You asked
How do I play?
Answered counted as answeredAsked with: Zendobg-6830-en-1e
Settled. Play on.
🔧 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 174 ms · ask 3781 ms · total 3957 ms
- single-flight (PR-5)
- queued 0 ms · generation 3957 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 2, "score": 0.047938, "snippet": "Initial Koans: As the Master, start the game off by building two koans in the middle of the playing field. One should have the Buddha-nature according to your rule; place a white stone next to it. The other should not; place a black stone next to it. You will be marking all of the koans in this way ", "headingPath": "Page 2 · 1. Build a Koan · 2. Say 'Master' or 'Mondo'", "sharpsignalDocId": 1121}, {"page": 7, "score": 0.046154, "snippet": "When you are selected to be the Master for a game of Zendo, you take on a very different role than you would if you were playing as one of the students. You will not be trying to guess the secret rule; instead, you will create the secret rule that the others are trying to guess. You will spend much ", "headingPath": "ADVICE FOR MASTERS", "sharpsignalDocId": 1121}, {"page": 1, "score": 0.045957, "snippet": "Designed by Kory Heath Does a dog have Buddha-nature? This is the most serious question of all. If you answer yes or no You lose your own Buddha-nature. Zendo is a game of inductive logic in which the Master creates a rule and the Students attempt to discover it by building and studying small arrang", "headingPath": "HOW to PLAY · Introduction:", "sharpsignalDocId": 1121}, {"page": 7, "score": 0.045956, "snippet": "The best rule-of-thumb is to remember that rules are usually more difficult than they sound. If you are trying to decide between a few different versions of a rule, go with the one that seems the simplest. It's much better to choose a rule that's too easy than one that's too difficult. An easy rule ", "headingPath": "ADVICE FOR MASTERS", "sharpsignalDocId": 1121}, {"page": 8, "score": 0.045285, "snippet": "large piece lying on its side with a medium piece inside it counts as a stack; it's dangerous to make this kind of decision 'on the fly' , in the middle of a game. You may sometimes be tempted to change a rule in the middle of a game, perhaps in the attempt to salvage a rule that's turning out to be", "headingPath": "Page 8", "sharpsignalDocId": 1121}, {"page": 1, "score": 0.031746, "snippet": "5 Rainbow Stashes, 60 tokens (20 each of black, white, and a third color) Setup: Choose someone to be the Master. The other players are the Students. Give each Student a black and a white stone, to serve as 'answering stones' . The remaining black and white stones are 'marking stones' , and the ston", "headingPath": "Equipment:", "sharpsignalDocId": 1121}, {"page": 2, "score": 0.030303, "snippet": "Make a Guess: If you have any guessing stones, you may choose to spend one or more of them to try to guess the Master's rule. Give a guessing stone to the Master and then state your guess as clearly as you can. Clarify the Guess: If the Master does not fully understand your guess, or if it is ambigu", "headingPath": "3. Guess the Rule (optional)", "sharpsignalDocId": 1121}, {"page": 7, "score": 0.030092, "snippet": "the Buddha-nature if it contains one or more red pieces and they're all upright' , then say that! If what you mean is 'a koan has the Buddha-nature if it contains no red pieces, or if it contains red pieces and they're all upright' , then say that. This is the approach that I recommend-try to be as ", "headingPath": "Page 7", "sharpsignalDocId": 1121}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 1, "quote": null, "headingPath": "HOW to PLAY · Introduction:", "sharpsignalDocId": 1121}, {"page": 1, "quote": null, "headingPath": "Equipment:", "sharpsignalDocId": 1121}, {"page": 2, "quote": null, "headingPath": "Page 2 · 1. Build a Koan · 2. Say 'Master' or 'Mondo'", "sharpsignalDocId": 1121}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1121 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1121 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 0.88638 of 1417 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 6, 2026 11:02 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 Zendo — Rulebook (corpus doc 1121) | Page 2 · 1. Build a Koan · 2. Say 'Master' or 'Mondo' | p.2 | 0.047938 (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 Zendo — Rulebook (corpus doc 1121) | ADVICE FOR MASTERS | p.7 | 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 |
| #3 | RULEBOOK Zendo — Rulebook (corpus doc 1121) | HOW to PLAY · Introduction: | p.1 | 0.045957 (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 Zendo — Rulebook (corpus doc 1121) | ADVICE FOR MASTERS | p.7 | 0.045956 (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 Zendo — Rulebook (corpus doc 1121) | Page 8 | p.8 | 0.045285 (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 Zendo — Rulebook (corpus doc 1121) | Equipment: | p.1 | 0.031746 (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 Zendo — Rulebook (corpus doc 1121) | 3. Guess the Rule (optional) | 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 |
| #8 | RULEBOOK Zendo — Rulebook (corpus doc 1121) | Page 7 | p.7 | 0.030092 (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 28 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 Zendo — Rulebook (corpus doc 1121) | HOW to PLAY · Introduction: | p.1 | #3 | 0.045957 (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 Zendo — Rulebook (corpus doc 1121) | Page 2 · 1. Build a Koan · 2. Say 'Master' or 'Mondo' | p.2 | #1 | 0.047938 (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 Zendo — Rulebook (corpus doc 1121) | ADVICE FOR MASTERS | p.7 | #4 | 0.045956 (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 Zendo — Rulebook (corpus doc 1121) | Page 10 | p.10 | #11 | 0.028986 (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 Zendo — Rulebook (corpus doc 1121) | Page 3 | p.3 | #10 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Zendo — Rulebook (corpus doc 1121) | ADVICE FOR MASTERS | p.7 | #2 | 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 |
| #7 | RULEBOOK Zendo — Rulebook (corpus doc 1121) | Page 7 | p.7 | #8 | 0.030092 (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 |
| #8 | RULEBOOK Zendo — Rulebook (corpus doc 1121) | Equipment: | p.1 | #6 | 0.031746 (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 Zendo — Rulebook (corpus doc 1121) | HOW to PLAY · Introduction: | p.1 | no quote on the wire |
| [2] | RULEBOOK Zendo — Rulebook (corpus doc 1121) | Equipment: | p.1 | no quote on the wire |
| [3] | RULEBOOK Zendo — Rulebook (corpus doc 1121) | Page 2 · 1. Build a Koan · 2. Say 'Master' or 'Mondo' | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 174 ms · first delta 1685 ms · total 3957 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 174 ms · ask 3781 ms · gateway work 3957 ms · total 3957 ms
- tokens in (the prompt the answerer read)
- 3308
- tokens out (what the answerer generated)
- 446
- tok/sec
- 200.9 tok/sec — 446 output tokens in 2.220 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 52s ago)
- answerer host (measured by rulesage)
- reachable (for 24h, checked 4s 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 1051), 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.