You asked
How do I play?
Answered counted as answeredAsked with: Botanikbg-271529-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 98 ms · ask 4864 ms · total 11461 ms
- single-flight (PR-5)
- queued 6496 ms · generation 4965 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.04918, "snippet": "3 SETUP ROUNDS OF PLAY PLAYING A TILE Example of the game setup Place the Registry between the two players; Place the Meca pawn next to the Registry; Each player takes a Source tile and places it faceup in front of them; Mix the remaining tiles to form one or more face-down stacks; Draw 5 tiles rand", "headingPath": "", "sharpsignalDocId": 1031}, {"page": 3, "score": 0.048387, "snippet": "y is s. er ry e e \u0007 Place the Registry between the two players; in front of them; \u0007 Mix the remaining tiles to form one or more face-down stacks; \u0007 Place the Meca pawn next to the Registry; \u0007 Each player takes a Source tile and places it faceup \u0007 Draw 5 tiles randomly and place one on the central ro", "headingPath": "3x 3x 3x In each color, there are 7 types of tiles: · SETUP · Example of the game setup · PLAYING A TILE", "sharpsignalDocId": 1031}, {"page": 7, "score": 0.046898, "snippet": "7 The game ends as soon as a player has taken and played the last tile. Finish the Round normally and then proceed to scoring. SCORING EXAMPLE The player with the most points wins. In case of a tie, the player with the most tiles in their machine wins. If still tied, have another go! 1) This yellow ", "headingPath": "", "sharpsignalDocId": 1031}, {"page": 2, "score": 0.046642, "snippet": "I n the hushed intimacy of her laboratory, the eminent researcher Beatrix Bury has just discovered a technology allowing to mechanically generate all kinds of edibles. Subtropical plants, stellar potatoes, Orion mandarins, this new technology opens a way to save the people of Forharms, prisoners of ", "headingPath": "PARTICULAR NATURE OF THE GAME · The tiles are distributed as follows: · 3x 3x 3x In each color, there are 7 types of tiles:", "sharpsignalDocId": 1031}, {"page": 7, "score": 0.046635, "snippet": "The game ends as soon as a player has taken and played the last tile. Finish the Round normally and then proceed to scoring. 1 · Remove from the game all tiles that are not connected to the pipe network starting at your Source; 2 · \u0007 Earn 1 victory point (VP) for each tile in a group of at least 3 a", "headingPath": "MECA-BOTANIST TILES", "sharpsignalDocId": 1031}, {"page": 6, "score": 0.045476, "snippet": "Below some examples of valid constructions. And some examples of forbidden constructions. Contact only at the corners is not enough. Here, the pipe network would be 100% closed. If you place a Meca-Botanist on your side or on a central pile, the rules stay the same. However, when a Meca-Botanist is ", "headingPath": "BUILDING YOUR MACHINE · MECA-BOTANIST TILES", "sharpsignalDocId": 1031}, {"page": 5, "score": 0.030303, "snippet": "Place the chosen tile on any central pile, there are no restrictions. Check if the tiles in that column (on your side and your opponent's) still have a link to the newly placed tile. Any tile that has no link anymore is immediately released. It is possible to release 0, 1, or, 2 tiles in one go. Her", "headingPath": "ON A CENTRAL PILE · BUILDING YOUR MACHINE", "sharpsignalDocId": 1031}, {"page": 3, "score": 0.029412, "snippet": "It’s in the urgency of a threatened world that the scientist puts two of her best teams in charge of developing her plan… that can seem quite demanding at times. Each team is engrossed in its mission and Beatrix’s laboratory becomes the battlefield of fierce competition to produce the best performin", "headingPath": "", "sharpsignalDocId": 1031}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "", "sharpsignalDocId": 1031}, {"page": 3, "quote": null, "headingPath": "3x 3x 3x In each color, there are 7 types of tiles: · SETUP · Example of the game setup · PLAYING A TILE", "sharpsignalDocId": 1031}, {"page": 4, "quote": null, "headingPath": "ON YOUR SIDE", "sharpsignalDocId": 1031}, {"page": 5, "quote": null, "headingPath": "ON A CENTRAL PILE · BUILDING YOUR MACHINE", "sharpsignalDocId": 1031}, {"page": 6, "quote": null, "headingPath": "BUILDING YOUR MACHINE · MECA-BOTANIST TILES", "sharpsignalDocId": 1031}, {"page": 7, "quote": null, "headingPath": "MECA-BOTANIST TILES", "sharpsignalDocId": 1031}, {"page": 7, "quote": null, "headingPath": "", "sharpsignalDocId": 1031}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1031 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1031 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 0.88853 of 2180 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 13:36 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 Botanik — Rulebook (corpus doc 1031) | p.3 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 | |
| #2 | RULEBOOK Botanik — Rulebook (corpus doc 1031) | 3x 3x 3x In each color, there are 7 types of tiles: · SETUP · Example of the game setup · PLAYING A TILE | 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 |
| #3 | RULEBOOK Botanik — Rulebook (corpus doc 1031) | p.7 | 0.046898 (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 Botanik — Rulebook (corpus doc 1031) | PARTICULAR NATURE OF THE GAME · The tiles are distributed as follows: · 3x 3x 3x In each color, there are 7 types of tiles: | p.2 | 0.046642 (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 Botanik — Rulebook (corpus doc 1031) | MECA-BOTANIST TILES | p.7 | 0.046635 (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 Botanik — Rulebook (corpus doc 1031) | BUILDING YOUR MACHINE · MECA-BOTANIST TILES | p.6 | 0.045476 (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 Botanik — Rulebook (corpus doc 1031) | ON A CENTRAL PILE · BUILDING YOUR MACHINE | p.5 | 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 Botanik — Rulebook (corpus doc 1031) | p.3 | 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 11 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 Botanik — Rulebook (corpus doc 1031) | p.3 | #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 | |
| #2 | RULEBOOK Botanik — Rulebook (corpus doc 1031) | MECA-BOTANIST TILES | p.7 | #5 | 0.046635 (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 Botanik — Rulebook (corpus doc 1031) | ON A CENTRAL PILE · BUILDING YOUR MACHINE | p.5 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Botanik — Rulebook (corpus doc 1031) | PARTICULAR NATURE OF THE GAME · The tiles are distributed as follows: · 3x 3x 3x In each color, there are 7 types of tiles: | p.2 | #4 | 0.046642 (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 Botanik — Rulebook (corpus doc 1031) | ON YOUR SIDE | p.4 | #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 |
| #6 | RULEBOOK Botanik — Rulebook (corpus doc 1031) | BUILDING YOUR MACHINE · MECA-BOTANIST TILES | p.6 | #6 | 0.045476 (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 Botanik — Rulebook (corpus doc 1031) | p.7 | #3 | 0.046898 (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 Botanik — Rulebook (corpus doc 1031) | 3x 3x 3x In each color, there are 7 types of tiles: · SETUP · Example of the game setup · PLAYING A TILE | p.3 | #2 | 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 |
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 Botanik — Rulebook (corpus doc 1031) | p.3 | no quote on the wire | |
| [2] | RULEBOOK Botanik — Rulebook (corpus doc 1031) | 3x 3x 3x In each color, there are 7 types of tiles: · SETUP · Example of the game setup · PLAYING A TILE | p.3 | no quote on the wire |
| [3] | RULEBOOK Botanik — Rulebook (corpus doc 1031) | ON YOUR SIDE | p.4 | no quote on the wire |
| [4] | RULEBOOK Botanik — Rulebook (corpus doc 1031) | ON A CENTRAL PILE · BUILDING YOUR MACHINE | p.5 | no quote on the wire |
| [5] | RULEBOOK Botanik — Rulebook (corpus doc 1031) | BUILDING YOUR MACHINE · MECA-BOTANIST TILES | p.6 | no quote on the wire |
| [6] | RULEBOOK Botanik — Rulebook (corpus doc 1031) | MECA-BOTANIST TILES | p.7 | no quote on the wire |
| [7] | RULEBOOK Botanik — Rulebook (corpus doc 1031) | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 98 ms · first delta 1300 ms · total 11461 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 6496 ms · retrieval 98 ms · ask 4864 ms · gateway work 4965 ms · total 11461 ms
- tokens in (the prompt the answerer read)
- 2977
- tokens out (what the answerer generated)
- 728
- tok/sec
- 201.6 tok/sec — 728 output tokens in 3.612 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 2s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 1s 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 961), 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.