Ruling — Skymines

You asked

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

Abstained — no grounded answer; closest passages below counted as honest abstain

Asked with: Skyminesbg-359438-en-1e

The answerer couldn't ground a confident answer in the rulebook. The closest rulebook passages are below — check them before ruling.

RULEBOOK Skymines — Rulebook · p.8 · Folding boxes

12 13 Give each player in clockwise seating order a specific single-energy card : The first player receives the single-energy card showing a 01 in the top right corner. The second player (if any) receives the single-energy card with the 02 . The third player (if any) receives the single-energy card

RULEBOOK Skymines — Rulebook · p.10 · 1) Planning phase · a) Place cards face down in your action area · b) Flip cards face up · 2) Action phase

The Planning phase is carried out by all players simultaneously and comprises 2 steps: Each player plans their Action phase by placing cards face down in their action area All players turn their placed cards face up Each player: Choose cards from your hand and place them face down in the available a

RULEBOOK Skymines — Rulebook · p.18 · 6) Drop out of Action phase · 3) Preparation phase for the next round · a) Flip the next special research plan face up

Perform this action only if you cannot or do not want to perform any of the other actions. To perform this action, carry out the following steps: Turn the face-down cards of your action area face up. Pick up exactly 1 of your resting decks . In the first round, each resting deck comprises only one c

RULEBOOK Skymines — Rulebook · p.7 ·

10 Each player: Choose a player color and take the corresponding player token. Then take the following items: Take a player board and place it in front of you with the standard side up. (Make sure that you leave room above and below your player board for cards.) Then place your player token onto the

RULEBOOK Skymines — Rulebook · p.19 · b) Return the bonus markers to the players (including possible bonus tiles) · c) Fill up the card display

Each player: Return all your bonus markers from bonus spaces to your reserve. If you return any markers from bonus tile spaces, also gain the corresponding bonus tiles now and place them face up in your action area next to your action slots. ( See page 20 for details on the bonus tiles. ) First, rem

🔧 debug — where this ruling came from

outcome: ABSTAINED — Abstained — no grounded answer; closest passages below
corpus profile: live
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 263 ms · ask 8968 ms · total 209733 ms
single-flight (PR-5): queued 200492 ms · generation 9241 ms
retrieval refs (raw): [{"page": 8, "score": 0.032787, "snippet": "12 13 Give each player in clockwise seating order a specific single-energy card : The first player receives the single-energy card showing a 01 in the top right corner. The second player (if any) receives the single-energy card with the 02 . The third player (if any) receives the single-energy card ", "headingPath": "Folding boxes", "sharpsignalDocId": 564}, {"page": 10, "score": 0.032258, "snippet": "The Planning phase is carried out by all players simultaneously and comprises 2 steps: Each player plans their Action phase by placing cards face down in their action area All players turn their placed cards face up Each player: Choose cards from your hand and place them face down in the available a", "headingPath": "1) Planning phase · a) Place cards face down in your action area · b) Flip cards face up · 2) Action phase", "sharpsignalDocId": 564}, {"page": 18, "score": 0.031746, "snippet": "Perform this action only if you cannot or do not want to perform any of the other actions. To perform this action, carry out the following steps: Turn the face-down cards of your action area face up. Pick up exactly 1 of your resting decks . In the first round, each resting deck comprises only one c", "headingPath": "6) Drop out of Action phase · 3) Preparation phase for the next round · a) Flip the next special research plan face up", "sharpsignalDocId": 564}, {"page": 7, "score": 0.03125, "snippet": "10 Each player: Choose a player color and take the corresponding player token. Then take the following items: Take a player board and place it in front of you with the standard side up. (Make sure that you leave room above and below your player board for cards.) Then place your player token onto the", "headingPath": "", "sharpsignalDocId": 564}, {"page": 19, "score": 0.030769, "snippet": "Each player: Return all your bonus markers from bonus spaces to your reserve. If you return any markers from bonus tile spaces, also gain the corresponding bonus tiles now and place them face up in your action area next to your action slots. ( See page 20 for details on the bonus tiles. ) First, rem", "headingPath": "b) Return the bonus markers to the players (including possible bonus tiles) · c) Fill up the card display", "sharpsignalDocId": 564}, {"page": 6, "score": 0.030303, "snippet": "7 Place the CrypCoin (of values 1 and 5) as a supply next to the game board. This supply is called the bank . 5 9 6 Place the 4 bonus tiles face up below the right side of the game board.", "headingPath": "Folding boxes", "sharpsignalDocId": 564}, {"page": 31, "score": 0.029851, "snippet": "The game is played according to the usual Belt side rules with one addition: The card in the game board's center poses a threat. This threat entails a specific consequence that affects all players at the end of the game. However, in order to negate that consequence for all players, the threat can be", "headingPath": "Playing the game · End of the game", "sharpsignalDocId": 564}, {"page": 19, "score": 0.029412, "snippet": "After the Action phase of round 7, the game ends. Now, the Final scoring phase takes place as follows: Each player: First, pick up all cards of your resting decks and add them to your hand. Then find from your hand all cards that show an additional company share on their right side. Sort these by co", "headingPath": "End of the game", "sharpsignalDocId": 564}]
citations (raw): []
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 564 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 564 boosted
answered-before recall: no past answered ruling for this game matched closely enough
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 08:06

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 Skymines — Rulebook (corpus doc 564)	Folding boxes	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 Skymines — Rulebook (corpus doc 564)	1) Planning phase · a) Place cards face down in your action area · b) Flip cards face up · 2) Action phase	p.10	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 Skymines — Rulebook (corpus doc 564)	6) Drop out of Action phase · 3) Preparation phase for the next round · a) Flip the next special research plan face up	p.18	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 Skymines — Rulebook (corpus doc 564)		p.7	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 Skymines — Rulebook (corpus doc 564)	b) Return the bonus markers to the players (including possible bonus tiles) · c) Fill up the card display	p.19	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 Skymines — Rulebook (corpus doc 564)	Folding boxes	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))	187
#7	RULEBOOK Skymines — Rulebook (corpus doc 564)	Playing the game · End of the game	p.31	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 Skymines — Rulebook (corpus doc 564)	End of the game	p.19	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

generation — timing and the path taken

timing split: retrieval 263 ms · first delta 9129 ms · total 209733 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 200492 ms · retrieval 263 ms · ask 8968 ms · gateway work 9241 ms · total 209733 ms
tokens in (the prompt the answerer read): 4137
tokens out (what the answerer generated): 9
tok/sec: 142.9 tok/sec — 9 output tokens in 0.063 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 11s 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: ABSTAINED — Abstained — no grounded answer; closest passages below
abstain rationale: I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped

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 496), 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.