Ruling — Archaeology: The New Expedition

You asked

When does the game end?

Answered counted as answered

Asked with: Archaeology: The New Expeditionbg-191300-en-1e

The game is over when every player is left without cards in his hand (meaning all remaining treasures have been sold to the museum).[1]

[1] RULEBOOK Archaeology: The New Expedition — Rulebook · p.9 · Ending The Game · Example

Settled. Play on.

🔧 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 84 ms · ask 1793 ms · total 1879 ms
single-flight (PR-5): queued 0 ms · generation 1879 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 9, "score": 0.04918, "snippet": "When there are no cards left in the deck, play continues, but players no longer dig for treasure at the start of their turn. Players continue taking other actions as usual on their turn, or they may pass and take no actions. However, if all players pass in sequence, then the first player who passed ", "headingPath": "Ending The Game · Example", "sharpsignalDocId": 1071}, {"page": 8, "score": 0.047883, "snippet": "A player may choose to sell a set of 1 or more Treasure cards of the same type from his hand to the museum. These sets are worth money at the end of the game. The value of a set of treasures is determined by the selling prices listed at the bottom of its card. For most treasures, you will notice tha", "headingPath": "c. Sell to the museum · 3. End of turn", "sharpsignalDocId": 1071}, {"page": 5, "score": 0.047131, "snippet": "The first player is the last person to have put their feet in the sand. Each turn, a player digs for treasure, and then may take other actions. At the start of his turn, the player must dig for treasure by drawing the top card from the dig site. The player has found that treasure! The card is added ", "headingPath": "Playing the Game · 1. Dig for treasure · If it's a Treasure card... · If it's a Thief card... · If it's a Sandstorm card... · Playing your Tent card", "sharpsignalDocId": 1071}, {"page": 2, "score": 0.046176, "snippet": "Great Pyra midSphinxMine 7 1 1 1 5 5 5 8 1 2 1 2 2 T omb Buried Ruins Temple After selling to the museu m, look at all the cards in 1 ch a mber . Make a pile of 12 facedown Treasure cards. When a Sa ndstorm card is drawn, add 1 of these to each ch a mber faceup. Draw all cards in 1 ch a mber . Look ", "headingPath": "", "sharpsignalDocId": 1071}, {"page": 2, "score": 0.04598, "snippet": "A game for 2 to 5 daring archaeologists, aged 10 and up, playing time of 20 minutes. 16 Pot Shards 16 Parchment Scraps 12 Coins 6 Broken Cups 8 Talismans 6 Maps 4 Pharaoh's Masks 12 Broken Tablets 5 Broken Pendants 10 Thief cards 6 Sandstorm cards 5 Tent cards Mine This rulebook 15 1 Shuffle the cha", "headingPath": "85 Treasure cards: · 21 other cards: · 6 Monument tiles · Goal and Overview", "sharpsignalDocId": 1071}, {"page": 12, "score": 0.03125, "snippet": "\u0007 Long Expedition (for 2 or 3 players): For a longer game with 2 or 3 players, simply add the Broken Tablet and Broken Pendant cards to the game during setup. When using this variant, also add 1 extra Thief card to the game. \u0007 Fierce Weather: In this variant, all 6 Sandstorm cards are used in the ga", "headingPath": "Variants · Credits", "sharpsignalDocId": 1071}, {"page": 6, "score": 0.030769, "snippet": "Adele draws a Sandstorm. She discards it faceup on the table. Ben is the player to her left and he decides not to use his tent. Christopher does the same. Daria chooses to use her tent and so discards it from the game. Adele has already used her tent previously. Ben has 6 cards and so must discard 3", "headingPath": "Example · After the storm... · 2. Other actions · a. Trade at the marketplace", "sharpsignalDocId": 1071}, {"page": 3, "score": 0.029412, "snippet": "1. \u0007 Set aside the Map, Thief, Sandstorm, and Tent cards. When playing with 2 or 3 players , return the Broken Tablet and Broken Pendant cards to the box. With 4 players , only return the Broken Pendant cards to the box. Shuffle all the remaining cards into 1 deck. \u0007 Deal 4 cards from the deck faced", "headingPath": "Setting Up the Game", "sharpsignalDocId": 1071}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 9, "quote": null, "headingPath": "Ending The Game · Example", "sharpsignalDocId": 1071}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 1071 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1071 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 0.94643 of 112 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 29, 2026 21:40 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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Ending The Game · Example	p.9	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)	c. Sell to the museum · 3. End of turn	p.8	0.047883 (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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Playing the Game · 1. Dig for treasure · If it's a Treasure card... · If it's a Thief card... · If it's a Sandstorm card... · Playing your Tent card	p.5	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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)		p.2	0.046176 (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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	85 Treasure cards: · 21 other cards: · 6 Monument tiles · Goal and Overview	p.2	0.04598 (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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Variants · Credits	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
#7	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Example · After the storm... · 2. Other actions · a. Trade at the marketplace	p.6	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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Setting Up the Game	p.3	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 15 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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Ending The Game · Example	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
#2	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Variants · Credits	p.12	#6	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
#3	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Playing the Game · 1. Dig for treasure · If it's a Treasure card... · If it's a Thief card... · If it's a Sandstorm card... · Playing your Tent card	p.5	#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
#4	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Setting Up the Game	p.3	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#5	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Example · After the storm... · 2. Other actions · a. Trade at the marketplace	p.6	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK Archaeology: The New Expedition — Rulebook (corpus doc 1071)		p.2	#4	0.046176 (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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	85 Treasure cards: · 21 other cards: · 6 Monument tiles · Goal and Overview	p.2	#5	0.04598 (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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	c. Sell to the museum · 3. End of turn	p.8	#2	0.047883 (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 Archaeology: The New Expedition — Rulebook (corpus doc 1071)	Ending The Game · Example	p.9	no quote on the wire

generation — timing and the path taken

timing split: retrieval 84 ms · first delta 1679 ms · total 1879 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 84 ms · ask 1793 ms · gateway work 1879 ms · total 1879 ms
tokens in (the prompt the answerer read): 3504
tokens out (what the answerer generated): 30
tok/sec: 194.8 tok/sec — 30 output tokens in 0.154 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 18s ago)
gateway schema (read from the running child): schema head 0042_definer_search_path (live revision not readable by this principal)
answerer host (measured by rulesage): reachable (for 60h, checked 6s 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 1001), 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.