms · ask 9081 ms · total 9421 ms
- single-flight (PR-5)
- queued 43 ms · generation 9378 ms
- retrieval refs (raw)
- [{"page": 14, "score": 0.032787, "snippet": "When all players have run out of Gift Cards in the Day Phase, the Night Phase starts. This is a 2-step process: All players take their Gift Cards from their discard pile cards into their hands and simultaneously check whether their values match the values of the Destiny Dice. For each match, you may", "headingPath": "PHASE 3: THE NIGHT PHASE · Step 1: Check Destiny Dice values · Step 2: Move all Ships", "sharpsignalDocId": 480}, {"page": 16, "score": 0.032258, "snippet": "Before the Night Phase begins, Meng's Servants will take an extra opportunity to further Meng's actions during the Twilight Phase in the following steps: T urn the discard pile of played Automa Cards of this Day facedown. One at a time, reveal each Automa card and take the bottom (Twilight) action, ", "headingPath": "Twilight Phase", "sharpsignalDocId": 480}, {"page": 5, "score": 0.031746, "snippet": "In the Day Phase, players perform various actions by exchanging Gift Cards with the Officials working in the Forbidden City, represented by the 7 Card locations on the Game Board. Beginning with the start player and going around the table in clockwise order, players will take turns exchanging Gift C", "headingPath": "PHASE 2: THE DAY PHASE · 1. Exchanging Gifts", "sharpsignalDocId": 480}, {"page": 16, "score": 0.03125, "snippet": "The board should be set up for a normal 2-player game, with these exceptions: Shuffle the 7 Gift Cards marked with the symbol and randomly pick 1. Remember the number you picked, place the 7 Gift Cards randomly on the Game Board and place Meng's Double Servant next to the Card with the number you pi", "headingPath": "SETUP (SOLO) · Human · Morning Phase · Day Phase", "sharpsignalDocId": 480}, {"page": 17, "score": 0.030769, "snippet": "The Night Phase rewards matching Gift Cards with the Destiny Dice and moves Ships as normal, with 1 exception: you do not count Meng's matching cards as normal. Regardless of his amount of matching Cards, Meng's discard pile of Gift Meng's actions are decided by the Gift Card and Automa Card that he", "headingPath": "Twilight Phase · CARD AND LOCATION ACTIONS (SOLO) · TRAVEL · Travel tokens · Special cases", "sharpsignalDocId": 480}, {"page": 16, "score": 0.030303, "snippet": "Player 5 cards Player 3 cards Player 2 cards Shuffle Meng's cards and place them facedown next to his Player Board. Shuffle the Automa deck and place it facedown next to Meng' s Player Board. These cards will determine where Meng exchanges gifts each turn. For an easy game, use only 1 Special Automa", "headingPath": "Meng", "sharpsignalDocId": 480}, {"page": 20, "score": 0.029851, "snippet": "Return the indicated number of Servants from the Servant Pool on your Player Board to your general supply. Move the indicated number of Servants from your Servant Pool on your Player Board to the appropriate space on the Game Board or your Ship. Immediately score the indicated number of VP by moving", "headingPath": "GENERAL ICONOGRAPHY · LIST OF TRAVEL TOKENS", "sharpsignalDocId": 480}, {"page": 2, "score": 0.029412, "snippet": "3 Destiny Dice Roll the 3 dice and place them on the indicated spaces. These determine which Gift Cards will grant you extra Servants and maybe even Victory Points at the end of each round. 1 Day Tracker Place it on the first space of the Day Track. It will indicate the current round. 1 Start Player", "headingPath": "GAME MATERI", "sharpsignalDocId": 480}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "R U L E B O O K", "sharpsignalDocId": 480}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 480 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 480 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 05:53
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 Gùgōng — Rulebook (corpus doc 480) | PHASE 3: THE NIGHT PHASE · Step 1: Check Destiny Dice values · Step 2: Move all Ships | p.14 | 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 Gùgōng — Rulebook (corpus doc 480) | Twilight Phase | p.16 | 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 Gùgōng — Rulebook (corpus doc 480) | PHASE 2: THE DAY PHASE · 1. Exchanging Gifts | 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 Gùgōng — Rulebook (corpus doc 480) | SETUP (SOLO) · Human · Morning Phase · Day Phase | p.16 | 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 Gùgōng — Rulebook (corpus doc 480) | Twilight Phase · CARD AND LOCATION ACTIONS (SOLO) · TRAVEL · Travel tokens · Special cases | p.17 | 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 Gùgōng — Rulebook (corpus doc 480) | Meng | p.16 | 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 Gùgōng — Rulebook (corpus doc 480) | GENERAL ICONOGRAPHY · LIST OF TRAVEL TOKENS | p.20 | 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 Gùgōng — Rulebook (corpus doc 480) | GAME MATERI | p.2 | 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 Gùgōng — Rulebook (corpus doc 480) | R U L E B O O K | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 287 ms · first delta 7593 ms · total 9421 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 43 ms · retrieval 287 ms · ask 9081 ms · gateway work 9378 ms · total 9421 ms
- tokens in (the prompt the answerer read)
- 4004
- tokens out (what the answerer generated)
- 236
- tok/sec
- 137.0 tok/sec — 236 output tokens in 1.723 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s 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 411), 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.