Ruling — Boonlake

You asked

How do we agree beforehand on the worth of each buried find?

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

Asked with: Boonlakebg-343905-en-1e · Boonlake: Artifactsbg-398052-en-1e

I looked through Boonlake'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 Boonlake — Rulebook · p.8 · Explore

When you explore, you add new building tiles to the gameboard. In order to explore, you proceed as follows: Reveal a gray building tile from the mound. Put the building tile on an unoccupied space on the gameboard that is adjacent to another building tile or is connected via a bridge with an already

RULEBOOK Boonlake — Rulebook · p.11 · Region scoring

First, you may either play a to get 2 coins. card, or discard one Then you choose one of the 4 regions (Boonlake, Unknown, New Hope, or Southern) whose reward on the region label has not yet been covered with a region marker. Put a region marker on the reward of the chosen region and gain the reward

RULEBOOK Boonlake — Rulebook · p.17 · Building a structure

If the Wise Eminence is allowed to build a structure, you check how many of their houses are on the gameboard. If there is no more than 1 house, they choose a location with an unoccupied building site (as described above) and place a house from their board there (that means the Wise Eminence places

RULEBOOK Boonlake — Rulebook · p.22 · Scoring tiles

In addition, the number of adjacent presences required decreases by 1 (i.e., you need only 2 adjacent presences). These effects are cumulative with other effects that facilitate this condition. When you place a building tile (which can also be a cattle pasture) on the gameboard, you may move this le

RULEBOOK Boonlake — Rulebook · p.14 · interim Scoring · Final Scoring · Leftover coins and cards don't get you any victory points.

Example: For their marker on the coin track and the one on the card track, Tino gets 5 coins and 1 victory point, plus 3 cards. For their player board, they get 5 coins and 4 victory points (and, possibly, additional victory points for settlements adjacent to the cattle they ha placed). Move all the

🔧 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 109 ms · ask 3611 ms · total 3722 ms

single-flight (PR-5)

queued 0 ms · generation 3722 ms

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

[{"page": 8, "score": 0.032787, "snippet": "When you explore, you add new building tiles to the gameboard. In order to explore, you proceed as follows: Reveal a gray building tile from the mound. Put the building tile on an unoccupied space on the gameboard that is adjacent to another building tile or is connected via a bridge with an already", "headingPath": "Explore", "sharpsignalDocId": 491}, {"page": 11, "score": 0.031754, "snippet": "First, you may either play a to get 2 coins. card, or discard one Then you choose one of the 4 regions (Boonlake, Unknown, New Hope, or Southern) whose reward on the region label has not yet been covered with a region marker. Put a region marker on the reward of the chosen region and gain the reward", "headingPath": "Region scoring", "sharpsignalDocId": 491}, {"page": 17, "score": 0.031258, "snippet": "If the Wise Eminence is allowed to build a structure, you check how many of their houses are on the gameboard. If there is no more than 1 house, they choose a location with an unoccupied building site (as described above) and place a house from their board there (that means the Wise Eminence places ", "headingPath": "Building a structure", "sharpsignalDocId": 491}, {"page": 22, "score": 0.02971, "snippet": "In addition, the number of adjacent presences required decreases by 1 (i.e., you need only 2 adjacent presences). These effects are cumulative with other effects that facilitate this condition. When you place a building tile (which can also be a cattle pasture) on the gameboard, you may move this le", "headingPath": "Scoring tiles", "sharpsignalDocId": 491}, {"page": 14, "score": 0.029274, "snippet": "Example: For their marker on the coin track and the one on the card track, Tino gets 5 coins and 1 victory point, plus 3 cards. For their player board, they get 5 coins and 4 victory points (and, possibly, additional victory points for settlements adjacent to the cattle they ha placed). Move all the", "headingPath": "interim Scoring · Final Scoring · Leftover coins and cards don't get you any victory points.", "sharpsignalDocId": 491}, {"page": 18, "score": 0.02885, "snippet": "The final scoring takes place at the end of the second round, as usual. Since the Wise Eminence begins the game, you carry out the last action. During the final scoring, the Wise Eminence gets their income one more time. (Instead, you can double the Wise Eminence's income during the fourth interim s", "headingPath": "Final Scoring", "sharpsignalDocId": 491}, {"page": 21, "score": 0.028439, "snippet": "Every time you would be allowed to play a card (or discard it to get 2 coins) and voluntarily forgo this, you get 1 coin for each production site you have built on your player board. Production sites showing 2 resources count double. You may use this lever also if you forgo playing a card at the 'Bu", "headingPath": "Lever effects", "sharpsignalDocId": 491}, {"page": 16, "score": 0.028039, "snippet": "Each number stands for a specific space on the gameboard. If the Wise Eminence can carry out the effect at their preferred location, they do so. Otherwise, they take the next higher space. If carrying out the effect isn't possible here either, they take the next higher space again, and so on. If the", "headingPath": "Choosing a location", "sharpsignalDocId": 491}]

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 491 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 491 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 13, 2026 18:09

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 Boonlake — Rulebook (corpus doc 491)	Explore	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 Boonlake — Rulebook (corpus doc 491)	Region scoring	p.11	0.031754 (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 Boonlake — Rulebook (corpus doc 491)	Building a structure	p.17	0.031258 (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 Boonlake — Rulebook (corpus doc 491)	Scoring tiles	p.22	0.02971 (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 Boonlake — Rulebook (corpus doc 491)	interim Scoring · Final Scoring · Leftover coins and cards don't get you any victory points.	p.14	0.029274 (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 Boonlake — Rulebook (corpus doc 491)	Final Scoring	p.18	0.02885 (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 Boonlake — Rulebook (corpus doc 491)	Lever effects	p.21	0.028439 (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 Boonlake — Rulebook (corpus doc 491)	Choosing a location	p.16	0.028039 (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 57 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 — 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 Boonlake: Artifacts — Rulebook (corpus doc 925)	One-time effects · Immediate effects	p.10	#9	0.016129 (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 re-ranker chose it
#2	RULEBOOK Boonlake — Rulebook (corpus doc 491)	Region scoring	p.11	#2	0.031754 (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
#3	RULEBOOK Boonlake: Artifacts — Rulebook (corpus doc 925)	Changes in the Solo Mode	p.9	#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 Boonlake — Rulebook (corpus doc 491)	Final Scoring	p.18	#6	0.02885 (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 Boonlake — Rulebook (corpus doc 491)	Interim Scoring & Final Scoring	p.13	#45	0.009524 (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 Boonlake: Artifacts — Rulebook (corpus doc 925)		p.7	#12	0.014925 (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
#7	RULEBOOK Boonlake — Rulebook (corpus doc 491)	Placing cattle · Movement of the Ship · Interim Scoring	p.18	#17	0.012987 (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
#8	RULEBOOK Boonlake: Artifacts — Rulebook (corpus doc 925)	The Shipyard · MasterING of sCORING tILES · 1st interim scoring:	p.9	#38	0.010204 (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 109 ms · first delta 3368 ms · total 3722 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 109 ms · ask 3611 ms · gateway work 3722 ms · total 3722 ms
tokens in (the prompt the answerer read): 2654
tokens out (what the answerer generated): 9
tok/sec: 33.1 tok/sec — 9 output tokens in 0.272 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 44s 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 422), 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.