Ruling — One Deck Dungeon

You asked

How do I play?

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

Asked with: One Deck Dungeonbg-179275-en-1e

I looked through One Deck Dungeon'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 One Deck Dungeon — Rulebook · p.26 · Campaign Mode

Campaign mode allows you to build up a hero's power over multiple plays. Each campaign sheet represents one player's adventures with one of the five heroes. At the end of each game you'll earn check-marks that you can apply toward earning talents . They will help you in future games. You earn one ch

RULEBOOK One Deck Dungeon — Rulebook · p.12 · TURN OPTION: ENTER A ROOM · EXAMPLE TURN #2: ENTER A ROOM · TURN #3 AND BEYOND:

All the action in One Deck Dungeon lies behind doors. When the party uses their turn to enter a room , you must select one of the doors in play. If the door is closed (face-down), first open the door by flipping it face-up. Then, the party can choose to either start an encounter or flee . If you fle

RULEBOOK One Deck Dungeon — Rulebook · p.5 · Setup steps:

Stack the experience level cards (level 1 on top, level 4 on the bottom). Shuffle all the encounter cards together into a deck. Place the stairs card underneath the deck. Slide the dungeon card under the Turn Reference, so that only the first floor of the dungeon is showing. Return the unused heroes

RULEBOOK One Deck Dungeon — Rulebook · p.11 · TURN OPTION: EXPLORE · EXAMPLE TURN #1: EXPLORE

To explore , add face-down doors from the encounter deck to the table until there are four total doors in play. Open doors (face-up cards that you fled from) count toward the limit of four, as do closed doors from previous explore turns. You cannot explore if there are already four doors (whether op

RULEBOOK One Deck Dungeon — Rulebook · p.4 · SETUP: CHOOSE A HERO & DUNGEON

HERO DUNGEON/BOSS Dots next to a dungeon's name represent its difficulty. More dots mean a harder dungeon (and boss!) The boss is on the back of the dungeon card. Each player chooses a hero card , and together your party chooses a dungeon to face. Multiplayer games are fully cooperative. Use the 1P

🔧 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 224 ms · ask 2130 ms · total 2357 ms

single-flight (PR-5)

queued 0 ms · generation 2357 ms

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

[{"page": 26, "score": 0.048412, "snippet": "Campaign mode allows you to build up a hero's power over multiple plays. Each campaign sheet represents one player's adventures with one of the five heroes. At the end of each game you'll earn check-marks that you can apply toward earning talents . They will help you in future games. You earn one ch", "headingPath": "Campaign Mode", "sharpsignalDocId": 1001}, {"page": 12, "score": 0.046671, "snippet": "All the action in One Deck Dungeon lies behind doors. When the party uses their turn to enter a room , you must select one of the doors in play. If the door is closed (face-down), first open the door by flipping it face-up. Then, the party can choose to either start an encounter or flee . If you fle", "headingPath": "TURN OPTION: ENTER A ROOM · EXAMPLE TURN #2: ENTER A ROOM · TURN #3 AND BEYOND:", "sharpsignalDocId": 1001}, {"page": 5, "score": 0.046343, "snippet": "Stack the experience level cards (level 1 on top, level 4 on the bottom). Shuffle all the encounter cards together into a deck. Place the stairs card underneath the deck. Slide the dungeon card under the Turn Reference, so that only the first floor of the dungeon is showing. Return the unused heroes", "headingPath": "Setup steps:", "sharpsignalDocId": 1001}, {"page": 11, "score": 0.045455, "snippet": "To explore , add face-down doors from the encounter deck to the table until there are four total doors in play. Open doors (face-up cards that you fled from) count toward the limit of four, as do closed doors from previous explore turns. You cannot explore if there are already four doors (whether op", "headingPath": "TURN OPTION: EXPLORE · EXAMPLE TURN #1: EXPLORE", "sharpsignalDocId": 1001}, {"page": 4, "score": 0.043905, "snippet": "HERO DUNGEON/BOSS Dots next to a dungeon's name represent its difficulty. More dots mean a harder dungeon (and boss!) The boss is on the back of the dungeon card. Each player chooses a hero card , and together your party chooses a dungeon to face. Multiplayer games are fully cooperative. Use the 1P ", "headingPath": "SETUP: CHOOSE A HERO & DUNGEON", "sharpsignalDocId": 1001}, {"page": 16, "score": 0.04374, "snippet": "In an encounter, the party must try and cover as many active challenge boxes as possible. In a combat encounter, all challenge boxes on the encounter card are active. In a peril encounter, only the box under the chosen option is active. The other box is ignored entirely. There are challenge boxes on", "headingPath": "STEP 4: USE SKILLS AND PLACE DICE", "sharpsignalDocId": 1001}, {"page": 9, "score": 0.03125, "snippet": "Every game turn in One Deck Dungeon is shared by the entire party. You will act together to face encounters and overcome them, which will of course result in wondrous loot! On the following pages are detailed descriptions of each part of the game turn. Here's a list of everything that will happen in", "headingPath": "Turns: Overview · PHASE 2: EXPLORE OR ENTER A ROOM · OPTION 2: ENTER A ROOM", "sharpsignalDocId": 1001}, {"page": 24, "score": 0.030769, "snippet": "When you descend from the third floor of the dungeon, flip over the dungeon card. It's time to fight the boss ! The Boss Fight consists of multiple rounds . The boss has a health value and a special ability along the bottom of its card. After each round, the party will deal damage to the boss. Heroi", "headingPath": "Boss Fight", "sharpsignalDocId": 1001}]

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 1001 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true

base rulebook doc 1001 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 14, 2026 19:09 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 One Deck Dungeon — Rulebook (corpus doc 1001)	Campaign Mode	p.26	0.048412 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	TURN OPTION: ENTER A ROOM · EXAMPLE TURN #2: ENTER A ROOM · TURN #3 AND BEYOND:	p.12	0.046671 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	Setup steps:	p.5	0.046343 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	TURN OPTION: EXPLORE · EXAMPLE TURN #1: EXPLORE	p.11	0.045455 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	SETUP: CHOOSE A HERO & DUNGEON	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
#6	RULEBOOK One Deck Dungeon — Rulebook (corpus doc 1001)	STEP 4: USE SKILLS AND PLACE DICE	p.16	0.04374 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	Turns: Overview · PHASE 2: EXPLORE OR ENTER A ROOM · OPTION 2: ENTER A ROOM	p.9	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 One Deck Dungeon — Rulebook (corpus doc 1001)	Boss Fight	p.24	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

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 40 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 One Deck Dungeon — Rulebook (corpus doc 1001)	TURN OPTION: ENTER A ROOM · EXAMPLE TURN #2: ENTER A ROOM · TURN #3 AND BEYOND:	p.12	#2	0.046671 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	TURN OPTION: EXPLORE · EXAMPLE TURN #1: EXPLORE	p.11	#4	0.045455 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	Four Player Rules · FOUR PLAYER CHANGES	p.28	#14	0.026667 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	CHALLENGE TIERS · Any Dungeon CAMPAIGN SHEET EXAMPLE	p.27	#10	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
#5	RULEBOOK One Deck Dungeon — Rulebook (corpus doc 1001)		p.4	#12	0.027364 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	Start of Turn / Explore · Rolling Dice and Using Skills	p.32	#20	0.014085 (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 One Deck Dungeon — Rulebook (corpus doc 1001)	SETUP: CHOOSE A HERO & DUNGEON	p.4	#5	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
#8	RULEBOOK One Deck Dungeon — Rulebook (corpus doc 1001)	Setup steps:	p.5	#3	0.046343 (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 224 ms · first delta 2254 ms · total 2357 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 224 ms · ask 2130 ms · gateway work 2357 ms · total 2357 ms
tokens in (the prompt the answerer read): 2575
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 40s ago)
answerer host (measured by rulesage): reachable (for 22h, checked 0s 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 931), 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.