Ruling — Archipelago

You asked

How do I play?

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

Asked with: Archipelagobg-105551-en-1e

I looked through Archipelago'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 Archipelago — Rulebook · p.5 · neg27i$7ing

D iplomacy, negotiations, promises, agreements, understandings, aOOLancese anG tUeacKeU\ aUe commonpOace activities in Archipelago. There can never be too much of it! This game is after all only semi-cooperative e Negotiations and exchanges are authorized with the following constraints: F Players ca

RULEBOOK Archipelago — Rulebook · p.8 · e;3l2rer 72.en &2n9er6i2n

A n explorer token can be turned into a single resource cube of any type during the resolution of a crisis. The explorer token is then removed from the game (do not put it back on the explorer token piles). An explorer token can only be converted during a crisis or when a player performs an action r

RULEBOOK Archipelago — Rulebook · p.4 · 8rn 0 'i6&29ering 7+e $r&+i3el$g2 · Region: one of the two sides of a single hexagon

F Randomly decide the order of play for this turn. Each player places his order marker on the evolution track in the icon corresponding to his position in the order of play. Shuffle the 24 region hexagons and deal each player 3 hexagons (providing 6 different region choices). F Initial exploration:

RULEBOOK Archipelago — Rulebook · p.13

T he 1ƒ coins on the port and market zones of the action wheel go to the bank. A t any given time, the evolution track contains 5 cards representing the current set of evolution cards available for purchase. Starting with the first player and continuing in the order of play, each player must either:

RULEBOOK Archipelago — Rulebook · p.3 · 9.

Each player chooses a color, takes the player screen aid, 1 ship, 2 citizens, 3 action discs (AD), and the order marker of his color. He places the ship on the open sea hexagon, being careful not to cover any fish icons, and places the other pieces in front of his screen, visible to all. He also rec

🔧 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 90 ms · ask 4340 ms · total 4433 ms

single-flight (PR-5)

queued 0 ms · generation 4433 ms

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

[{"page": 5, "score": 0.047875, "snippet": "D iplomacy, negotiations, promises, agreements, understandings, aOOLancese anG tUeacKeU\\ aUe commonpOace activities in Archipelago. There can never be too much of it! This game is after all only semi-cooperative e Negotiations and exchanges are authorized with the following constraints: F Players ca", "headingPath": "neg27i$7ing", "sharpsignalDocId": 697}, {"page": 8, "score": 0.045695, "snippet": "A n explorer token can be turned into a single resource cube of any type during the resolution of a crisis. The explorer token is then removed from the game (do not put it back on the explorer token piles). An explorer token can only be converted during a crisis or when a player performs an action r", "headingPath": "e;3l2rer 72.en &2n9er6i2n", "sharpsignalDocId": 697}, {"page": 4, "score": 0.043905, "snippet": "F Randomly decide the order of play for this turn. Each player places his order marker on the evolution track in the icon corresponding to his position in the order of play. Shuffle the 24 region hexagons and deal each player 3 hexagons (providing 6 different region choices). F Initial exploration: ", "headingPath": "8rn 0 'i6&29ering 7+e $r&+i3el$g2 · Region: one of the two sides of a single hexagon", "sharpsignalDocId": 697}, {"page": 13, "score": 0.043817, "snippet": "T he 1ƒ coins on the port and market zones of the action wheel go to the bank. A t any given time, the evolution track contains 5 cards representing the current set of evolution cards available for purchase. Starting with the first player and continuing in the order of play, each player must either:", "headingPath": "", "sharpsignalDocId": 697}, {"page": 3, "score": 0.032787, "snippet": "Each player chooses a color, takes the player screen aid, 1 ship, 2 citizens, 3 action discs (AD), and the order marker of his color. He places the ship on the open sea hexagon, being careful not to cover any fish icons, and places the other pieces in front of his screen, visible to all. He also rec", "headingPath": "9.", "sharpsignalDocId": 697}, {"page": 12, "score": 0.032258, "snippet": "An active, non-engaged citizen can build a market, occupy it, and operate it. Each market gives its controlling player the opportunity to perform two transactions on the domestic market (see Transaction) without using action discs. T o control a market, a player must either occupy it with an active ", "headingPath": "Markets", "sharpsignalDocId": 697}, {"page": 12, "score": 0.03125, "snippet": "An active, non-engaged citizen or ship can build a port, occupy it, and operate it. Each port gives its controlling player the opportunity to perform two transactions on the export market (see Transaction) without using action discs. T o control a port, the player must either occupy it with an activ", "headingPath": "Ports · Each player can use one port or market during each of his rounds. To do so, he · Towns", "sharpsignalDocId": 697}, {"page": 17, "score": 0.029851, "snippet": "T Ke GestUo\\eG sKLp Joes EacN to tKe pOa\\eUls reserve and can be rebuilt at a later time. Move the rebellion marker down 1 for each temple in the archipelago. The Pope earns its controller 1 VP at the end of the game. Spend 5 stone resources and 2 action discs. Move the rebellion marker up 2. The Py", "headingPath": "Pirate · Pope · Pyramid · Recruiter · Thief", "sharpsignalDocId": 697}]

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

base rulebook doc 697 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 15, 2026 12:04

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 Archipelago — Rulebook (corpus doc 697)	neg27i$7ing	p.5	0.047875 (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 Archipelago — Rulebook (corpus doc 697)	e;3l2rer 72.en &2n9er6i2n	p.8	0.045695 (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 Archipelago — Rulebook (corpus doc 697)	8rn 0 'i6&29ering 7+e $r&+i3el$g2 · Region: one of the two sides of a single hexagon	p.4	0.043905 (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 Archipelago — Rulebook (corpus doc 697)		p.13	0.043817 (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 Archipelago — Rulebook (corpus doc 697)	9.	p.3	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
#6	RULEBOOK Archipelago — Rulebook (corpus doc 697)	Markets	p.12	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
#7	RULEBOOK Archipelago — Rulebook (corpus doc 697)	Ports · Each player can use one port or market during each of his rounds. To do so, he · Towns	p.12	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
#8	RULEBOOK Archipelago — Rulebook (corpus doc 697)	Pirate · Pope · Pyramid · Recruiter · Thief	p.17	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

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 54 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 Archipelago — Rulebook (corpus doc 697)	9.	p.3	#5	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 Archipelago — Rulebook (corpus doc 697)	5 sets of player pieces	p.3	#27	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
#3	RULEBOOK Archipelago — Rulebook (corpus doc 697)	each player must either:	p.13	#13	0.027047 (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 re-ranker chose it
#4	RULEBOOK Archipelago — Rulebook (corpus doc 697)	Markets	p.12	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Archipelago — Rulebook (corpus doc 697)	Ports · Each player can use one port or market during each of his rounds. To do so, he · Towns	p.12	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Archipelago — Rulebook (corpus doc 697)	5 sets of player pieces	p.3	#36	0.011236 (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 Archipelago — Rulebook (corpus doc 697)	neg27i$7ing	p.5	#1	0.047875 (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
#8	RULEBOOK Archipelago — Rulebook (corpus doc 697)	8rn 0 'i6&29ering 7+e $r&+i3el$g2 · Region: one of the two sides of a single hexagon	p.4	#3	0.043905 (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

generation — timing and the path taken

timing split: retrieval 90 ms · first delta 4333 ms · total 4433 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 90 ms · ask 4340 ms · gateway work 4433 ms · total 4433 ms
tokens in (the prompt the answerer read): 3295
tokens out (what the answerer generated): 9
tok/sec: 204.5 tok/sec — 9 output tokens in 0.044 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 35s 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 630), 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.