You asked
How do I play?
Answered counted as answeredAsked with: Mini Roguebg-311715-en-1e
Question closed. Friendships intact.
🔧 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 116 ms · ask 7574 ms · total 7693 ms
- single-flight (PR-5)
- queued 0 ms · generation 7693 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 26, "score": 0.048139, "snippet": "Monster or Boss cards: When resolving a Monster or Boss card with both players on the same card, always consult the Monster's second HP value. Then, starting with the Party Leader, the Combat sequence will be resolved as follows: The Party Leader performs their Attack phase, . then the Monster Attac", "headingPath": "How to Play · COMBAT STANCES CARD VARIANT", "sharpsignalDocId": 1128}, {"page": 16, "score": 0.047643, "snippet": "Nobles, students, soldiers, and scholars - champions from all backgrounds and upbringings - converge on the same dungeon... Each Character has unique Skills. Once any Skill is used, flip the Character card facedown to indicate it is used. A Character cannot use their Skills while their card is faced", "headingPath": "CHARACTER CLASSES AND SKILLS · DIFFICULTY", "sharpsignalDocId": 1128}, {"page": 25, "score": 0.047493, "snippet": "When both players are in the same Room, they resolve the card one after the other, starting with the Party Leader. The outcome or choices of action can be different for each player. For example, the first player might succeed at a Trap Skill Check, whereas the second player might fail the check. In ", "headingPath": "How to Play", "sharpsignalDocId": 1128}, {"page": 24, "score": 0.046432, "snippet": "If your HP falls to 0, your Character has succumbed to their injuries and you have lost the game.. . If you reach the last room of the Dungeon and defeat the final Boss, the fabled Og's Blood is yours! Victorious, you may finally pick it up and leave this cursed dungeon. Congratulations! Why is it t", "headingPath": "END OF THE GAME · 2 PLAYER CO-OPERATIVE RULES · Setup · How to Play", "sharpsignalDocId": 1128}, {"page": 3, "score": 0.045002, "snippet": "In this solitaire or co-operative game, you play as an adventurer, delving into a dungeon, room after room and floor after floor, in order to find the Og's Blood : a fabled and mysterious artifact rumored to be a ruby gemstone. A dungeon area is laid out as a grid of room cards. Each time you face t", "headingPath": "OBJECT OF THE GAME · COMPONENTS", "sharpsignalDocId": 1128}, {"page": 8, "score": 0.03125, "snippet": "Every turn, you will guide your Character through a single Area, starting from the entrance, going from left to right and from top to bottom, heading towards the exit. Each Area contains Rooms with encounters that need to be resolved one at a time before moving forward. Here is a game turn in detail", "headingPath": "TURN SEQUENCE · Preparation Phase · Exploration Phase", "sharpsignalDocId": 1128}, {"page": 4, "score": 0.030769, "snippet": "Choose a Character card and place it faceup to the left of your Character mat. Set your Character's starting stats according to the values on the top right corner of your Character card. If a stat is not shown on the Character card, set it to 0. You will keep track of each stat by moving its wooden ", "headingPath": "SETUP", "sharpsignalDocId": 1128}, {"page": 10, "score": 0.029412, "snippet": "Whenever you face a Monster or Boss (see Room cards), you enter a Combat. Each party takes a turn attacking the other. Your Character attacks first, then defends themselves against the monster's attack. . It is a fight to the death, and whoever loses all their HP dies horribly. You may use your Comb", "headingPath": "COMBAT · Attack Phase", "sharpsignalDocId": 1128}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "SETUP", "sharpsignalDocId": 1128}, {"page": 8, "quote": null, "headingPath": "TURN SEQUENCE · Preparation Phase · Exploration Phase", "sharpsignalDocId": 1128}, {"page": 24, "quote": null, "headingPath": "END OF THE GAME · 2 PLAYER CO-OPERATIVE RULES · Setup · How to Play", "sharpsignalDocId": 1128}, {"page": 25, "quote": null, "headingPath": "How to Play", "sharpsignalDocId": 1128}, {"page": 26, "quote": null, "headingPath": "How to Play · COMBAT STANCES CARD VARIANT", "sharpsignalDocId": 1128}, {"page": 10, "quote": null, "headingPath": "COMBAT · Attack Phase", "sharpsignalDocId": 1128}, {"page": 3, "quote": null, "headingPath": "OBJECT OF THE GAME · COMPONENTS", "sharpsignalDocId": 1128}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1128 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1128 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 0.89996 of 2829 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 6, 2026 13:28 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 Mini Rogue — Rulebook (corpus doc 1128) | How to Play · COMBAT STANCES CARD VARIANT | p.26 | 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 |
| #2 | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | CHARACTER CLASSES AND SKILLS · DIFFICULTY | p.16 | 0.047643 (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 Mini Rogue — Rulebook (corpus doc 1128) | How to Play | p.25 | 0.047493 (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 Mini Rogue — Rulebook (corpus doc 1128) | END OF THE GAME · 2 PLAYER CO-OPERATIVE RULES · Setup · How to Play | p.24 | 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 Mini Rogue — Rulebook (corpus doc 1128) | OBJECT OF THE GAME · COMPONENTS | p.3 | 0.045002 (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 Mini Rogue — Rulebook (corpus doc 1128) | TURN SEQUENCE · Preparation Phase · Exploration Phase | p.8 | 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 Mini Rogue — Rulebook (corpus doc 1128) | SETUP | p.4 | 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 Mini Rogue — Rulebook (corpus doc 1128) | COMBAT · Attack Phase | p.10 | 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 39 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 Mini Rogue — Rulebook (corpus doc 1128) | How to Play | p.25 | #3 | 0.047493 (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 Mini Rogue — Rulebook (corpus doc 1128) | How to Play · COMBAT STANCES CARD VARIANT | p.26 | #1 | 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 |
| #3 | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | TURN SEQUENCE · Preparation Phase · Exploration Phase | p.8 | #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 |
| #4 | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | TURN EXAMPLE | p.22 | #10 | 0.028259 (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 Mini Rogue — Rulebook (corpus doc 1128) | COMBAT · Attack Phase | p.10 | #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 |
| #6 | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | OBJECT OF THE GAME · COMPONENTS | p.3 | #5 | 0.045002 (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 Mini Rogue — Rulebook (corpus doc 1128) | SETUP | p.4 | #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 |
| #8 | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | END OF THE GAME · 2 PLAYER CO-OPERATIVE RULES · Setup · How to Play | p.24 | #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 |
chosen chunks — what the answer actually cited
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.
| # | document | heading | page | quote chars |
|---|---|---|---|---|
| [1] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | SETUP | p.4 | no quote on the wire |
| [2] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | TURN SEQUENCE · Preparation Phase · Exploration Phase | p.8 | no quote on the wire |
| [3] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | END OF THE GAME · 2 PLAYER CO-OPERATIVE RULES · Setup · How to Play | p.24 | no quote on the wire |
| [4] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | How to Play | p.25 | no quote on the wire |
| [5] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | How to Play · COMBAT STANCES CARD VARIANT | p.26 | no quote on the wire |
| [6] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | COMBAT · Attack Phase | p.10 | no quote on the wire |
| [7] | RULEBOOK Mini Rogue — Rulebook (corpus doc 1128) | OBJECT OF THE GAME · COMPONENTS | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 116 ms · first delta 3204 ms · total 7693 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 116 ms · ask 7574 ms · gateway work 7693 ms · total 7693 ms
- tokens in (the prompt the answerer read)
- 3591
- tokens out (what the answerer generated)
- 876
- tok/sec
- 199.8 tok/sec — 876 output tokens in 4.384 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 17s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 8s 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 1058), 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.