You asked
How do I play?
Answered counted as answeredAsked with: Takbg-197405-en-1e
Answer in hand — your move.
🔧 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 103 ms · ask 4795 ms · total 10796 ms
- single-flight (PR-5)
- queued 5896 ms · generation 4900 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 1, "score": 0.04918, "snippet": "ak is a simple two-player strategy game. The goal is to build a road , a line of pieces connecting opposite sides of the board. T Some examples of winning roads You can play Tak on different sizes of board, from 3x3 to 6x6 and higher. The board on the back of this book is a 'hybrid 5x5' board, meani", "headingPath": "How to Play Tak · The Board · The Pieces", "sharpsignalDocId": 965}, {"page": 7, "score": 0.047875, "snippet": "Scoring is not strictly necessary, but it is a good way to track your results over several games. Because there is a slight advantage for the player who goes first, it's most equitable to play an even number of games, alternating who goes first. Your score for winning is equal to the size of the boa", "headingPath": "Scoring · Basic Strategy", "sharpsignalDocId": 965}, {"page": 6, "score": 0.04741, "snippet": "The goal of the game is to create a road , which is a line of pieces that joins opposite edges of the board (north to south or east to west). This is called a 'road win.' A road is mainly composed of flat stones. Your capstone can also be part of a road, but standing stones cannot. If either player ", "headingPath": "Winning the Game", "sharpsignalDocId": 965}, {"page": 8, "score": 0.046875, "snippet": "Tak is a super-portable game, especially if you learn to play without a board. Fancy Tak sets include boards of one kind or another: sturdy wooden boards, versatile leather boards, or boards painted onto cloth squares. Any decent tavern should have a 5x5 Tak board, or, in the less refined establishm", "headingPath": "Playing Without a Board", "sharpsignalDocId": 965}, {"page": 2, "score": 0.046176, "snippet": "Capstones: Capstones embody the better aspects of both standing and flat stones: they do count as part of a road, but they can't have another piece stacked on top. In addition, a capstone by itself has the ability to flatten a standing stone . The board starts empty. All pieces begin in the player's", "headingPath": "The Pieces · Setting Up · The Goal · Other Victory Conditions", "sharpsignalDocId": 965}, {"page": 3, "score": 0.046154, "snippet": "On your turn you may either place a piece in an empty space, or move one of the stacks under your control. If you place your last piece, or if you fill the last space on the board, the game ends immediately. See Winning the Game , below. Place: You can place a flat stone, a standing stone, or your c", "headingPath": "On Each Turn · Movement Examples", "sharpsignalDocId": 965}, {"page": 5, "score": 0.029851, "snippet": "Moving Capstones: Capstones move like any other piece, except that they have one extra option: By itself, a capstone can fl atten a standing stone. In this example, Black will move his capstone two steps, to flatten White's standing stone. 1: Black could move up to five of the pieces in this stack, ", "headingPath": "Movement Examples", "sharpsignalDocId": 965}, {"page": 4, "score": 0.029412, "snippet": "Moving a Taller Stack: At left is an example of making a move with a taller stack. White controls this stack, with a standing stone on top. She decides to move east. (Movement is always in a straight line.) 1: White can take as many as five pieces off the top of this stack. ( See carry limit, below.", "headingPath": "Movement Examples", "sharpsignalDocId": 965}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "The Pieces · Setting Up · The Goal · Other Victory Conditions", "sharpsignalDocId": 965}, {"page": 3, "quote": null, "headingPath": "On Each Turn · Movement Examples", "sharpsignalDocId": 965}, {"page": 6, "quote": null, "headingPath": "Additional Movement Rules", "sharpsignalDocId": 965}, {"page": 6, "quote": null, "headingPath": "Winning the Game", "sharpsignalDocId": 965}, {"page": 1, "quote": null, "headingPath": "How to Play Tak · The Board · The Pieces", "sharpsignalDocId": 965}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 965 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 965 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 0.88345 of 1939 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 02:51 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 Tak — Rulebook (corpus doc 965) | How to Play Tak · The Board · The Pieces | p.1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Tak — Rulebook (corpus doc 965) | Scoring · Basic Strategy | p.7 | 0.047875 (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 Tak — Rulebook (corpus doc 965) | Winning the Game | p.6 | 0.04741 (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 Tak — Rulebook (corpus doc 965) | Playing Without a Board | p.8 | 0.046875 (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 Tak — Rulebook (corpus doc 965) | The Pieces · Setting Up · The Goal · Other Victory Conditions | p.2 | 0.046176 (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 Tak — Rulebook (corpus doc 965) | On Each Turn · Movement Examples | p.3 | 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 Tak — Rulebook (corpus doc 965) | Movement Examples | p.5 | 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 Tak — Rulebook (corpus doc 965) | Movement Examples | p.4 | 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 9 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 Tak — Rulebook (corpus doc 965) | On Each Turn · Movement Examples | p.3 | #6 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Tak — Rulebook (corpus doc 965) | Playing Without a Board | p.8 | #4 | 0.046875 (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 Tak — Rulebook (corpus doc 965) | Winning the Game | p.6 | #3 | 0.04741 (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 Tak — Rulebook (corpus doc 965) | Additional Movement Rules | p.6 | #9 | 0.014493 (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 |
| #5 | RULEBOOK Tak — Rulebook (corpus doc 965) | Movement Examples | p.4 | #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 Tak — Rulebook (corpus doc 965) | The Pieces · Setting Up · The Goal · Other Victory Conditions | p.2 | #5 | 0.046176 (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 Tak — Rulebook (corpus doc 965) | Scoring · Basic Strategy | p.7 | #2 | 0.047875 (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 Tak — Rulebook (corpus doc 965) | How to Play Tak · The Board · The Pieces | p.1 | #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
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 Tak — Rulebook (corpus doc 965) | The Pieces · Setting Up · The Goal · Other Victory Conditions | p.2 | no quote on the wire |
| [2] | RULEBOOK Tak — Rulebook (corpus doc 965) | On Each Turn · Movement Examples | p.3 | no quote on the wire |
| [3] | RULEBOOK Tak — Rulebook (corpus doc 965) | Additional Movement Rules | p.6 | no quote on the wire |
| [4] | RULEBOOK Tak — Rulebook (corpus doc 965) | Winning the Game | p.6 | no quote on the wire |
| [5] | RULEBOOK Tak — Rulebook (corpus doc 965) | How to Play Tak · The Board · The Pieces | p.1 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 103 ms · first delta 1525 ms · total 10796 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 5896 ms · retrieval 103 ms · ask 4795 ms · gateway work 4900 ms · total 10796 ms
- tokens in (the prompt the answerer read)
- 3321
- tokens out (what the answerer generated)
- 655
- tok/sec
- 200.6 tok/sec — 655 output tokens in 3.266 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 20s ago)
- answerer host (measured by rulesage)
- reachable (for 24h, checked 3s 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 895), 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.