Ruling — Roll Player Adventures

You asked

How do I play?

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

Asked with: Roll Player Adventuresbg-254708-en-1e

I looked through Roll Player Adventures'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 Roll Player Adventures — Rulebook · p.14 · SKILL CHECK: MANIPULATE AND PLACE DICE · SKILL CHECK: RESOLUTION

Each player gathers the cards from their hand space (but not from their spent space). The players may play cards from their hands to alter the dice in the dice pool. They can coordinate with each other to decide who should play which cards and in what order. See 'Card Icons' on page 22. Cards are pl

RULEBOOK Roll Player Adventures — Rulebook · p.16 · COMBAT: MANIPULATE AND PLACE DICE · COMBAT: END OF ROUND

Each player gathers the cards from their hand space (but not from their spent space). The players may play cards from their hands to alter the dice in the dice pool. They can coordinate with each other to decide who should play which cards and in what order. See 'Card Icons' on page 22. Cards are pl

RULEBOOK Roll Player Adventures — Rulebook · p.6 · Campaign Setup v · 1. Fill Dice Bag · 2. Prepare Party Journal · 3. Take Character Sheets · 4. Select Pregenerated Characters · 5. Record Character Details · …

Follow the steps below when starting a new campaign. Adventure setup is carried out before each new adventure within the campaign, but campaign setup only has to be done once, at the very start of the campaign. Find the 36 attribute dice and place them in the black drawstring bag. Leave the familiar

RULEBOOK Roll Player Adventures — Rulebook · p.15 · Combat v · COMBAT: SETUP

The party will encounter enemies during an adventure, which often leads to combat. Combat is indicated in the storybook by a combat box that indicates the enemy's name, number, and any modifiers. During combat, the players must work together to cover each dice slot on the enemy card with a matching

RULEBOOK Roll Player Adventures — Rulebook · p.8 · Adventure Setup v · 1. Prepare Party Journal · 2. Create Supply · 3. Discovery, Title, and Rare Decks · 4. Player Aids and Character Sheets · 5. Storybooks · …

Once campaign setup is complete, follow these steps when starting each adventure: Place the party journal in the center of the table. Place the dice bag, skillbook, enemy deck, modifier deck, gold, XP, stamina, encounter tokens, bonus play tokens, favor markers, round markers, market decks, familiar

🔧 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 93 ms · ask 3268 ms · total 3362 ms

single-flight (PR-5)

queued 0 ms · generation 3362 ms

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

[{"page": 14, "score": 0.04918, "snippet": "Each player gathers the cards from their hand space (but not from their spent space). The players may play cards from their hands to alter the dice in the dice pool. They can coordinate with each other to decide who should play which cards and in what order. See 'Card Icons' on page 22. Cards are pl", "headingPath": "SKILL CHECK: MANIPULATE AND PLACE DICE · SKILL CHECK: RESOLUTION", "sharpsignalDocId": 744}, {"page": 16, "score": 0.048387, "snippet": "Each player gathers the cards from their hand space (but not from their spent space). The players may play cards from their hands to alter the dice in the dice pool. They can coordinate with each other to decide who should play which cards and in what order. See 'Card Icons' on page 22. Cards are pl", "headingPath": "COMBAT: MANIPULATE AND PLACE DICE · COMBAT: END OF ROUND", "sharpsignalDocId": 744}, {"page": 6, "score": 0.046635, "snippet": "Follow the steps below when starting a new campaign. Adventure setup is carried out before each new adventure within the campaign, but campaign setup only has to be done once, at the very start of the campaign. Find the 36 attribute dice and place them in the black drawstring bag. Leave the familiar", "headingPath": "Campaign Setup v · 1. Fill Dice Bag · 2. Prepare Party Journal · 3. Take Character Sheets · 4. Select Pregenerated Characters · 5. Record Character Details · …", "sharpsignalDocId": 744}, {"page": 15, "score": 0.044388, "snippet": "The party will encounter enemies during an adventure, which often leads to combat. Combat is indicated in the storybook by a combat box that indicates the enemy's name, number, and any modifiers. During combat, the players must work together to cover each dice slot on the enemy card with a matching ", "headingPath": "Combat v · COMBAT: SETUP", "sharpsignalDocId": 744}, {"page": 8, "score": 0.044103, "snippet": "Once campaign setup is complete, follow these steps when starting each adventure: Place the party journal in the center of the table. Place the dice bag, skillbook, enemy deck, modifier deck, gold, XP, stamina, encounter tokens, bonus play tokens, favor markers, round markers, market decks, familiar", "headingPath": "Adventure Setup v · 1. Prepare Party Journal · 2. Create Supply · 3. Discovery, Title, and Rare Decks · 4. Player Aids and Character Sheets · 5. Storybooks · …", "sharpsignalDocId": 744}, {"page": 9, "score": 0.043364, "snippet": "Unlike many board games, Roll Player Adventures does not have traditional turns. The storybook drives the action and presents the players with choices. Over the course of an adventure, the players will read from storybooks, encounter challenges, and engage in combat scenarios that will lead to rolli", "headingPath": "Key Concepts v · ENTRIES · KEYWORDS · TITLES", "sharpsignalDocId": 744}, {"page": 13, "score": 0.031746, "snippet": "The party will encounter situations that test their skills during an adventure. Skill checks are indicated in the storybook by a skill check box that indicates the skill check's name, difficulty level, and any modifiers. During a skill check, the players must work together to cover each dice slot on", "headingPath": "Skill Checks v · SKILL CHECK: SETUP", "sharpsignalDocId": 744}, {"page": 20, "score": 0.030366, "snippet": "As the party explores Ulos, they might gain or lose a member along the way. If the number of players in the party changes between adventures, the campaign can still go on! Just make the following adjustments to add or remove a player. Adjust the play limit to reflect the new player count. Refer to t", "headingPath": "Adding and Removing Players v · ADDING A PLAYER · REMOVING A PLAYER", "sharpsignalDocId": 744}]

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

base rulebook doc 744 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 26, 2026 07:17 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 Roll Player Adventures — Rulebook (corpus doc 744)	SKILL CHECK: MANIPULATE AND PLACE DICE · SKILL CHECK: RESOLUTION	p.14	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Roll Player Adventures — Rulebook (corpus doc 744)	COMBAT: MANIPULATE AND PLACE DICE · COMBAT: END OF ROUND	p.16	0.048387 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Campaign Setup v · 1. Fill Dice Bag · 2. Prepare Party Journal · 3. Take Character Sheets · 4. Select Pregenerated Characters · 5. Record Character Details · …	p.6	0.046635 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Combat v · COMBAT: SETUP	p.15	0.044388 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Adventure Setup v · 1. Prepare Party Journal · 2. Create Supply · 3. Discovery, Title, and Rare Decks · 4. Player Aids and Character Sheets · 5. Storybooks · …	p.8	0.044103 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Key Concepts v · ENTRIES · KEYWORDS · TITLES	p.9	0.043364 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Skill Checks v · SKILL CHECK: SETUP	p.13	0.031746 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Adding and Removing Players v · ADDING A PLAYER · REMOVING A PLAYER	p.20	0.030366 (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 45 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 Roll Player Adventures — Rulebook (corpus doc 744)	COMBAT: MANIPULATE AND PLACE DICE · COMBAT: END OF ROUND	p.16	#2	0.048387 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Adding and Removing Players v · ADDING A PLAYER · REMOVING A PLAYER	p.20	#8	0.030366 (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
#3	RULEBOOK Roll Player Adventures — Rulebook (corpus doc 744)	Familiars v	p.20	#15	0.026519 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Legendary Mode v · LEGENDARY SKILL CHECK FAILURE PENALTY	p.21	#11	0.027693 (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 Roll Player Adventures — Rulebook (corpus doc 744)	LEGENDARY HAND LIMIT	p.21	#13	0.027584 (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 Roll Player Adventures — Rulebook (corpus doc 744)	RESTING	p.12	#10	0.027973 (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 Roll Player Adventures — Rulebook (corpus doc 744)	Combat v · COMBAT: SETUP	p.15	#4	0.044388 (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 Roll Player Adventures — Rulebook (corpus doc 744)	SKILL CHECK: MANIPULATE AND PLACE DICE · SKILL CHECK: RESOLUTION	p.14	#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 93 ms · first delta 3266 ms · total 3362 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 93 ms · ask 3268 ms · gateway work 3362 ms · total 3362 ms
tokens in (the prompt the answerer read): 2910
tokens out (what the answerer generated): 9
tok/sec: 191.5 tok/sec — 9 output tokens in 0.047 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 16s 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 4s 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.
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 678), 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.