Ruling — Paleo — RuleSage

You asked

How do I play?

Answered counted as answered

Asked with: Paleobg-300531-en-1e

The game is played over multiple rounds, each consisting of a day phase and a night phase.[1]

**Day Phase**

1. All players take their turns simultaneously.[2]

2. Each player looks at the backs of the top 3 cards of their deck and chooses 1 card to place facedown in front of them.[2]

3. The other 2 cards are returned to the top of the player's deck in an order of their choice.[2]

4. Once each player has chosen a card, all chosen cards are revealed simultaneously.[2]

5. The players decide, as a group, the order in which cards are resolved.[2]

6. Each player chooses 1 option on their card and resolves it.[2]

7. Players continue choosing and resolving cards until all players' decks are empty.[2]

**Night Phase**

1. The night phase begins once all players are asleep (no one has any cards remaining in their decks).[3]

2. Each player must feed all the people in their group by paying 1 food from the storage area to the supply for each person; if there is not enough food, 1 skull token is placed on the night board for each unfed person.[3]

3. After feeding, the group must deal with any faceup mission cards by choosing and resolving 1 of the shown actions as a group.[3]

4. The group must also deal with any night action cards in the same way as mission cards, choosing and resolving 1 of the shown actions.[3]

5. All cards in the faceup and facedown discard piles on the wilderness board are shuffled together and dealt out facedown, as evenly as possible, to the players.[3]

6. The night phase ends and the next day phase begins.[3]

**Ending the Game**

* **Winning:** The players win immediately if they collect 5 victory tokens as a tribe and add them to the corresponding space on the night board to complete the cave painting.[1]

* **Losing:** The players lose immediately if the tribe collects a 5th skull token.[1]

* **Exception:** If the 5th skull token and 5th victory token are collected during the same action, the players win.[1]

[1] RULEBOOK Paleo — Rulebook · p.2 · KEY CONCEPTS

[2] RULEBOOK Paleo — Rulebook · p.4 · CARD SETUP · DAY PHASE · CHOOSE A CARD · Card Backs · Example: Additional symbols on a card back · ADDITIONAL INFORMATION · …

[3] RULEBOOK Paleo — Rulebook · p.9

🔧 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 72 ms · ask 3910 ms · total 3985 ms
single-flight (PR-5): queued 0 ms · generation 3985 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 10, "score": 0.04866, "snippet": "– 10 – See this example for a full breakdown of how a round is played. This example assigns colors to the players, unlike the normal game. 3You are playing a 3-player game. Each player looks at the backs of the top 3 cards of their decks, and chooses 1 card to reveal. 1 2 Resolving an action: Orange", "headingPath": "", "sharpsignalDocId": 385}, {"page": 2, "score": 0.048139, "snippet": "Each player controls a group of people, including fierce warriors, clever inventors, and watchful scouts. Together, the players form a tribe, working together to explore their surroundings. You will encounter trials and adventures in the wilderness, and only by working together can you triumph and b", "headingPath": "OBJECT OF THE GAME & ENDING THE GAME · IMPORTANT!", "sharpsignalDocId": 385}, {"page": 12, "score": 0.047883, "snippet": "E You now know everything you need to begin playing your first game. You can skip this section for now, and refer back to it when it becomes necessary. Some cards require you to place tool tokens or resources directly onto them. As soon as you gain a tool or resource, you must decide whether to take", "headingPath": "NIGHT PHASE · PLACING TOOLS AND RESOURCES ON CARDS · USING ALTERNATIVE ACTION CARDS · Example: Using an alternative action · ADDITIONAL ACTIONS · NEW CARDS", "sharpsignalDocId": 385}, {"page": 2, "score": 0.046432, "snippet": "Paleo is a cooperative game. All players are working together on the same team, and will win and lose together. You are always allowed to discuss strategy with other players, and players can freely share information with each other. The game is played over multiple rounds. Each round consists of a d", "headingPath": "KEY CONCEPTS", "sharpsignalDocId": 385}, {"page": 3, "score": 0.046175, "snippet": "– 3 – Most aspects of setup are the same each game; the only changes are based on which modules you use. Rules specific to each module are detailed under “Modules” on pages 2 & 3 of the supplemental rules. Place the 3 boards in the middle of the play area. 1 SETUP Sort the tool tokens by type. Next,", "headingPath": "", "sharpsignalDocId": 385}, {"page": 7, "score": 0.030769, "snippet": "Some actions have unpredictable outcomes. Roll the number of dice shown. The dice increase the ability requirements to resolve the action. If the die results mean that you cannot resolve the action, you must instead resolve a negative action on the card, or ignore the card if there are no negative a", "headingPath": "DICE · Example: Dice · RED BACKS", "sharpsignalDocId": 385}, {"page": 4, "score": 0.029851, "snippet": "River The first phase of every round is the day phase, where players resolve cards from their decks and make new discoveries. Each day phase consists of multiple turns. All players take their turns simultaneously . Look at the backs of the top 3 cards of your deck, and choose 1 of them to place face", "headingPath": "CARD SETUP · DAY PHASE · CHOOSE A CARD · Card Backs · Example: Additional symbols on a card back · ADDITIONAL INFORMATION · …", "sharpsignalDocId": 385}, {"page": 9, "score": 0.02967, "snippet": "– 9 – NIGHT PHASE Once all players are asleep (no one has any cards remaining in their decks), the night phase begins. See “End of Day Phase” on page 4. FEEDING Each player must feed all of the people in their group. For each person, pay 1 food from the storage area to the supply. If there is not en", "headingPath": "", "sharpsignalDocId": 385}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "KEY CONCEPTS", "sharpsignalDocId": 385}, {"page": 4, "quote": null, "headingPath": "CARD SETUP · DAY PHASE · CHOOSE A CARD · Card Backs · Example: Additional symbols on a card back · ADDITIONAL INFORMATION · …", "sharpsignalDocId": 385}, {"page": 9, "quote": null, "headingPath": "", "sharpsignalDocId": 385}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 385 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 385 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 0.90574 of 1602 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 15, 2026 12:12

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 Paleo — Rulebook (corpus doc 385)		p.10	0.04866 (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 Paleo — Rulebook (corpus doc 385)	OBJECT OF THE GAME & ENDING THE GAME · IMPORTANT!	p.2	0.048139 (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 Paleo — Rulebook (corpus doc 385)	NIGHT PHASE · PLACING TOOLS AND RESOURCES ON CARDS · USING ALTERNATIVE ACTION CARDS · Example: Using an alternative action · ADDITIONAL ACTIONS · NEW CARDS	p.12	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
#4	RULEBOOK Paleo — Rulebook (corpus doc 385)	KEY CONCEPTS	p.2	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
#5	RULEBOOK Paleo — Rulebook (corpus doc 385)		p.3	0.046175 (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 Paleo — Rulebook (corpus doc 385)	DICE · Example: Dice · RED BACKS	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
#7	RULEBOOK Paleo — Rulebook (corpus doc 385)	CARD SETUP · DAY PHASE · CHOOSE A CARD · Card Backs · Example: Additional symbols on a card back · ADDITIONAL INFORMATION · …	p.4	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 Paleo — Rulebook (corpus doc 385)		p.9	0.02967 (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 20 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 Paleo — Rulebook (corpus doc 385)		p.10	#1	0.04866 (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 Paleo — Rulebook (corpus doc 385)		p.3	#5	0.046175 (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 Paleo — Rulebook (corpus doc 385)	KEY CONCEPTS	p.2	#4	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
#4	RULEBOOK Paleo — Rulebook (corpus doc 385)	CARD SETUP · DAY PHASE · CHOOSE A CARD · Card Backs · Example: Additional symbols on a card back · ADDITIONAL INFORMATION · …	p.4	#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
#5	RULEBOOK Paleo — Rulebook (corpus doc 385)	CARD SETUP	p.2	#14	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
#6	RULEBOOK Paleo — Rulebook (corpus doc 385)		p.9	#8	0.02967 (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
#7	RULEBOOK Paleo — Rulebook (corpus doc 385)	NIGHT PHASE · PLACING TOOLS AND RESOURCES ON CARDS · USING ALTERNATIVE ACTION CARDS · Example: Using an alternative action · ADDITIONAL ACTIONS · NEW CARDS	p.12	#3	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
#8	RULEBOOK Paleo — Rulebook (corpus doc 385)	OBJECT OF THE GAME & ENDING THE GAME · IMPORTANT!	p.2	#2	0.048139 (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 Paleo — Rulebook (corpus doc 385)	KEY CONCEPTS	p.2	no quote on the wire
[2]	RULEBOOK Paleo — Rulebook (corpus doc 385)	CARD SETUP · DAY PHASE · CHOOSE A CARD · Card Backs · Example: Additional symbols on a card back · ADDITIONAL INFORMATION · …	p.4	no quote on the wire
[3]	RULEBOOK Paleo — Rulebook (corpus doc 385)		p.9	no quote on the wire

generation — timing and the path taken

timing split: retrieval 72 ms · first delta 1595 ms · total 3985 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 3910 ms · gateway work 3985 ms · total 3985 ms
tokens in (the prompt the answerer read): 3458
tokens out (what the answerer generated): 481
tok/sec: 204.6 tok/sec — 481 output tokens in 2.351 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 16s 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: 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 314), 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.