You asked
How do I play?
Answered counted as answeredAsked with: Wyrmspanbg-410201-en-1e
The book has spoken.
🔧 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 84 ms · ask 5413 ms · total 5499 ms
- single-flight (PR-5)
- queued 0 ms · generation 5499 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.046671, "snippet": "Wyrmspan takes place over 4 rounds. Each round, players take several turns in clockwise order, beginning with the player who has the start player marker. Players continue taking turns until they decide to pass; this typically occurs when a player has used all of their coins or they do not have any d", "headingPath": "GAMEPLAY", "sharpsignalDocId": 52}, {"page": 16, "score": 0.045945, "snippet": "Go to stonemaiergames.com/games/wyrmspan/rules-faq", "headingPath": "WANT TO WATCH A HOW-TO-PLAY VIDEO OR READ THE FAQ?", "sharpsignalDocId": 52}, {"page": 16, "score": 0.044949, "snippet": "Post it on the Wyrmspan Facebook group, on BoardGameGeek, or in the Wyrmspan channel of the Stonemaier Games Discord server: stonemaiergames.com/discord", "headingPath": "HAVE A QUESTION WHILE PLAYING OR A STORY TO SHARE?", "sharpsignalDocId": 52}, {"page": 5, "score": 0.044563, "snippet": "PLAY A CAVE CARD INTO 1 OF YOUR CAVES. 1 The first space in each cave is already excavated, so over the course of the game you may excavate the 2nd, 3rd, and 4th spaces in each cave. Any cave card can be placed in any cave; the colors of the cave cards are purely for aesthetics. Select the left-most", "headingPath": "EXCAVATE", "sharpsignalDocId": 52}, {"page": 4, "score": 0.043184, "snippet": "During a game of Wyrmspan, you will build a sanctuary for dragons. Your sanctuary begins with 3 excavated spaces-the leftmost space in your Crimson Cavern, your Golden Grotto, and your Amethyst Abyss. Throughout the game, you will build out these 3 caves from left to right, first excavating each emp", "headingPath": "OVERVIEW", "sharpsignalDocId": 52}, {"page": 5, "score": 0.032258, "snippet": "Select one action on your player mat (excavate, entice, or explore), move your adventurer there, pay the cost of that action (place the coin/eggs on the action), and then perform the action. If the public supply of eggs or coins runs low, players may return excess tokens from their mats to the suppl", "headingPath": "ON YOUR TURN", "sharpsignalDocId": 52}, {"page": 2, "score": 0.030769, "snippet": "Places their player mat in front of them (see the image on the right). A Places their starting resources in their player area (left of their mat). B Places their starting egg on 1 of the 2 nest icons on their player mat. C 3 dragon cards (drawn from the deck) & 3 cave cards (drawn from the deck) Cho", "headingPath": "EACH PLAYER THEN:", "sharpsignalDocId": 52}, {"page": 2, "score": 0.030303, "snippet": "Gain the 3 tokens in any combination of gold, crystal, meat, and milk. TIP: We recommend that players first look at their starting cards, then choose which resources to gain from the public supply based on those starting cards. Typically (though not always) players will wish to gain resources that m", "headingPath": "3 resources of their choice", "sharpsignalDocId": 52}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "EACH PLAYER THEN:", "sharpsignalDocId": 52}, {"page": 5, "quote": null, "headingPath": "ON YOUR TURN", "sharpsignalDocId": 52}, {"page": 5, "quote": null, "headingPath": "EXCAVATE", "sharpsignalDocId": 52}, {"page": 14, "quote": null, "headingPath": "TURN END", "sharpsignalDocId": 52}, {"page": 11, "quote": null, "headingPath": "ACTIVATING ABILITIES MULTIPLE", "sharpsignalDocId": 52}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 52 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 52 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 0.87306 of 1158 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 25, 2026 10:29 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 Wyrmspan — Rulebook (corpus doc 52) | GAMEPLAY | p.4 | 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 |
| #2 | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | WANT TO WATCH A HOW-TO-PLAY VIDEO OR READ THE FAQ? | p.16 | 0.045945 (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)) | 50 |
| #3 | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | HAVE A QUESTION WHILE PLAYING OR A STORY TO SHARE? | p.16 | 0.044949 (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)) | 152 |
| #4 | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | EXCAVATE | p.5 | 0.044563 (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 Wyrmspan — Rulebook (corpus doc 52) | OVERVIEW | p.4 | 0.043184 (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 Wyrmspan — Rulebook (corpus doc 52) | ON YOUR TURN | p.5 | 0.032258 (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 Wyrmspan — Rulebook (corpus doc 52) | EACH PLAYER THEN: | p.2 | 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 Wyrmspan — Rulebook (corpus doc 52) | 3 resources of their choice | p.2 | 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 |
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 36 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 Wyrmspan — Rulebook (corpus doc 52) | TURN END | p.14 | #13 | 0.028577 (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 |
| #2 | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | In Either Order: | p.5 | #11 | 0.029206 (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 Wyrmspan — Rulebook (corpus doc 52) | EXCAVATE | p.5 | #4 | 0.044563 (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 Wyrmspan — Rulebook (corpus doc 52) | ACTIVATING ABILITIES MULTIPLE | p.11 | #10 | 0.029643 (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 Wyrmspan — Rulebook (corpus doc 52) | OVERVIEW | p.4 | #5 | 0.043184 (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 |
| #6 | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | DRAGON ABILITIES | p.7 | #9 | 0.029911 (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 Wyrmspan — Rulebook (corpus doc 52) | EACH PLAYER THEN: | p.2 | #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 Wyrmspan — Rulebook (corpus doc 52) | ON YOUR TURN | p.5 | #6 | 0.032258 (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 |
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 Wyrmspan — Rulebook (corpus doc 52) | EACH PLAYER THEN: | p.2 | no quote on the wire |
| [2] | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | ON YOUR TURN | p.5 | no quote on the wire |
| [3] | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | EXCAVATE | p.5 | no quote on the wire |
| [4] | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | TURN END | p.14 | no quote on the wire |
| [5] | RULEBOOK Wyrmspan — Rulebook (corpus doc 52) | ACTIVATING ABILITIES MULTIPLE | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 84 ms · first delta 2504 ms · total 5499 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 84 ms · ask 5413 ms · gateway work 5499 ms · total 5499 ms
- tokens in (the prompt the answerer read)
- 1962
- tokens out (what the answerer generated)
- 398
- tok/sec
- 135.5 tok/sec — 398 output tokens in 2.938 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 33s ago)
- answerer host (measured by rulesage)
- reachable (for 24h, checked 5s 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 4), 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.