Ruling — Roll Player

You asked

What does each player take, and what goes in the middle, before we begin?

Answered counted as answered

Asked with: Roll Playerbg-169426-en-1e

Each player takes the following: * 5 Gold, with an additional 1 Gold for a third player and 2 additional Gold for a fourth player [1]. * A Class card of a matching color from a randomly drawn die, including choosing one of the two Classes on that card [1]. * One Backstory card, one Alignment card, and one Player Aid card [1]. * Two tracking tokens of their Class color [1]. The following are placed in the center of the table: * The Market (a number of cards equal to the number of players plus one) [1]. * Initiative cards lined up in numerical order [1].

[1] RULEBOOK Roll Player — Rulebook · p.7 · Setup v

🔧 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 261 ms · ask 6306 ms · total 6576 ms
single-flight (PR-5): queued 0 ms · generation 6576 ms
retrieval refs (raw): [{"page": 8, "score": 0.032787, "snippet": "Roll Player is played over a series of rounds, each divided into four phases: the Roll Phase, the Dice Phase, the Market Phase, and the Cleanup Phase. During the Roll Phase, the Start Player draws dice from the dice bag equal to the number of Initiative cards in play and rolls them to create the Dic", "headingPath": "Overview of a Round v · ROLL PHASE · DICE PHASE", "sharpsignalDocId": 370}, {"page": 7, "score": 0.032258, "snippet": "All players roll a die. The player with the highest roll is the Start Player. Place all 73 dice into the dice bag. Beginning with the Start Player and proceeding clockwise around the table, each player chooses a Character Sheet and selects the male or female side (gender choice does not affect gamep", "headingPath": "Setup v", "sharpsignalDocId": 370}, {"page": 10, "score": 0.031746, "snippet": "During the Cleanup Phase, the players prepare for the next round: Each player discards any unused Charisma tokens. Each player may refresh one exhausted Skill card by turning it upright (See page 11 for more detail about Skill cards), thereby making it available for use in the next round. The Start ", "headingPath": "CLEANUP PHASE", "sharpsignalDocId": 370}, {"page": 10, "score": 0.03125, "snippet": "During the Market Phase, each player has the opportunity to buy a card from the Market. The player order for this phase is dictated by the numbers on the Initiative cards that were chosen during the Dice Phase. The player with the lowest value Initiative card buys first, followed by the next lowest,", "headingPath": "MARKET PHASE", "sharpsignalDocId": 370}, {"page": 15, "score": 0.030769, "snippet": "If the player selected the '3' Initiative card, the player rolls the enemy die: If 1-2, move the leftmost card in the Market to the trash pile. If 3-4, move the middle card in the Market to the trash pile. If 5-6, move the rightmost card in the Market to the trash pile. Buy a card from the remaining", "headingPath": "DICE PHASE · MARKET PHASE · CLEANUP PHASE", "sharpsignalDocId": 370}, {"page": 6, "score": 0.030303, "snippet": "The five Initiative cards are used to coordinate the flow of gameplay. Dice and Gold are placed on Initiative cards at the beginning of each round. Players then take turns selecting an Initiative card. The number on the card dictates player order when it is time to purchase Market cards. Two-Player ", "headingPath": "Initiative Cards v · Setup v", "sharpsignalDocId": 370}, {"page": 16, "score": 0.029851, "snippet": "Roll to determine the Start Player. Choose a Character Sheet and select the male or female side. Take 5 Gold (3rd player +1 Gold / 4th player +2 Gold). Draw a random die and take the Class card of the matching color. Choose a side. Take a Player Aid card, a Backstory card, and an Alignment card. Pla", "headingPath": "Setup · 1. Roll · 2. Dice · 3. Market · 4. Cleanup", "sharpsignalDocId": 370}, {"page": 14, "score": 0.029412, "snippet": "For a less random setup, give each player one die of each player color (green, blue, red, white, purple, and black), rather than drawing randomly from the dice bag. Then, if playing with three players, give each player a gold die in addition to the set of six dice, or if playing with four players, t", "headingPath": "Less Random Setup · Random Market Deck · Short Game · Friendly Market · SETUP · ROLL PHASE", "sharpsignalDocId": 370}]
citations (raw): [{"page": 7, "quote": null, "headingPath": "Setup v", "sharpsignalDocId": 370}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 370 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 370 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 18:19

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 Roll Player — Rulebook (corpus doc 370)	Overview of a Round v · ROLL PHASE · DICE PHASE	p.8	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 Roll Player — Rulebook (corpus doc 370)	Setup v	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 Roll Player — Rulebook (corpus doc 370)	CLEANUP PHASE	p.10	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 Roll Player — Rulebook (corpus doc 370)	MARKET PHASE	p.10	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 Roll Player — Rulebook (corpus doc 370)	DICE PHASE · MARKET PHASE · CLEANUP PHASE	p.15	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 Roll Player — Rulebook (corpus doc 370)	Initiative Cards v · Setup v	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 Roll Player — Rulebook (corpus doc 370)	Setup · 1. Roll · 2. Dice · 3. Market · 4. Cleanup	p.16	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 Roll Player — Rulebook (corpus doc 370)	Less Random Setup · Random Market Deck · Short Game · Friendly Market · SETUP · ROLL PHASE	p.14	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 Roll Player — Rulebook (corpus doc 370)	Setup v	p.7	no quote on the wire

generation — timing and the path taken

timing split: retrieval 261 ms · first delta 5494 ms · total 6576 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 261 ms · ask 6306 ms · gateway work 6576 ms · total 6576 ms
tokens in (the prompt the answerer read): 3472
tokens out (what the answerer generated): 139
tok/sec: 137.2 tok/sec — 139 output tokens in 1.013 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 33s 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 299), 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.