Ruling — Sea Salt & Paper

← Sea Salt & Paper

You asked

How do I play?

Answered counted as answered

Asked with: Sea Salt & Paperbg-367220-en-1e

1. Shuffle the cards into a deck and place them facedown within easy reach.[1]

2. Choose the first player at random.[1]

3. Reveal the first two cards and place them faceup next to the deck to form two discard piles.[1]

4. Players take turns playing clockwise.[1]

5. During a turn, a player must add a card to their hand in one of two ways: take the first two cards from the deck, add one to their hand and discard the second faceup on a discard pile of their choice, OR take the card on top of one of the two discard piles.[1]

6. A player may play Duo cards in pairs by placing them faceup in front of them to trigger their effect.[1]

7. A player can trigger more than one effect during their turn.[1]

8. If a player has reached 7 points or more by counting the points on their cards (both in hand and in front of them), they can decide to end the round.[1]

9. If the player ends the round, they reveal their hand and announce "STOP" (if they do not want to take a risk) or "LAST CHANCE" (if they are willing to take the bet of having the most points).[2]

10. If "STOP" is announced, all players reveal their hands and immediately score points.[2]

11. If "LAST CHANCE" is announced, other players each take a final turn (taking a card and playing cards) and reveal their hands; then all players count points.[2]

12. If the deck is empty at the end of a player's turn, the round ends immediately without scoring.[2]

13. If no one has reached or exceeded the required victory points, a new round starts by shuffling all cards and reforming the deck and discard piles, with the player to the left of the previous round's ender starting.[2]

14. The game ends as soon as one player reaches or exceeds the required victory points (40 points for 2 players, 35 points for 3 players, or 30 points for 4 players).[2]

15. A player wins immediately if they place 4 mermaid cards.[3][2]

[1] RULEBOOK Sea Salt & Paper — Rulebook · p.1 · COMPONENTS · GAME SETUP · GAME OBJECTIVE · GAME TURN · 2. Duo cards can be played · 3. The round can be ended

[2] RULEBOOK Sea Salt & Paper — Rulebook · p.1 · END OF THE ROUND · PLAYER 1 = 7 pts · PLAYER 2 = 4 pts · END OF GAME · CARD DETAILS

[3] RULEBOOK Sea Salt & Paper — Rulebook · p.1 · 1 point for each pair of · Mermaid cards · Collector cards · Point Multiplier cards

That settles it — whose turn was it?

🔧 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 87 ms · ask 5003 ms · total 15885 ms
single-flight (PR-5): queued 10793 ms · generation 5092 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 1, "score": 0.04918, "snippet": "58 cards, 6 game aids, a rulebook. Keep the game aids available. Shuffle the cards into a deck, placed facedown within easy reach. Choose the first player at random. Reveal the first two cards and place them faceup next to the deck to form two discard piles. The game is played in rounds until one pl", "headingPath": "COMPONENTS · GAME SETUP · GAME OBJECTIVE · GAME TURN · 2. Duo cards can be played · 3. The round can be ended", "sharpsignalDocId": 227}, {"page": 1, "score": 0.048387, "snippet": "When a player triggers the end of the round, they reveal their hand of cards and must announce STOP or LAST CHANCE. They say STOP if they do not want to take a risk. All players reveal their hands and immediately score the points on their cards (in their hand and in front of them). They say LAST CHA", "headingPath": "END OF THE ROUND · PLAYER 1 = 7 pts · PLAYER 2 = 4 pts · END OF GAME · CARD DETAILS", "sharpsignalDocId": 227}, {"page": 1, "score": 0.047123, "snippet": "crab cards. Effect: The player chooses a discard pile, consults it without shuffling it, and chooses a card from it to add to their hand. They do not have to show it to the other players. 1 point for each pair of boat cards. Effect: The player immediately takes another turn. 1 point for each pair of", "headingPath": "1 point for each pair of · Mermaid cards · Collector cards · Point Multiplier cards", "sharpsignalDocId": 227}, {"page": 1, "score": 0.031746, "snippet": "Game designers: Bruno Cathala & Théo Rivière ColorADD is a universal, inclusive and nondiscriminative language that enables the colorblind to identify colors. Used under license by Bombyx. Photographer: Pierre-Yves Gallard Creation and production of the origami: Lucien Derainne & Pierre-Yves Gallard", "headingPath": "CREDITS", "sharpsignalDocId": 227}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 1, "quote": null, "headingPath": "COMPONENTS · GAME SETUP · GAME OBJECTIVE · GAME TURN · 2. Duo cards can be played · 3. The round can be ended", "sharpsignalDocId": 227}, {"page": 1, "quote": null, "headingPath": "END OF THE ROUND · PLAYER 1 = 7 pts · PLAYER 2 = 4 pts · END OF GAME · CARD DETAILS", "sharpsignalDocId": 227}, {"page": 1, "quote": null, "headingPath": "1 point for each pair of · Mermaid cards · Collector cards · Point Multiplier cards", "sharpsignalDocId": 227}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 227 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 227 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 0.90557 of 1525 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Aug 25, 2026 16:59 UTC

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 Sea Salt & Paper — Rulebook (corpus doc 227)	COMPONENTS · GAME SETUP · GAME OBJECTIVE · GAME TURN · 2. Duo cards can be played · 3. The round can be ended	p.1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	END OF THE ROUND · PLAYER 1 = 7 pts · PLAYER 2 = 4 pts · END OF GAME · CARD DETAILS	p.1	0.048387 (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 Sea Salt & Paper — Rulebook (corpus doc 227)	1 point for each pair of · Mermaid cards · Collector cards · Point Multiplier cards	p.1	0.047123 (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 Sea Salt & Paper — Rulebook (corpus doc 227)	CREDITS	p.1	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

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 4 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 Sea Salt & Paper — Rulebook (corpus doc 227)	COMPONENTS · GAME SETUP · GAME OBJECTIVE · GAME TURN · 2. Duo cards can be played · 3. The round can be ended	p.1	#1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	1 point for each pair of · Mermaid cards · Collector cards · Point Multiplier cards	p.1	#3	0.047123 (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 + full-text + the doc-priority boost arm	the re-ranker chose it
#3	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	CREDITS	p.1	#4	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
#4	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	END OF THE ROUND · PLAYER 1 = 7 pts · PLAYER 2 = 4 pts · END OF GAME · CARD DETAILS	p.1	#2	0.048387 (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 + full-text + the doc-priority boost arm	the re-ranker chose it

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	COMPONENTS · GAME SETUP · GAME OBJECTIVE · GAME TURN · 2. Duo cards can be played · 3. The round can be ended	p.1	no quote on the wire
[2]	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	END OF THE ROUND · PLAYER 1 = 7 pts · PLAYER 2 = 4 pts · END OF GAME · CARD DETAILS	p.1	no quote on the wire
[3]	RULEBOOK Sea Salt & Paper — Rulebook (corpus doc 227)	1 point for each pair of · Mermaid cards · Collector cards · Point Multiplier cards	p.1	no quote on the wire

generation — timing and the path taken

timing split: retrieval 87 ms · first delta 1439 ms · total 15885 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 10793 ms · retrieval 87 ms · ask 5003 ms · gateway work 5092 ms · total 15885 ms
tokens in (the prompt the answerer read): 1837
tokens out (what the answerer generated): 485
tok/sec: 133.9 tok/sec — 485 output tokens in 3.623 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 51s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 1s ago)
answerer node (the seat proxy's own header — this probe, not this ask): node1
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 153), 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.