Ruling — Finspan

You asked

What breaks a tie?

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

Asked with: Finspanbg-436126-en-1e

I looked through Finspan's rulebook and couldn't find a solid answer to that one — and I'd rather tell you so than guess at your table. Try asking it another way, or ask me about setup, turns, or how the game ends: those I know cold.

The closest rulebook passages are below — check them before ruling.

RULEBOOK Finspan — Rulebook · p.9 · IMPORTANT NOTES SCHOOL TOKENS

A school forms whenever 3 or more young share the same slot in your ocean. When this occurs, immediately return 3 young from that slot to the supply and replace them with 1 school token (shown as this icon in the game: ). At the end of weeks 1 through 3: a. Score points for this week's achievement.

RULEBOOK Finspan — Rulebook · p.8 · END OF WEEK

The week ends after each player has taken 6 turns (used all their divers). At the end of weeks 1, 2, and 3, players simultaneously perform each step in order: Gain points based on this week's achievement (points for each instance of the item), noting the points on the scorepad. EXAMPLE: At the end o

RULEBOOK Finspan — Rulebook · p.8 · END OF GAME

The game ends after the completion of week 4. After activating in any order 'GAME END' abilities on fish in oceans that don't award end-game points (including fish that enter play during this step), players simultaneously perform each step in order: GAME END (YEOW): Gain any 'GAME END' points on fi

RULEBOOK Finspan — Rulebook · p.1 · OVERVIEW AND GOAL

In Finspan, the fish you discover over 4 weeks will generate a series of benefits as you dive deeper into the ocean. Each dive site specializes in a key aspect of expanding your research: Grow your collection of fish. Discover freshly laid eggs. Hatch eggs into young, and nurture the young into scho

RULEBOOK Finspan — Rulebook · p.7 · SAMPLE DIVE TURN

You place a diver at the top of the middle dive site to select it as your dive location. Starting at the top and moving down the column, you evaluate each zone's dive site bonus and activate the fish in that column. 1 Gain the topmost dive site bonus, since you have at least 1 fish in the Sunlight Z

Strategy guides → — community tips, kept separate from rulings

🔧 debug — where this ruling came from

outcome

ABSTAINED — Abstained — no grounded answer; closest passages below

warm abstain

this ruling — W1 — generic warm abstain · receipt: none (generic)

corpus profile

live,vps

answerer pin (deploy-frozen, attribution only)

gemma4:26b think:false 5571076f3d70

timings

search 72 ms · ask 1904 ms · total 1978 ms

single-flight (PR-5)

queued 0 ms · generation 1978 ms

retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read

[{"page": 9, "score": 0.032787, "snippet": "A school forms whenever 3 or more young share the same slot in your ocean. When this occurs, immediately return 3 young from that slot to the supply and replace them with 1 school token (shown as this icon in the game: ). At the end of weeks 1 through 3: a. Score points for this week's achievement. ", "headingPath": "IMPORTANT NOTES SCHOOL TOKENS", "sharpsignalDocId": 54}, {"page": 8, "score": 0.032258, "snippet": "The week ends after each player has taken 6 turns (used all their divers). At the end of weeks 1, 2, and 3, players simultaneously perform each step in order: Gain points based on this week's achievement (points for each instance of the item), noting the points on the scorepad. EXAMPLE: At the end o", "headingPath": "END OF WEEK", "sharpsignalDocId": 54}, {"page": 8, "score": 0.031746, "snippet": "The game ends after the completion of week 4. After activating in any order 'GAME END' abilities on fish in oceans that don't award end-game points (including fish that enter play during this step), players simultaneously perform each step in order: GAME END (YEOW): Gain any 'GAME END' points on fi", "headingPath": "END OF GAME", "sharpsignalDocId": 54}, {"page": 1, "score": 0.03125, "snippet": "In Finspan, the fish you discover over 4 weeks will generate a series of benefits as you dive deeper into the ocean. Each dive site specializes in a key aspect of expanding your research: Grow your collection of fish. Discover freshly laid eggs. Hatch eggs into young, and nurture the young into scho", "headingPath": "OVERVIEW AND GOAL", "sharpsignalDocId": 54}, {"page": 7, "score": 0.030769, "snippet": "You place a diver at the top of the middle dive site to select it as your dive location. Starting at the top and moving down the column, you evaluate each zone's dive site bonus and activate the fish in that column. 1 Gain the topmost dive site bonus, since you have at least 1 fish in the Sunlight Z", "headingPath": "SAMPLE DIVE TURN", "sharpsignalDocId": 54}, {"page": 12, "score": 0.030303, "snippet": "Play a fish from your hand on an empty or occupied slot on your ocean mat after paying its cost. As a cost: Discard a fish card from your hand. As a benefit: Draw a fish card from the deck. As a cost: Discard an egg from a fish. As a benefit: Put an egg on a fish (in your ocean) that doesn't already", "headingPath": "ABILITY ICONOGRAPHY", "sharpsignalDocId": 54}, {"page": 9, "score": 0.029851, "snippet": "Whenever you pay cards from your hand as a cost to play a fish, place those cards face up into your personal discard pile. (There is no shared discard pile.) The main function of your discard pile is for the benefit, which allows you to gain any card from your discard pile to your hand. Turn your di", "headingPath": "PERSONAL DISCARD PILES", "sharpsignalDocId": 54}, {"page": 9, "score": 0.029412, "snippet": "The vertical area on the right side of fish cards shows the fish's ability. Benefits from fish abilities are optional for each affected player. Gaining all or part of a benefit is allowed. WHEN PLAYED: Gain this benefit when you play a fish (after all other 'play a fish' steps). IF ACTIVATED: Gain t", "headingPath": "FISH ABILITIES", "sharpsignalDocId": 54}]

citations (raw) — what the answer cited, chosen from a retrieval this page cannot show

[]

boost provenance — errata + base rulebook (E2/E3)

no registered errata card matched this query; base rulebook doc 54 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 54 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 14, 2026 11:32

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 Finspan — Rulebook (corpus doc 54)	IMPORTANT NOTES SCHOOL TOKENS	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 Finspan — Rulebook (corpus doc 54)	END OF WEEK	p.8	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 Finspan — Rulebook (corpus doc 54)	END OF GAME	p.8	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 Finspan — Rulebook (corpus doc 54)	OVERVIEW AND GOAL	p.1	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 Finspan — Rulebook (corpus doc 54)	SAMPLE DIVE TURN	p.7	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 Finspan — Rulebook (corpus doc 54)	ABILITY ICONOGRAPHY	p.12	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 Finspan — Rulebook (corpus doc 54)	PERSONAL DISCARD PILES	p.9	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 Finspan — Rulebook (corpus doc 54)	FISH ABILITIES	p.9	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 32 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 Finspan — Rulebook (corpus doc 54)	IMPORTANT NOTES SCHOOL TOKENS	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
#2	RULEBOOK Finspan — Rulebook (corpus doc 54)	END OF GAME	p.9	#25	0.011765 (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 Finspan — Rulebook (corpus doc 54)	Photographers:	p.11	#31	0.010989 (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
#4	RULEBOOK Finspan — Rulebook (corpus doc 54)	DIVE	p.6	#13	0.013699 (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
#5	RULEBOOK Finspan — Rulebook (corpus doc 54)	DIVE	p.6	#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
#6	RULEBOOK Finspan — Rulebook (corpus doc 54)	END OF WEEK	p.8	#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
#7	RULEBOOK Finspan — Rulebook (corpus doc 54)	PERSONAL DISCARD PILES	p.9	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Finspan — Rulebook (corpus doc 54)	PLAYER SETUP	p.3	#32	0.01087 (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

generation — timing and the path taken

timing split: retrieval 72 ms · first delta 1892 ms · total 1978 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 72 ms · ask 1904 ms · gateway work 1978 ms · total 1978 ms
tokens in (the prompt the answerer read): 2150
tokens out (what the answerer generated): 9
tok/sec: 200.0 tok/sec — 9 output tokens in 0.045 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 57s 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 5), 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.