You asked
How do I play?
Answered counted as answeredAsked with: Witchstonebg-318560-en-1e
🔧 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 70 ms · ask 6882 ms · total 15825 ms
- single-flight (PR-5)
- queued 8872 ms · generation 6953 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.048387, "snippet": "93 93 93 93 89 92 91 90 89 92 91 90 89 92 91 90 89 92 91 90 The player to their right ( i.e., the last one in the order of play ) places their Big Witch figure standing upright on one of the 4 tower spaces in the Crystal ball. 88 88 88 88 87 87 87 87 83 84 86 85 83 84 86 85 83 84 86 85 83 84 86 85 W", "headingPath": "\u0007 Players' Preparations", "sharpsignalDocId": 962}, {"page": 6, "score": 0.047123, "snippet": "When you activate the Scroll action, you get 1 Scroll from the display. If there is currently only one Scroll action available to you, you obtain the first displayed Scroll ( position 1 5 furthest away from the draw pile ). Display the Scroll face up in front of you. , If you activate multiple Scrol", "headingPath": "Get 1 Scroll from the display. Multiple Scroll actions give you more choices. · There are two kinds of Scrolls: Reinforcing Spells and Prophecies. 1. Reinforcing Spells", "sharpsignalDocId": 962}, {"page": 3, "score": 0.047073, "snippet": "The starting player begins the game by choosing one of their 5 hex tiles from behind their screen and laying it over 2 empty spaces of their Cauldron. Six spaces of the Cauldron contain printed action symbols that may not be covered. Spaces that contain Crystals cannot be covered by hex tiles either", "headingPath": "Course of the Game", "sharpsignalDocId": 962}, {"page": 8, "score": 0.046696, "snippet": "For advanced players who play with a group that includes beginners, it is also possible to play with handicaps . At the start of the game, mix your hex tiles face down and return 4 of them to the game box without looking at them. Depending on the handicap level, you play with fewer tiles to choose f", "headingPath": "\u0007 For Mixed Player Groups · Martino Chiacchiera", "sharpsignalDocId": 962}, {"page": 3, "score": 0.046239, "snippet": "1 . \u0007 Everybody chooses a player color. Take the following components in your color: the screen , the Magic cauldron , 15 hex tiles , 12 Witches and Wizards - hereafter collectively called 'Witches' (1 Big Witch and 11 small ones ), 20 Energy units , 3 Owl Counters 1 position marker , the animal mar", "headingPath": "\u0007 Players' Preparations", "sharpsignalDocId": 962}, {"page": 4, "score": 0.046154, "snippet": "100/ (+ 1 black crystal) into the cauldron; mix 0 93 92 91 90 89 88 87 86 85 84 83 82 81 80 79 78 77 76 Take game components in one player color; put put 5 of them face up behind your screen; place counters the scoring track , pentagram , and magic wand . Shuffle the scrolls and put 6 of them face u", "headingPath": "\u0007 Multiple actions of one action type through clusters", "sharpsignalDocId": 962}, {"page": 2, "score": 0.045002, "snippet": "Mix the magic chips; put 1 face up on each location and the other 5 face up below the vial rack. Put the special hex tiles face down in the center of the pentagram; place 1 tile face up on each of the 3 hexagonal spaces. Put the owl tiles, stacked in ascending order, on the owl spaces. Determine the", "headingPath": "", "sharpsignalDocId": 962}, {"page": 2, "score": 0.029412, "snippet": "Create your Magic Spells with the help of your Cauldron and grow a network of Magic Energy around the stone. Send out your Witches, scoop the Magic Crystals from your Cauldron, and make good use of the Pentagram and the Magic Wand. But don't forget to keep an eye on the Prophecies in order to ensure", "headingPath": "", "sharpsignalDocId": 962}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "\u0007 Players' Preparations", "sharpsignalDocId": 962}, {"page": 3, "quote": null, "headingPath": "\u0007 Players' Preparations", "sharpsignalDocId": 962}, {"page": 2, "quote": null, "headingPath": "", "sharpsignalDocId": 962}, {"page": 3, "quote": null, "headingPath": "Course of the Game", "sharpsignalDocId": 962}, {"page": 8, "quote": null, "headingPath": "\u0007 For Mixed Player Groups · Martino Chiacchiera", "sharpsignalDocId": 962}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 962 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 962 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 0.89067 of 2497 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 13, 2026 20:53
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 Witchstone — Rulebook (corpus doc 962) | Players' Preparations | p.3 | 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 |
| #2 | RULEBOOK Witchstone — Rulebook (corpus doc 962) | Get 1 Scroll from the display. Multiple Scroll actions give you more choices. · There are two kinds of Scrolls: Reinforcing Spells and Prophecies. 1. Reinforcing Spells | p.6 | 0.047123 (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 Witchstone — Rulebook (corpus doc 962) | Course of the Game | p.3 | 0.047073 (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 Witchstone — Rulebook (corpus doc 962) | For Mixed Player Groups · Martino Chiacchiera | p.8 | 0.046696 (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 Witchstone — Rulebook (corpus doc 962) | Players' Preparations | p.3 | 0.046239 (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 Witchstone — Rulebook (corpus doc 962) | Multiple actions of one action type through clusters | p.4 | 0.046154 (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 Witchstone — Rulebook (corpus doc 962) | p.2 | 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 | |
| #8 | RULEBOOK Witchstone — Rulebook (corpus doc 962) | p.2 | 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 31 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 Witchstone — Rulebook (corpus doc 962) | For Mixed Player Groups · Martino Chiacchiera | p.8 | #4 | 0.046696 (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 Witchstone — Rulebook (corpus doc 962) | Course of the Game | p.3 | #3 | 0.047073 (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 Witchstone — Rulebook (corpus doc 962) | Double Reinforcing Spell | p.7 | #10 | 0.027253 (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 Witchstone — Rulebook (corpus doc 962) | Players' Preparations | p.3 | #1 | 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 |
| #5 | RULEBOOK Witchstone — Rulebook (corpus doc 962) | p.2 | #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 Witchstone — Rulebook (corpus doc 962) | Object of the Game · Set-up | p.2 | #14 | 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 Witchstone — Rulebook (corpus doc 962) | Players' Preparations | p.3 | #5 | 0.046239 (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 Witchstone — Rulebook (corpus doc 962) | p.2 | #7 | 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 |
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 Witchstone — Rulebook (corpus doc 962) | Players' Preparations | p.3 | no quote on the wire |
| [2] | RULEBOOK Witchstone — Rulebook (corpus doc 962) | Players' Preparations | p.3 | no quote on the wire |
| [3] | RULEBOOK Witchstone — Rulebook (corpus doc 962) | p.2 | no quote on the wire | |
| [4] | RULEBOOK Witchstone — Rulebook (corpus doc 962) | Course of the Game | p.3 | no quote on the wire |
| [5] | RULEBOOK Witchstone — Rulebook (corpus doc 962) | For Mixed Player Groups · Martino Chiacchiera | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 70 ms · first delta 2947 ms · total 15825 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 8872 ms · retrieval 70 ms · ask 6882 ms · gateway work 6953 ms · total 15825 ms
- tokens in (the prompt the answerer read)
- 4240
- tokens out (what the answerer generated)
- 804
- tok/sec
- 203.6 tok/sec — 804 output tokens in 3.948 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s ago)
- 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 710), 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.