Ruling — In the Year of the Dragon

You asked

What needs to be placed on the table before the first round begins?

Answered counted as answered

Asked with: In the Year of the Dragonbg-31594-en-1e

Before the first round begins, the following must be placed on the table: 1. The game board [1]. 2. Person tiles, sorted by color and then by experience level (with older persons in the first row and matching younger persons in the second row) [2][1]. 3. Event tiles, with two peace tiles placed face up in the first two spaces of the event row, and the remaining ten tiles shuffled, placed face down, and drawn one at a time to be placed face up from left to right [2]. 4. Action cards, thoroughly shuffled and placed in a face down pile in the middle space on the board [2]. 5. Each player's person marker, placed on the 0 space of the person track [2]. 6. Each player's scoring marker, placed on the 0 space of the scoring track [2]. 7. Each player's dragon (in a stand), placed in their playing area [2]. 8. Each player's hand of 11 person cards [2]. 9. Each player's game overview, placed near their playing area [2]. 10. Each player's four palace floors and two 2-story palaces [2]. 11. Each player's 6 yuan (3 silver and 1 gold), placed next to their palaces [2].

[1] RULEBOOK In the Year of the Dragon — Rulebook · p.2 · PREPARATION

[2] RULEBOOK In the Year of the Dragon — Rulebook · p.2 · PREPARATION

🔧 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 238 ms · ask 6195 ms · total 103261 ms
single-flight (PR-5): queued 96815 ms · generation 6446 ms
retrieval refs (raw): [{"page": 2, "score": 0.032787, "snippet": "Before your first game, carefully punch out all of the tiles from their frames, and place the dragons in their stands. Place the game board in the middle of the table. Set up the rest of the pieces as shown in the diagram to the right: The Person Tiles: First, sort these tiles by their color. Then s", "headingPath": "PREPARATION", "sharpsignalDocId": 544}, {"page": 3, "score": 0.032258, "snippet": "Shuffle the 7 action cards at the start of this phase. Then place them, still face down, in the large center space on the board in as many groups as there are players (e.g., if there are 2 players, they are divided into 2 groups; if there are 3 players, 3 groups, etc.) . The cards should be divided ", "headingPath": "1st Phase: Action · PLAYING THE GAME", "sharpsignalDocId": 544}, {"page": 3, "score": 0.031746, "snippet": "each player must summon his first 2 subjects to court. The oldest player starts. He takes 2 different person tiles of his choosing from the second row (i.e., the younger persons). In clockwise order, the other players then choose their first 2 persons, following the same restrictions. Additionally, ", "headingPath": "Before the game begins , · PLAYING THE GAME", "sharpsignalDocId": 544}, {"page": 2, "score": 0.03125, "snippet": "The front side shows an overview of the game's phases, and the back side displays the actions and events in brief. Additionally, each player takes 4 palace floors and builds 2 palaces with 2 stories each in his playing area, and takes 6 yuan (3 silver and 1 gold). (Each player should place his money", "headingPath": "PREPARATION", "sharpsignalDocId": 544}, {"page": 2, "score": 0.030769, "snippet": "Place the person tiles on the board (sorted by younger and older), along with the event tiles (2 peace tiles first, then randomly), and the action cards (in a face down pile) Note: Only in a 5-player game will you place all 10 person tiles of each type on the display. When playing with fewer, return", "headingPath": "PREPARATION", "sharpsignalDocId": 544}, {"page": 8, "score": 0.030303, "snippet": "After an event occurs, each player must check to see if he has any uninhabited palaces. If so, each such palace must be reduced by 1 floor (returning lost palace floors to the supply). Note that this can lead to the complete disappearance of an unpopulated, one-story palace. Note: Because of this ru", "headingPath": "Decay · 4th Phase: Scoring", "sharpsignalDocId": 544}, {"page": 2, "score": 0.029851, "snippet": "1 person marker (person track) 1 scoring marker (scoring track) 1 dragon 11 person cards 1 game overview 4 palace floors (2 2-story palaces) 6 yuan Place the remaining pieces (money, rice sacks, fireworks, privileges, palace floors) handy above the board", "headingPath": "Each player takes:", "sharpsignalDocId": 544}, {"page": 6, "score": 0.029412, "snippet": "After everyone has taken an action or replenished his supply of yuan to 3, each player, in the order shown on the person track (which may have changed through the action 'Military Parade') , plays 1 person card from his hand onto the common discard pile on the board. The player then takes the matchi", "headingPath": "2nd Phase: Person · Note: · 3rd Phase: Event · Peace:", "sharpsignalDocId": 544}]
citations (raw): [{"page": 2, "quote": null, "headingPath": "PREPARATION", "sharpsignalDocId": 544}, {"page": 2, "quote": null, "headingPath": "PREPARATION", "sharpsignalDocId": 544}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 544 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 544 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 08:04

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 In the Year of the Dragon — Rulebook (corpus doc 544)	PREPARATION	p.2	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 In the Year of the Dragon — Rulebook (corpus doc 544)	1st Phase: Action · PLAYING THE GAME	p.3	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 In the Year of the Dragon — Rulebook (corpus doc 544)	Before the game begins , · PLAYING THE GAME	p.3	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 In the Year of the Dragon — Rulebook (corpus doc 544)	PREPARATION	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 In the Year of the Dragon — Rulebook (corpus doc 544)	PREPARATION	p.2	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 In the Year of the Dragon — Rulebook (corpus doc 544)	Decay · 4th Phase: Scoring	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 In the Year of the Dragon — Rulebook (corpus doc 544)	Each player takes:	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))	254
#8	RULEBOOK In the Year of the Dragon — Rulebook (corpus doc 544)	2nd Phase: Person · Note: · 3rd Phase: Event · Peace:	p.6	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

#	document	heading	page	quote chars
[1]	RULEBOOK In the Year of the Dragon — Rulebook (corpus doc 544)	PREPARATION	p.2	no quote on the wire
[2]	RULEBOOK In the Year of the Dragon — Rulebook (corpus doc 544)	PREPARATION	p.2	no quote on the wire

generation — timing and the path taken

timing split: retrieval 238 ms · first delta 4284 ms · total 103261 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 96815 ms · retrieval 238 ms · ask 6195 ms · gateway work 6446 ms · total 103261 ms
tokens in (the prompt the answerer read): 3583
tokens out (what the answerer generated): 289
tok/sec: 138.3 tok/sec — 289 output tokens in 2.090 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 46s 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 476), 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.