You asked
How do I setup the game?
Answered counted as answeredTo set up the game, follow these steps: 1. Prepare the game as you would for a standard game [1]. 2. Select 1 card from each of the Orange and Blue Ecosystem Cards and place them face up next to the Pools; return unused cards to the box [2][3]. 3. For your first game, it is recommended to use Cryptic Coloration (Orange #1) and Bountiful Caves (Blue #2) [2][3]. 4. Each player places an Ocean Board in front of them [2][3]. 5. Each player takes 5 Seashells [2][3]. 6. Place 2 Seashells on the Ocean Board and keep the other 3 nearby, outside the Ocean Board; return any unused Seashells to the box [3]. 7. The player who most recently saw a fish in the ocean takes the first turn [3]. 8. Play proceeds clockwise starting with the last player, where each player selects a Sealife Tile from the Sealife Pool and places it face up in any empty space on their Ocean Board [3]. 9. Once every player has taken a Sealife Tile, refill the empty Sealife Pool and begin the game [3].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:12b think:false 4eb23ef187e2
- timings
- search 235 ms · ask 10216 ms · total 10462 ms
- single-flight (PR-5)
- queued 0 ms · generation 10462 ms
- retrieval refs (raw)
- [{"page": 12, "score": 0.032522, "snippet": "Prepare a standard game (see page 3) EXCLUDING Ecosystem Cards. NOTE For your first game, use the provided Sealife Tile setup below.", "headingPath": "GAME SETUP", "sharpsignalDocId": 64}, {"page": 3, "score": 0.032266, "snippet": "· Shuffle all the Coral Tiles and place them into the Coral Pouch. Ensure the Coral Pouch is within easy reach of all players. Refer to the table below for the required number of Fish based on player count. Add the specified amount to the Fish Pouch and mix well. Place the Fish Pouch below the Coral", "headingPath": "GAME SETUP", "sharpsignalDocId": 64}, {"page": 3, "score": 0.016129, "snippet": "Select 1 card from each of the Orange and Blue Ecosystem Cards and place them face up next to the Pools. Return unused cards to the box. For your first game, we recommend using Cryptic Coloration (Orange #1) and Bountiful Caves (Blue #2) . NOTE Each player places an Ocean Board in front of them. Eac", "headingPath": "GAME SETUP", "sharpsignalDocId": 64}, {"page": 12, "score": 0.015625, "snippet": "Prepare as you would for a standard game (see page 3). Then, place the Lionfish Card next to your Ocean Board.", "headingPath": "GAME SETUP", "sharpsignalDocId": 64}, {"page": 12, "score": 0.015385, "snippet": "Whenever you need to spend a Seashell, you may instead draw a random Fish from the Fish Pouch and place it on the Lionfish Card. This can be done at any time during the game, as many times as you like. When placing Fish on the Lionfish Card, place the first 2 Fish in the two empty spaces at the top ", "headingPath": "GAMEPLAY CHANGES", "sharpsignalDocId": 64}, {"page": 4, "score": 0.015152, "snippet": "At the end of your turn, refill the empty spots in the Pools with new Tiles and Fish, ensuring that there are 5 Coral Tiles, 5 Sealife Tiles, and 5 Fish available in the Pools. Once fully refilled, the next player takes their turn.", "headingPath": "SPEND 2 SEASHELLS TO MOVE AN INCOMPLETE FISH", "sharpsignalDocId": 64}, {"page": 15, "score": 0.014925, "snippet": "Play using these modified game rules. If you break any of the modified rules during the game, you cannot complete the Achievement. | NO | MODIFIED RULES | COMPLETED | | 1 | Coral Tiles must be placed neighboring another Coral Tile(s), excluding the first Coral Tile. | | | 2 | Decrease the Tile and F", "headingPath": "ACHIEVEMENT MODE - MODIFIED GAME RULES", "sharpsignalDocId": 64}, {"page": 13, "score": 0.014706, "snippet": "In Shallow Sea, you can earn achievements whether you're playing solo or with multiple players. Use the Achievement Record Sheet below to track accomplishments for up to 4 players. Complete all achievements to reach Legendary Mariner and make your name shine! Follow these steps to play in Achievemen", "headingPath": "SCORING", "sharpsignalDocId": 64}]
- citations (raw)
- [{"page": 12, "quote": null, "headingPath": "GAME SETUP", "sharpsignalDocId": 64}, {"page": 3, "quote": null, "headingPath": "GAME SETUP", "sharpsignalDocId": 64}, {"page": 3, "quote": null, "headingPath": "GAME SETUP", "sharpsignalDocId": 64}]
- 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 22, 2026 01:15
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 Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | p.12 | 0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 132 |
| #2 | RULEBOOK Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | p.3 | 0.032266 (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 Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | 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 |
| #4 | RULEBOOK Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | p.12 | 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) | 110 |
| #5 | RULEBOOK Shallow Sea — Rulebook (corpus doc 64) | GAMEPLAY CHANGES | p.12 | 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 Shallow Sea — Rulebook (corpus doc 64) | SPEND 2 SEASHELLS TO MOVE AN INCOMPLETE FISH | p.4 | 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) | 231 |
| #7 | RULEBOOK Shallow Sea — Rulebook (corpus doc 64) | ACHIEVEMENT MODE - MODIFIED GAME RULES | p.15 | 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 Shallow Sea — Rulebook (corpus doc 64) | SCORING | p.13 | 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 Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | p.12 | no quote on the wire |
| [2] | RULEBOOK Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | p.3 | no quote on the wire |
| [3] | RULEBOOK Shallow Sea — Rulebook (corpus doc 64) | GAME SETUP | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 235 ms · first delta n/a · total 10462 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 235 ms · ask 10216 ms · gateway work 10462 ms · total 10462 ms
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 37s ago)
- stream path
- not recorded — this ruling predates the stream-path column (V41)
- 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
- SERVED — setup-shaped and this game's approved setup checklist is offered above
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 11), 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.