Ruling — The Lost Expedition

You asked

How do I play?

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

Asked with: The Lost Expeditionbg-216459-en-1e

I looked through The Lost Expedition'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 The Lost Expedition — Rulebook · p.9 · MORNING · EVENING

Starting with the leader and going clockwise, each player plays one card at a time face up into the middle of the table until each player has played two cards. The cards should be in a single row visible to everybody. This forms the path the explorers are taking for this hike. In a two-player game,

RULEBOOK The Lost Expedition — Rulebook · p.11 · EVENING · GAME END

In the Evening, cards will remain in the order in which they are played; however, you may now add to either the start or the end of the path. Begin by playing one card from your hand to form the path. You may now either draw a card from the deck or play a card from your hand, and place it to the lef

RULEBOOK The Lost Expedition — Rulebook · p.12 · TWO PATHS

Each round takes the same format of Morning and Evening, and ends the same way. However, for both Morning and Evening each player has a choice of two paths to add cards to: one path above the row of expedition cards, and one path below it. There is no limit to how many or how few cards can be added

RULEBOOK The Lost Expedition — Rulebook · p.10 · ENDING THE ROUND · ENDING THE GAME · SOLO RULES · SETUP · MORNING

At the end of every round pass the leader token to the next player clockwise, then each player draws four cards from the adventure deck. If the adventure deck is empty, the players immediately lose one Food, and then shuffl e the discards to form a new deck. If the deck is empty for the second time

RULEBOOK The Lost Expedition — Rulebook · p.8 · SETUP · GOAL

Take one explorer of each Expertise and put them on the table to form your team area. It doesn't matter how many players are playing, you always use exactly three explorers. Take three Ammunition tokens and four Food tokens from the supply and add them to your team area. Shuffl e the adventure cards

🔧 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 169 ms · ask 1570 ms · total 1741 ms

single-flight (PR-5)

queued 0 ms · generation 1741 ms

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

[{"page": 9, "score": 0.04918, "snippet": "Starting with the leader and going clockwise, each player plays one card at a time face up into the middle of the table until each player has played two cards. The cards should be in a single row visible to everybody. This forms the path the explorers are taking for this hike. In a two-player game, ", "headingPath": "MORNING · EVENING", "sharpsignalDocId": 1000}, {"page": 11, "score": 0.048131, "snippet": "In the Evening, cards will remain in the order in which they are played; however, you may now add to either the start or the end of the path. Begin by playing one card from your hand to form the path. You may now either draw a card from the deck or play a card from your hand, and place it to the lef", "headingPath": "EVENING · GAME END", "sharpsignalDocId": 1000}, {"page": 12, "score": 0.047131, "snippet": "Each round takes the same format of Morning and Evening, and ends the same way. However, for both Morning and Evening each player has a choice of two paths to add cards to: one path above the row of expedition cards, and one path below it. There is no limit to how many or how few cards can be added ", "headingPath": "TWO PATHS", "sharpsignalDocId": 1000}, {"page": 10, "score": 0.046875, "snippet": "At the end of every round pass the leader token to the next player clockwise, then each player draws four cards from the adventure deck. If the adventure deck is empty, the players immediately lose one Food, and then shuffl e the discards to form a new deck. If the deck is empty for the second time ", "headingPath": "ENDING THE ROUND · ENDING THE GAME · SOLO RULES · SETUP · MORNING", "sharpsignalDocId": 1000}, {"page": 8, "score": 0.046432, "snippet": "Take one explorer of each Expertise and put them on the table to form your team area. It doesn't matter how many players are playing, you always use exactly three explorers. Take three Ammunition tokens and four Food tokens from the supply and add them to your team area. Shuffl e the adventure cards", "headingPath": "SETUP · GOAL", "sharpsignalDocId": 1000}, {"page": 4, "score": 0.044337, "snippet": "In The Lost Expedition you will be leading a team of three explorers to follow the path of Percy Fawcett on the road to El Dorado. T o win the game, simply get to the lost city with one of those explorers still alive! You'll have to make the best use of your Expertise and Resources to survive as you", "headingPath": "GAME OVERVIEW · THE ADVENTURE CARDS", "sharpsignalDocId": 1000}, {"page": 16, "score": 0.030769, "snippet": "You must trigger every yellow box, and any number of blue boxes, but only ever one red box. Spend one Food at the end of every Morning and Evening. If you run out of Food, spend a Health from any explorer every time you would spend a Food. If you run out of Expertise, take one Health token from the ", "headingPath": "RULES TO REMEMBER", "sharpsignalDocId": 1000}, {"page": 12, "score": 0.029851, "snippet": "In this version two players will compete to be the fi rst to get their team of explorers to the lost city. T o win, you will need to beat the other player in a race to the city, or to survive longest. These rules are broadly similar to the cooperative version, and those rules should be read fi rst. ", "headingPath": "HEAD-TO-HEAD RULES · SETUP", "sharpsignalDocId": 1000}]

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 1000 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 1000 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 recorded

Sep 5, 2026 14:24 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 The Lost Expedition — Rulebook (corpus doc 1000)	MORNING · EVENING	p.9	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK The Lost Expedition — Rulebook (corpus doc 1000)	EVENING · GAME END	p.11	0.048131 (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 The Lost Expedition — Rulebook (corpus doc 1000)	TWO PATHS	p.12	0.047131 (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 The Lost Expedition — Rulebook (corpus doc 1000)	ENDING THE ROUND · ENDING THE GAME · SOLO RULES · SETUP · MORNING	p.10	0.046875 (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 The Lost Expedition — Rulebook (corpus doc 1000)	SETUP · GOAL	p.8	0.046432 (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 The Lost Expedition — Rulebook (corpus doc 1000)	GAME OVERVIEW · THE ADVENTURE CARDS	p.4	0.044337 (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 The Lost Expedition — Rulebook (corpus doc 1000)	RULES TO REMEMBER	p.16	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
#8	RULEBOOK The Lost Expedition — Rulebook (corpus doc 1000)	HEAD-TO-HEAD RULES · SETUP	p.12	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 18 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 The Lost Expedition — Rulebook (corpus doc 1000)	EVENING · GAME END	p.11	#2	0.048131 (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
#2	RULEBOOK The Lost Expedition — Rulebook (corpus doc 1000)	SETUP · GOAL	p.8	#5	0.046432 (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 The Lost Expedition — Rulebook (corpus doc 1000)	TWO PATHS	p.13	#10	0.014493 (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 The Lost Expedition — Rulebook (corpus doc 1000)	HEAD-TO-HEAD RULES · SETUP	p.12	#8	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
#5	RULEBOOK The Lost Expedition — Rulebook (corpus doc 1000)	CLARIFICATIONS	p.14	#9	0.028485 (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
#6	RULEBOOK The Lost Expedition — Rulebook (corpus doc 1000)	ENDING THE ROUND · ENDING THE GAME · SOLO RULES · SETUP · MORNING	p.10	#4	0.046875 (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
#7	RULEBOOK The Lost Expedition — Rulebook (corpus doc 1000)	TWO PATHS	p.12	#3	0.047131 (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 The Lost Expedition — Rulebook (corpus doc 1000)	MORNING · EVENING	p.9	#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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars

generation — timing and the path taken

timing split: retrieval 169 ms · first delta 1639 ms · total 1741 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 169 ms · ask 1570 ms · gateway work 1741 ms · total 1741 ms
tokens in (the prompt the answerer read): 2910
tokens out (what the answerer generated): 9
tok/sec: 180.0 tok/sec — 9 output tokens in 0.050 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 28s ago)
answerer host (measured by rulesage): reachable (for 23h, checked 9s 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: ABSTAINED — Abstained — no grounded answer; closest passages below
abstain rationale: I don't have enough information.
BOILERPLATE, not reasoning: this is the answerer's fixed abstention phrase, the same sentence it emits whenever it declines. It records THAT the answerer declined and never why — no per-ruling reason was captured, because none was sent. 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 930), 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.