You asked
How do I play?
Answered counted as answeredAsked with: Vindicationbg-224783-en-1e
The table has its answer — dice up.
🔧 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 110 ms · ask 9324 ms · total 9436 ms
- single-flight (PR-5)
- queued 0 ms · generation 9436 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.046486, "snippet": "After the game is set up and players have placed their tokens on the starting locations indicated on their journey card, reveal the regions adjacent to the players by drawing from the pouch. The player on the lowest-numbered space gets the starting player miniature (Sestra, Lorekeeper) and goes firs", "headingPath": "Initial Placement · Starting the Game · Turn Summary", "sharpsignalDocId": 450}, {"page": 48, "score": 0.04526, "snippet": "Option 1: Recommended Setup To get the deepest experience, set aside all cards with an icon in the upper left, and manually remove all of the cards that reference other players, proficiencies, or mastery. Though meticulous, this task can be accomplished in under 10 minutes, and is worthwhile for pla", "headingPath": "", "sharpsignalDocId": 450}, {"page": 41, "score": 0.043494, "snippet": "When playing solo, you will use the 'shroud' - the cardboard sleeve designed to obscure the details (B) and results (C) of the card until you've made your choice for the option (A). → When drawing a chronicle card, keep that card face-down → Place the card face-down in the shroud so that you can't s", "headingPath": "Using Chronicles in Solo Player Mode", "sharpsignalDocId": 450}, {"page": 41, "score": 0.042674, "snippet": "Using Chronicles in Solo Player Mode When playing solo, you will use the “shroud” — the cardboard sleeve designed to obscure the details (B) and results (C) of the card until you’ve made your choice for the option (A). → When drawing a chronicle card, keep that card face-down → Place the card face-d", "headingPath": "", "sharpsignalDocId": 450}, {"page": 4, "score": 0.042361, "snippet": "For each color, place 1 less proficiency tile than the number of players in a stack on the main board beneath the related attribute circle. (e.g. in a 3-player game, use 2 tiles of each color, 12 total). From the community tray, place the 4 round, metal trigger tokens on the scoring track at the 30,", "headingPath": "Proficiency Tiles · Trigger Tokens · End-Game Trigger Cards · Community Tray · Promo Cards, Modules, and Expansions", "sharpsignalDocId": 450}, {"page": 9, "score": 0.030303, "snippet": "Some regions offer cards (traits, relics, monsters, companions, etc). Normally, when you acquire a card type, you may choose from the face-up card or draw blind from the face-down stack. If there are no face-up cards in a stack, simply flip the top face-down card to reveal it. If an effect would cau", "headingPath": "Acquiring Cards · Empowered Draw · Card Honor · IMPORTANT · Area Control Overview", "sharpsignalDocId": 450}, {"page": 55, "score": 0.029851, "snippet": "Mastery Tiles Once you have unlocked the proficiency, immediately place the mastery tile along the edge of the scoring track (alongside one of the numbered spaces between your scoring marker and the end-game marker). For example, if your scoring disc is at 63, and the end-game marker is at 75, you m", "headingPath": "", "sharpsignalDocId": 450}, {"page": 49, "score": 0.029412, "snippet": "Place your standee on the triangular starting position (spaces numbered 1-12 around the edge of the map) of your choice. There is no strategic difference between starting positions. Place 3 trigger tokens on the honor track spaces marked 30, 45, and 60. You will not need the 4th. For the purposes of", "headingPath": "Player Standee · Honor Tokens (Trigger Tokens) · Proficiency Tiles · NO CONTROLLED REGIONS", "sharpsignalDocId": 450}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 38, "quote": null, "headingPath": "", "sharpsignalDocId": 450}, {"page": 38, "quote": null, "headingPath": "In a Nutshell · Setup", "sharpsignalDocId": 450}, {"page": 6, "quote": null, "headingPath": "Initial Placement · Starting the Game · Turn Summary", "sharpsignalDocId": 450}, {"page": 41, "quote": null, "headingPath": "", "sharpsignalDocId": 450}, {"page": 41, "quote": null, "headingPath": "Using Chronicles in Solo Player Mode", "sharpsignalDocId": 450}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 450 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 450 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 0.88330 of 1928 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 25, 2026 16:17 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 Vindication — Rulebook (corpus doc 450) | Initial Placement · Starting the Game · Turn Summary | p.6 | 0.046486 (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 Vindication — Rulebook (corpus doc 450) | p.48 | 0.04526 (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 Vindication — Rulebook (corpus doc 450) | Using Chronicles in Solo Player Mode | p.41 | 0.043494 (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 Vindication — Rulebook (corpus doc 450) | p.41 | 0.042674 (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 Vindication — Rulebook (corpus doc 450) | Proficiency Tiles · Trigger Tokens · End-Game Trigger Cards · Community Tray · Promo Cards, Modules, and Expansions | p.4 | 0.042361 (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 Vindication — Rulebook (corpus doc 450) | Acquiring Cards · Empowered Draw · Card Honor · IMPORTANT · Area Control Overview | p.9 | 0.030303 (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 Vindication — Rulebook (corpus doc 450) | p.55 | 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 Vindication — Rulebook (corpus doc 450) | Player Standee · Honor Tokens (Trigger Tokens) · Proficiency Tiles · NO CONTROLLED REGIONS | p.49 | 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 80 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 Vindication — Rulebook (corpus doc 450) | Initial Placement · Starting the Game · Turn Summary | p.6 | #1 | 0.046486 (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 Vindication — Rulebook (corpus doc 450) | p.38 | #11 | 0.027757 (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 Vindication — Rulebook (corpus doc 450) | p.41 | #4 | 0.042674 (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 Vindication — Rulebook (corpus doc 450) | Fighting Ronak · 1) Generate Attributes · 2) Contribute Attributes · 3) Roll the Monster (black) and Attribute (white) Dice · The Guardian Returns · Visiting Tuuk-Tuuk | p.33 | #17 | 0.024697 (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 Vindication — Rulebook (corpus doc 450) | Mercenary Standees · Treachery Expansion Cards · Distribution of Treachery Cards · Messin' With Your Mojo · IMPORTANT: ADJACENCY | p.29 | #41 | 0.012346 (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)) | full-text | the re-ranker chose it |
| #6 | RULEBOOK Vindication — Rulebook (corpus doc 450) | In a Nutshell · Setup | p.38 | #10 | 0.027778 (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 Vindication — Rulebook (corpus doc 450) | Using Chronicles in Solo Player Mode | p.41 | #3 | 0.043494 (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 Vindication — Rulebook (corpus doc 450) | p.48 | #2 | 0.04526 (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 Vindication — Rulebook (corpus doc 450) | p.38 | no quote on the wire | |
| [2] | RULEBOOK Vindication — Rulebook (corpus doc 450) | In a Nutshell · Setup | p.38 | no quote on the wire |
| [3] | RULEBOOK Vindication — Rulebook (corpus doc 450) | Initial Placement · Starting the Game · Turn Summary | p.6 | no quote on the wire |
| [4] | RULEBOOK Vindication — Rulebook (corpus doc 450) | p.41 | no quote on the wire | |
| [5] | RULEBOOK Vindication — Rulebook (corpus doc 450) | Using Chronicles in Solo Player Mode | p.41 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 110 ms · first delta 4802 ms · total 9436 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 110 ms · ask 9324 ms · gateway work 9436 ms · total 9436 ms
- tokens in (the prompt the answerer read)
- 3440
- tokens out (what the answerer generated)
- 617
- tok/sec
- 131.8 tok/sec — 617 output tokens in 4.683 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 2s 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 381), 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.