You asked
How do I play?
Answered counted as answeredAsked with: Pirates of Maracaibobg-397385-en-1e
The table has its answer — dice up.
🔧 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 80 ms · ask 7819 ms · total 16257 ms
- single-flight (PR-5)
- queued 8356 ms · generation 7901 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.048916, "snippet": "The game takes place over three rounds , with players taking turns in clockwise order. During a player's turn, they move their Ship token across the Caribbean and then perform the actions shown where they stop. Each round ends once a player has reached Maracaibo, and after 3 rounds, the game will en", "headingPath": "GAMEPLAY · PLAYER TURN", "sharpsignalDocId": 427}, {"page": 10, "score": 0.047643, "snippet": "If your Ship is on any card in the right-most column of cards, you can move onto the Gulf using 1 movement. This is the first space a ship reaches on the Exploration board. You must stop at this space once your Ship moves onto it. You may Upgrade your ship as described on page 9. Then, you may choos", "headingPath": "The Gulf · Maracaibo · END OF ROUND", "sharpsignalDocId": 427}, {"page": 1, "score": 0.045285, "snippet": "A game by Alexander Pfister, Ryan Hendrickson, and Ralph Bienert For 1 - 4 players ages 12 and up · playing time: 25 minutes per player The Caribbean at the end of the 17th Century: Profitable trade routes, burgeoning industry, and an aggressive contest for power by various distant nations has creat", "headingPath": "Rulebook Rulebook", "sharpsignalDocId": 427}, {"page": 12, "score": 0.045002, "snippet": "You compete against Jordan, who is an automated opponent controlled by a deck of Solo cards. Follow the setup instructions for a two-player game; you are in control of one of the selected colors, and Jordan is in control of the other selected color. The only exceptions are: The Figurehead Market onl", "headingPath": "INTRODUCTION · SETUP · GAMEPLAY", "sharpsignalDocId": 427}, {"page": 4, "score": 0.032258, "snippet": "Optionally select one or more modules that will modify the setup and rules for the game. It is recommended that no module be used until all players are familiar with the game. A list of modules can be found on page 14. Place the Exploration board between the players. Sort the Tier I cards by type (a", "headingPath": "SETUP", "sharpsignalDocId": 427}, {"page": 5, "score": 0.031746, "snippet": "Each player places their components in the following locations: Ship token in the starting zone, to the left of the Caribbean. Explorer on the starting space of the Exploration track at the bottom of the Exploration board. Score token on the 0 space of the score track at the top of the Exploration b", "headingPath": "SETUP", "sharpsignalDocId": 427}, {"page": 14, "score": 0.030769, "snippet": "Select one or more of the following Modules and modify the setup and gameplay rules accordingly: When creating the Tier I deck, place the Location cards face down, and all other cards face up. Shuffle the deck and then place the cards into the Caribbean so that the Location cards stay face down. Pla", "headingPath": "MODULES · Setup · Gameplay · Solo Gameplay", "sharpsignalDocId": 427}, {"page": 14, "score": 0.030303, "snippet": "Ignore the 'Pay 1 doubloon rule when landing on a Card with opponent ships'; instead, do the following: When you end ship movement on a card with any opponent ships, immediately enter combat. All players with ships on this card roll 1 die. There is no reroll and ignore the color of die. Apply perman", "headingPath": "Gameplay · Solo Gameplay · Setup · Endgame Scoring", "sharpsignalDocId": 427}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "GAMEPLAY · PLAYER TURN", "sharpsignalDocId": 427}, {"page": 12, "quote": null, "headingPath": "INTRODUCTION · SETUP · GAMEPLAY", "sharpsignalDocId": 427}, {"page": 7, "quote": null, "headingPath": "", "sharpsignalDocId": 427}, {"page": 7, "quote": null, "headingPath": "2. Perform Actions · 1. Increase Treasure Value", "sharpsignalDocId": 427}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 427 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 427 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 0.90658 of 2280 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 24, 2026 17:19 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 Pirates of Maracaibo — Rulebook (corpus doc 427) | GAMEPLAY · PLAYER TURN | 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 Pirates of Maracaibo — Rulebook (corpus doc 427) | The Gulf · Maracaibo · END OF ROUND | p.10 | 0.047643 (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 Pirates of Maracaibo — Rulebook (corpus doc 427) | Rulebook Rulebook | p.1 | 0.045285 (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 Pirates of Maracaibo — Rulebook (corpus doc 427) | INTRODUCTION · SETUP · GAMEPLAY | p.12 | 0.045002 (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 Pirates of Maracaibo — Rulebook (corpus doc 427) | SETUP | p.4 | 0.032258 (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 Pirates of Maracaibo — Rulebook (corpus doc 427) | SETUP | p.5 | 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 |
| #7 | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | MODULES · Setup · Gameplay · Solo Gameplay | p.14 | 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 |
| #8 | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | Gameplay · Solo Gameplay · Setup · Endgame Scoring | p.14 | 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 |
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 34 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 Pirates of Maracaibo — Rulebook (corpus doc 427) | GAMEPLAY · PLAYER TURN | 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 Pirates of Maracaibo — Rulebook (corpus doc 427) | MODULES · Setup · Gameplay · Solo Gameplay | p.14 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | SETUP | p.5 | #6 | 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 |
| #4 | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | p.7 | #10 | 0.029469 (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 | |
| #5 | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | 2. Perform Actions · 1. Increase Treasure Value | p.7 | #13 | 0.013699 (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 Pirates of Maracaibo — Rulebook (corpus doc 427) | SETUP | p.4 | #5 | 0.032258 (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 |
| #7 | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | INTRODUCTION · SETUP · GAMEPLAY | p.12 | #4 | 0.045002 (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 Pirates of Maracaibo — Rulebook (corpus doc 427) | Gameplay | p.14 | #11 | 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 |
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 Pirates of Maracaibo — Rulebook (corpus doc 427) | GAMEPLAY · PLAYER TURN | p.6 | no quote on the wire |
| [2] | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | INTRODUCTION · SETUP · GAMEPLAY | p.12 | no quote on the wire |
| [3] | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | p.7 | no quote on the wire | |
| [4] | RULEBOOK Pirates of Maracaibo — Rulebook (corpus doc 427) | 2. Perform Actions · 1. Increase Treasure Value | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 80 ms · first delta 2430 ms · total 16257 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 8356 ms · retrieval 80 ms · ask 7819 ms · gateway work 7901 ms · total 16257 ms
- tokens in (the prompt the answerer read)
- 3549
- tokens out (what the answerer generated)
- 703
- tok/sec
- 131.2 tok/sec — 703 output tokens in 5.358 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 356), 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.