You asked
How do I set up the game?
Answered counted as answered1. Place the clearing (the game board) in the center of the play area, within reach of all players [1]. 2. Place the 14 reference cards next to the clearing [1]. 3. Everyone takes a cave card and places it in front of themselves [1]. 4. Set the 3 winter cards aside [1]. 5. Shuffle the remaining cards and return a certain number of them to the game box, unseen, based on the player count: 30 cards for 2 players, 20 cards for 3 players, 10 cards for 4 players, and none (play with all cards) for 5 players [1]. 6. Divide the remaining cards into three face-down piles of similar size [1]. 7. Shuffle two winter cards into one of the piles and put the third winter card on top of that pile [1]. 8. Place the other two piles on top of the pile containing the winter cards to form a deck, and place it on the left side of the clearing [1]. 9. Everyone draws 6 cards into their hand [1].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 225 ms · ask 3966 ms · total 4203 ms
- single-flight (PR-5)
- queued 0 ms · generation 4203 ms
- retrieval refs (raw)
- [{"page": 2, "score": 0.032787, "snippet": "2 1 Place the clearing (i.e., the game board) in the center of the play area, within reach of all players. Place the 14 reference cards next to it. 2 Everyone: take a cave card and place it in front of yourself. 3 Set the 3 winter cards aside. Shuffle the remaining cards and return a certain number ", "headingPath": "Components · Setup · Game Flow · A) Draw Two Cards · B) Play a Card and Check the Clearing", "sharpsignalDocId": 130}, {"page": 3, "score": 0.016129, "snippet": "When taking this action, draw two cards, one at a time , and add them to your hand. For each card you draw with this action, you have the choice of either taking a face-down card from the top of the deck or a face-up card from the clearing (which is empty at the start of the game). Important: You ar", "headingPath": "A) Drawing Two Cards · Winter Cards · B) Playing a Card and Checking the Clearing", "sharpsignalDocId": 130}, {"page": 4, "score": 0.015873, "snippet": "4 To play a card from your hand, you must first pay its cost by placing that many (other) cards from your hand face up into the clearing . When playing a split card, choose one half to play and pay only its cost. Normally, it does not matter which cards you discard as payment. Some species, however,", "headingPath": "B) Playing a Card and Checking the Clearing · Playing a Card · Trees · Example:", "sharpsignalDocId": 130}, {"page": 7, "score": 0.015625, "snippet": "When the 3rd winter card is revealed, the game ends immediately and you proceed to scoring. You may not finish your turn. Total the points of all visible cards in your forest, and add the number of cards under your cave, if any. This is your score. If you are unsure how a specific card scores, consu", "headingPath": "End of Game · Scoring · Scoring example: · Top/Bottom · Left/Right · Trees", "sharpsignalDocId": 130}, {"page": 5, "score": 0.015385, "snippet": "Instead of playing a tree, you may play any card from your hand face down as a universal tree sapling . Like a tree, a tree sapling provides a card slot on each of its four sides. However, it does not belong to any of the eight tree species and is not considered a tree species of its own. The split ", "headingPath": "Tree Sapling · Animals, Plants, and Mushrooms · Effect and Bonus", "sharpsignalDocId": 130}, {"page": 1, "score": 0.015152, "snippet": "A card game by Kosch for 2-5 players, ages 10 and up Playing time: 60 minutes Life is bustling in the local forest: Animals scurry around the clearings looking for edible plants and insects. Some enjoy the dense treetops, while others prefer the lush undergrowth and only feel comfortable in the shel", "headingPath": "Forest Shuffle · Object of the Game · Components", "sharpsignalDocId": 130}, {"page": 8, "score": 0.014925, "snippet": "Sycamore Oak Designer: Kosch Illustrations: Toni Llobet, Judit Piella Graphik design: Klemens Franz | atelier198 R&D: Maren Holderbaum Translation: Sonja Hüttinger Forestry consultant: Felix Behnke Kosch says: Caro, without your inspiration this game would not have been invented. You always find the", "headingPath": "Tree symbols · Credits · Effect and Bonus", "sharpsignalDocId": 130}, {"page": 6, "score": 0.014706, "snippet": "Most cards provide an instant effect that you use once immediately after playing it. Some of them allow you to put cards in your cave. l e Mushrooms, however, provide a permanent effect , which you can use for the rest of the game, beginning on your next turn. Chaffi nch if on a Beech Mushrooms have", "headingPath": "There are two types of effects: · Mushrooms · Bonus · Checking the Clearing", "sharpsignalDocId": 130}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "Components · Setup · Game Flow · A) Draw Two Cards · B) Play a Card and Check the Clearing", "sharpsignalDocId": 130}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
- 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)
- debug row retained until
- Oct 31, 2026 14:03
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 Forest Shuffle — Rulebook (corpus doc 130) | Components · Setup · Game Flow · A) Draw Two Cards · B) Play a Card and Check the Clearing | p.2 | 0.032787 (at the 2-arm ceiling (0.03279) — the top of a 2-arm fuse; whether more arms ran here was never recorded) | 300 |
| #2 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | A) Drawing Two Cards · Winter Cards · B) Playing a Card and Checking the Clearing | p.3 | 0.016129 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | B) Playing a Card and Checking the Clearing · Playing a Card · Trees · Example: | p.4 | 0.015873 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #4 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | End of Game · Scoring · Scoring example: · Top/Bottom · Left/Right · Trees | p.7 | 0.015625 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #5 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | Tree Sapling · Animals, Plants, and Mushrooms · Effect and Bonus | p.5 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #6 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | Forest Shuffle · Object of the Game · Components | p.1 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #7 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | Tree symbols · Credits · Effect and Bonus | p.8 | 0.014925 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #8 | RULEBOOK Forest Shuffle — Rulebook (corpus doc 130) | There are two types of effects: · Mushrooms · Bonus · Checking the Clearing | p.6 | 0.014706 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
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 Forest Shuffle — Rulebook (corpus doc 130) | Components · Setup · Game Flow · A) Draw Two Cards · B) Play a Card and Check the Clearing | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 225 ms · first delta 2573 ms · total 4203 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 225 ms · ask 3966 ms · gateway work 4203 ms · total 4203 ms
- tokens in (the prompt the answerer read)
- 3073
- tokens out (what the answerer generated)
- 238
- tok/sec
- 149.5 tok/sec — 238 output tokens in 1.592 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 27s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 52), 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.