Ruling — Roll for the Galaxy

You asked

How should we prepare everything before the first turn?

Answered counted as answered

Asked with: Roll for the Galaxybg-132531-en-1e

To prepare everything before the first turn, follow these steps:

1. Put all dice, VP chips (common pool), phase tiles (with the $\text{ }$ side up, in order), faction tile, and home world tile in the center of the play area.[1]

2. Give each player a dice cup, a credit marker, a mat, a screen, and a phase strip.[1]

3. Place the credit marker on the $1 space of the mat.[1]

4. Each player draws two tiles from the bag and places them in the construction zone on the mat: one tile development-side-up on the left and one tile world-side-up on the right.[1] (For a first game, place these so that the lowest-cost development and lowest-cost world are face up).[1]

5. Use 12 VPs per player (in 1VP and 5VP chips): 2 players use 24, 3 players use 36, 4 players use 48, and 5 players use 60.[1]

6. Set all 10VP chips aside to be used only in the final round and put the other VP chips away.[1]

7. Give each player one faction tile and one home world tile (chosen at random) and have them place these tiles face-up in front of their mat to form the initial empire/tableau.[1]

8. Return any unused player components to the box.[1]

9. Each player takes dice:

a. Put 3 Home (white) dice in your cup.[1]

b. Put 2 Home dice in your Citizenry.[1]

c. Take all dice granted by worlds in your empire and place them as indicated in the Citizenry, the dice cup, or as a good on that world.[1]

[1] RULEBOOK Roll for the Galaxy — Rulebook · p.2

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live,vps
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 83 ms · ask 4641 ms · total 4725 ms
single-flight (PR-5): queued 0 ms · generation 4725 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 9, "score": 0.032787, "snippet": "Most play can and should be done simultaneously. However, there are a few cases where player order can matter, such as: when a player might build to 12 or more tile squares (triggering game end), or when the VP chip pool might be exhausted (triggering game end). When a need for strict timing occurs,", "headingPath": "TIMING · ETIQUETTE · FOR RACE FOR THE GALAXY PLAYERS", "sharpsignalDocId": 324}, {"page": 6, "score": 0.032258, "snippet": "Put each settler , one at a time, on the top-most tile in the world construction zone ( ) stack. Once the number of settlers equals the top-most world's cost (the number in the ), the world is complete . Move its tile to the tableau and put the settlers who completed it in the Citizenry. Use any rem", "headingPath": "Settle", "sharpsignalDocId": 324}, {"page": 10, "score": 0.031746, "snippet": "Q: Must I use all my explorers during an Explore phase? A: Yes (each explorer must either Scout or Stock). Q: Must I declare in advance what all my explorers will do? A: No; you do each task one after the other, deciding which task - Scout or Stock - each explorer does as you do it. Q: What happens ", "headingPath": "Explore · Develop and Settle", "sharpsignalDocId": 324}, {"page": 4, "score": 0.03125, "snippet": "Each player lifts his screen to reveal his assigned workers, announcing the phase he has selected. Flip the matching phase tile from its ' ' side to its black side. 2-Player Game : roll a spare Home (white) die. If the rolled face is a phase that wasn't selected by either player, flip that phase til", "headingPath": "REVEAL · PHASES I IV V II III", "sharpsignalDocId": 324}, {"page": 2, "score": 0.030769, "snippet": "2 Give Each Player: • a dice cup • a credit marker • a mat (put the marker on its 1 space) • a screen • a phase strip • initial tiles (see right) 3 Each Player Draws Game Tiles: Draw two tiles from the bag and place them in the construction zone on the mat. Put one tile development‑side‑up on the le", "headingPath": "", "sharpsignalDocId": 324}, {"page": 3, "score": 0.030303, "snippet": "Roll for the Galaxy is played in rounds (usually 11-14). Each round consists of 5 steps: Roll Assign Reveal Do Phases - resolve the selected phases in order Manage Empire Each step is done simultaneously by all players. Repeat rounds until one or both game end conditions are met: all initial VP chip", "headingPath": "ROUNDS · ROLL · ASSIGN", "sharpsignalDocId": 324}, {"page": 7, "score": 0.029851, "snippet": "IV Each producer creates a good ( ) on a non-gray world ( ) in the player's tableau. The producer die ( ) becomes the good; put it on the world. Any producer die (of any color) can become a good on any non-gray world. Matching a good's color with the world's color matters only if the good will be Co", "headingPath": "Settle", "sharpsignalDocId": 324}, {"page": 5, "score": 0.029412, "snippet": "Explore Use each explorer to either Scout ( ) or Stock ( ). Put it in the Citizenry ( ) after using it. To Scout — after possibly abandoning some tiles from your construction zone — draw 1 or more tiles from the bag and examine them. Then, in any order, choose whether each tile will be a development", "headingPath": "", "sharpsignalDocId": 324}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "", "sharpsignalDocId": 324}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 324 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 324 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)
answer fence: passed — letter density 0.87814 of 1116 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 12, 2026 17:15

retrieval — what the passage search returned

what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.

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 for the Galaxy — Rulebook (corpus doc 324)	TIMING · ETIQUETTE · FOR RACE FOR THE GALAXY PLAYERS	p.9	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 for the Galaxy — Rulebook (corpus doc 324)	Settle	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 Roll for the Galaxy — Rulebook (corpus doc 324)	Explore · Develop and Settle	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 for the Galaxy — Rulebook (corpus doc 324)	REVEAL · PHASES I IV V II III	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 Roll for the Galaxy — Rulebook (corpus doc 324)		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 Roll for the Galaxy — Rulebook (corpus doc 324)	ROUNDS · ROLL · ASSIGN	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 Roll for the Galaxy — Rulebook (corpus doc 324)	Settle	p.7	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 for the Galaxy — Rulebook (corpus doc 324)		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

what the answerer read — the passages it actually had in front of it

what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.

candidate pool: the answering read scored 19 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.

floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.

arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.

read at	document	heading	page	fused rank	fused RRF score	carried by	how it got its slot
#1	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)	ROUNDS · ROLL · ASSIGN	p.3	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)	FINE POINTS · Setup · Assign	p.10	#11	0.014085 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one))	vector	the re-ranker chose it
#3	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)		p.5	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#4	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)	Explore · Develop and Settle	p.10	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)		p.2	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)	TIMING · ETIQUETTE · FOR RACE FOR THE GALAXY PLAYERS	p.9	#1	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))	vector + the doc-priority boost arm	the re-ranker chose it
#7	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)	Settle	p.6	#2	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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)	Individual Power Clarifications	p.11	#16	0.013158 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one))	vector	the re-ranker chose it

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Roll for the Galaxy — Rulebook (corpus doc 324)		p.2	no quote on the wire

generation — timing and the path taken

timing split: retrieval 83 ms · first delta 1791 ms · total 4725 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 83 ms · ask 4641 ms · gateway work 4725 ms · total 4725 ms
tokens in (the prompt the answerer read): 3826
tokens out (what the answerer generated): 399
tok/sec: 139.3 tok/sec — 399 output tokens in 2.864 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 51s 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: BEFORE_FIRST_PLAY — "before the first turn" / "before we begin"
matched words (in the normalized question): before the first turn

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 252), 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.