You asked
How do I setup the game?
Answered counted as answeredAsked with: Aquaticabg-283393-en-1e
🔧 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 100 ms · ask 3272 ms · total 3374 ms
- single-flight (PR-5)
- queued 0 ms · generation 3374 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.048916, "snippet": "Place the Game Board (1) in the centre of the table. Shuffle the Ocean Characters (6) deck and place it on the bottom row of the board. Take 6 cards from the top of the deck and fill the Character's row (as shown in the picture). Shuffle the Locations deck (3) and place it in the middle row of the b", "headingPath": "GAME BOARD SETUP", "sharpsignalDocId": 545}, {"page": 7, "score": 0.046751, "snippet": "Each player takes one of the player boards (2), and places it in front of them, face up. Each player chooses one of the available symbols and takes the set of 6 starting Character cards and 4 Trained Mantas with their chosen symbol. In further games you can start using the King cards (4). In basic m", "headingPath": "PLAYER SETUP", "sharpsignalDocId": 545}, {"page": 27, "score": 0.046696, "snippet": "SETUP Remove the 1 set of Ocean Character cards with the symbol in the bottom right corner from the Ocean Character deck and return it to the box (you will be playing only with one remaining set of cards). Shuffle the King card deck, draw 3 cards, and choose 1 to use. Place the remaining King cards ", "headingPath": "SOLO MODE · HOW TO PLAY · END OF THE GAME", "sharpsignalDocId": 545}, {"page": 16, "score": 0.031746, "snippet": "If you don't want to Buy a Location, you can Conquer it. This requires a certain amount of Power. Choose 1 Location card from the board, pay the amount of Power shown at the top of the card, and insert it into an empty slot of your player board so that the top Depth is in the circle. You need to hav", "headingPath": "3. Conquer Location", "sharpsignalDocId": 545}, {"page": 15, "score": 0.03125, "snippet": "You can buy the discovered Locations from the tribes that are living there. To buy a Location, follow these steps: Choose 1 Location from the Ocean board. Pay the number of Coins shown at the top of the Location card. Insert the Location into an empty slot of your player board so that the top Depth ", "headingPath": "2. Buy Location", "sharpsignalDocId": 545}, {"page": 19, "score": 0.030769, "snippet": "If you play the Researcher as your main action, it lets you raise a total of 3 Depths. This means that you can raise 1 single Location 3 Depths, or spread the effect between any number of different Locations. 1 Slide Location 'A' up once and slide Location 'B' up twice. 3 Example 2. You are using a ", "headingPath": "4. Raise Location 1", "sharpsignalDocId": 545}, {"page": 18, "score": 0.029851, "snippet": "As one of your additional actions, you are using a ready Manta with the raise effect. It lets you raise 1 depth. 1 As a King, you are trying to bring Prosperity to your realm by exploiting Locations you have discovered. When you exploit a Location, you 'raise' resources from it to your Kingdom. By r", "headingPath": "3. Conquer Location · 4. Raise Location 1", "sharpsignalDocId": 545}, {"page": 23, "score": 0.029412, "snippet": "Scouting allows you to explore the Ocean and find new Locations for the players to buy or conquer. When you scout, follow these steps: Take every Location from the top Location row and place them in the discard pile. Move every Location from the bottom row to the top row. In case there are more then", "headingPath": "5. Scout", "sharpsignalDocId": 545}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "GAME BOARD SETUP", "sharpsignalDocId": 545}, {"page": 7, "quote": null, "headingPath": "PLAYER SETUP", "sharpsignalDocId": 545}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 545 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 545 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 0.88372 of 860 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 14, 2026 06:06
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 Aquatica — Rulebook (corpus doc 545) | GAME BOARD SETUP | 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 Aquatica — Rulebook (corpus doc 545) | PLAYER SETUP | p.7 | 0.046751 (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 Aquatica — Rulebook (corpus doc 545) | SOLO MODE · HOW TO PLAY · END OF THE GAME | p.27 | 0.046696 (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 Aquatica — Rulebook (corpus doc 545) | 3. Conquer Location | p.16 | 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 |
| #5 | RULEBOOK Aquatica — Rulebook (corpus doc 545) | 2. Buy Location | p.15 | 0.03125 (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 Aquatica — Rulebook (corpus doc 545) | 4. Raise Location 1 | p.19 | 0.030769 (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 Aquatica — Rulebook (corpus doc 545) | 3. Conquer Location · 4. Raise Location 1 | p.18 | 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)) | 300 |
| #8 | RULEBOOK Aquatica — Rulebook (corpus doc 545) | 5. Scout | p.23 | 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 33 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 Aquatica — Rulebook (corpus doc 545) | GAME BOARD SETUP | 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 |
| #2 | RULEBOOK Aquatica — Rulebook (corpus doc 545) | PLAYER SETUP | p.7 | #2 | 0.046751 (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 Aquatica — Rulebook (corpus doc 545) | p.2 | #12 | 0.027638 (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 Aquatica — Rulebook (corpus doc 545) | 4. Score | p.22 | #15 | 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 |
| #5 | RULEBOOK Aquatica — Rulebook (corpus doc 545) | 3. Conquer Location | p.16 | #4 | 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 |
| #6 | RULEBOOK Aquatica — Rulebook (corpus doc 545) | ADVANCED MODE | p.26 | #18 | 0.013889 (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 |
| #7 | RULEBOOK Aquatica — Rulebook (corpus doc 545) | SIMPLE DIVING, DEEP STRATEGIES RULEBOOK | p.2 | #10 | 0.028783 (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 Aquatica — Rulebook (corpus doc 545) | SOLO MODE · HOW TO PLAY · END OF THE GAME | p.27 | #3 | 0.046696 (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 Aquatica — Rulebook (corpus doc 545) | GAME BOARD SETUP | p.6 | no quote on the wire |
| [2] | RULEBOOK Aquatica — Rulebook (corpus doc 545) | PLAYER SETUP | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 100 ms · first delta 1932 ms · total 3374 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 100 ms · ask 3272 ms · gateway work 3374 ms · total 3374 ms
- tokens in (the prompt the answerer read)
- 1854
- tokens out (what the answerer generated)
- 293
- tok/sec
- 207.9 tok/sec — 293 output tokens in 1.409 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s 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)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 477), 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.