You asked
How do I play?
Answered counted as answeredAsked with: Verdantbg-334065-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 193 ms · ask 9070 ms · total 9265 ms
- single-flight (PR-5)
- queued 0 ms · generation 9265 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.048916, "snippet": "Beginning with the starting player and proceeding clockwise around the table, players will take turns drafting Plant Cards, Room Cards, and Item Tokens and adding them into their expanding home. Players will make spatial matches and use Nurture Tokens to care for their plant collection as the game p", "headingPath": "Gameplay Overview · Game Start · 1. Select a card and a token.", "sharpsignalDocId": 677}, {"page": 16, "score": 0.048139, "snippet": "Set up and play a multiplayer game of Verdant following the standard rules with one rules modification from the list below. Any player who plays the game will fill in their Achievement shape under the rule modification that was used. Whenever you fill in a shape, fill in a leaf on your plant on the ", "headingPath": "Achievements (rules modifications)", "sharpsignalDocId": 677}, {"page": 14, "score": 0.046642, "snippet": "Grow your own plant by gaining Achievements as you play Verdant! Achievements can be earned and tracked as you play multiplayer and solo games. Below is the Achievement Plant Track where up to 4 players can keep track of their overall progress. You may begin gaining Achievements at any time. To do s", "headingPath": "Verdant Achievements · Scenarios", "sharpsignalDocId": 677}, {"page": 9, "score": 0.045957, "snippet": "Once you have completed all of the previous steps, you will refill the market by adding a card and token from the appropriate deck and bag, respectively. In addition, you will add the new Green Thumb Token to the remaining card in the column from which you selected your card. Your turn is now comple", "headingPath": "7. Refill the Market.", "sharpsignalDocId": 677}, {"page": 16, "score": 0.045228, "snippet": "Set up and play a multiplayer game of Verdant using the standard rules. Any player who plays the game will fill in a maximum of one Achievement shape in their column if they earned an Achievement. Whenever you fill in a shape, fill in a leaf on your plant on the Achievement Plant Track (page 14). Sc", "headingPath": "Achievements (standard game)", "sharpsignalDocId": 677}, {"page": 4, "score": 0.045139, "snippet": "Once you have played Verdant with the standard setup, you can add more scoring variety to the game by adding end game scoring Goal Cards! Shuffle each of the 3 Goal Card decks (Plants, Items, and Rooms) and draw 1 card from each deck. Return all other Goal Cards to the box - they will not be used th", "headingPath": "Advanced Setup *", "sharpsignalDocId": 677}, {"page": 7, "score": 0.043697, "snippet": "You will be creating a 5 X 3 grid of cards in your personal play area. This growing tableau of cards is referred to as your home. You must place cards according to the following placement rules: Cards must be placed orthogonally adjacent to other cards. Plant Cards must be placed next to Room Cards,", "headingPath": "2. Place the card into your home. · 3. Check lighting conditions and collect verdancy. · Lighting Conditions", "sharpsignalDocId": 677}, {"page": 10, "score": 0.029877, "snippet": "The game ends when all players' homes have 15 cards (a completed 5 X 3 grid). Note : each player will play exactly 13 turns. Record scores on the Scorepad for the following: Each player scores each completed Plant Card in their home. For each completed plant, players score the number of points indic", "headingPath": "End Game & Scoring · 1. Completed Plants 1 · 2. Extra Verdancy on Incomplete Plants 2 · 4 · 5. Furniture and Pets 5 · 6", "sharpsignalDocId": 677}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 677}, {"page": 6, "quote": null, "headingPath": "Gameplay Overview · Game Start · 1. Select a card and a token.", "sharpsignalDocId": 677}, {"page": 9, "quote": null, "headingPath": "6. Place any unused Item Tokens in Storage and check Green Thumb Token limit. · Green Thumb Token Actions", "sharpsignalDocId": 677}, {"page": 9, "quote": null, "headingPath": "7. Refill the Market.", "sharpsignalDocId": 677}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 677 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 677 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 0.91848 of 2760 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 23, 2026 18:39 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 Verdant — Rulebook (corpus doc 677) | Gameplay Overview · Game Start · 1. Select a card and a token. | p.6 | 0.048916 (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 Verdant — Rulebook (corpus doc 677) | Achievements (rules modifications) | p.16 | 0.048139 (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 Verdant — Rulebook (corpus doc 677) | Verdant Achievements · Scenarios | p.14 | 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 |
| #4 | RULEBOOK Verdant — Rulebook (corpus doc 677) | 7. Refill the Market. | p.9 | 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 |
| #5 | RULEBOOK Verdant — Rulebook (corpus doc 677) | Achievements (standard game) | p.16 | 0.045228 (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 Verdant — Rulebook (corpus doc 677) | Advanced Setup * | p.4 | 0.045139 (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 Verdant — Rulebook (corpus doc 677) | 2. Place the card into your home. · 3. Check lighting conditions and collect verdancy. · Lighting Conditions | p.7 | 0.043697 (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 Verdant — Rulebook (corpus doc 677) | End Game & Scoring · 1. Completed Plants 1 · 2. Extra Verdancy on Incomplete Plants 2 · 4 · 5. Furniture and Pets 5 · 6 | p.10 | 0.029877 (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 27 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 Verdant — Rulebook (corpus doc 677) | Achievements (rules modifications) | p.16 | #2 | 0.048139 (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 Verdant — Rulebook (corpus doc 677) | Gameplay Overview · Game Start · 1. Select a card and a token. | p.6 | #1 | 0.048916 (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 Verdant — Rulebook (corpus doc 677) | Setup | p.4 | #10 | 0.02971 (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 Verdant — Rulebook (corpus doc 677) | Achievements (standard game) | p.16 | #5 | 0.045228 (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 Verdant — Rulebook (corpus doc 677) | 6. Place any unused Item Tokens in Storage and check Green Thumb Token limit. · Green Thumb Token Actions | p.9 | #12 | 0.028309 (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 |
| #6 | RULEBOOK Verdant — Rulebook (corpus doc 677) | Verdant Achievements · Scenarios | p.14 | #3 | 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 |
| #7 | RULEBOOK Verdant — Rulebook (corpus doc 677) | Advanced Setup * | p.4 | #6 | 0.045139 (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 Verdant — Rulebook (corpus doc 677) | 7. Refill the Market. | p.9 | #4 | 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 |
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 Verdant — Rulebook (corpus doc 677) | Setup | p.4 | no quote on the wire |
| [2] | RULEBOOK Verdant — Rulebook (corpus doc 677) | Gameplay Overview · Game Start · 1. Select a card and a token. | p.6 | no quote on the wire |
| [3] | RULEBOOK Verdant — Rulebook (corpus doc 677) | 6. Place any unused Item Tokens in Storage and check Green Thumb Token limit. · Green Thumb Token Actions | p.9 | no quote on the wire |
| [4] | RULEBOOK Verdant — Rulebook (corpus doc 677) | 7. Refill the Market. | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 193 ms · first delta 3072 ms · total 9265 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 193 ms · ask 9070 ms · gateway work 9265 ms · total 9265 ms
- tokens in (the prompt the answerer read)
- 2991
- tokens out (what the answerer generated)
- 822
- tok/sec
- 134.3 tok/sec — 822 output tokens in 6.120 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 33s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, 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 610), 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.