You asked
How do I set up the game?
Answered counted as answeredAsked with: Robinson Crusoe: Adventures on the Cursed Islandbg-121921-en-1e
🔧 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 260 ms · ask 21749 ms · total 476043 ms
- single-flight (PR-5)
- queued 454025 ms · generation 22018 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.047493, "snippet": "Place the board in the middle of the table. 1 Decide which scenario to play. We recommend the introductory scenario, Castaways , for your first game. Place the chosen Scenario sheet next to the board and place the Round marker on the first space of the round track. More information on Scenario sheet", "headingPath": "4 Character sheets · SETUP", "sharpsignalDocId": 300}, {"page": 27, "score": 0.046671, "snippet": "If players think a scenario is too hard for them, they can make it easier by: Adding the Dog. This is especially recommended for 3 players. Adding Friday Drawing more Starting Equipment Using fewer Event cards with the book symbol and more Event cards with the adventure symbol when creating the deck", "headingPath": "EASIER GAME · HARDER GAME · RANDOM WRECKAGE CARDS", "sharpsignalDocId": 300}, {"page": 5, "score": 0.046343, "snippet": "Shuffle the Beast cards and place them face down next to the board to form the Beast deck. Note: The space on the game board is for the Hunting deck, which will be created during the game. Shuffle the Mystery cards. Place them face down next to the board. 9 Take the 11 Island tiles. 10 Find tile #8 ", "headingPath": "SETUP", "sharpsignalDocId": 300}, {"page": 11, "score": 0.03125, "snippet": "Unless specified otherwise, each Action may be carried out multiple times during a round, by one or more characters. The Threat Action requires 1 or 2 Action pawns, as shown on the card. Hunting requires 2 Action pawns and can only be carried out if there is at least 1 Beast card in the Hunting deck", "headingPath": "GAME FLOW · HOW TO ASSIGN PAWNS · REQUIREMENTS FOR PLACING ACTION PAWNS", "sharpsignalDocId": 300}, {"page": 16, "score": 0.030769, "snippet": "With each Build Action, you can attempt to build a Shelter, a Roof, a Palisade, Weapons, or turn an Invention into an Item. A Shelter protects the group during the night, and the Roof and Palisade protect from the weather and dangerous animals. Weapons are needed for hunting and defense, and Inventi", "headingPath": "3. BUILD · ROLLING THE ACTION DICE", "sharpsignalDocId": 300}, {"page": 12, "score": 0.030303, "snippet": "and assigned to the Action; required Inventions must have already been built (have their Item side face up) and any required Weapon level must exist. You cannot use anything from the Future Resources space to plan (or carry out) your Actions. If the requirements cannot be fulfilled during the Planni", "headingPath": "GAME FLOW · Example: · Examples:", "sharpsignalDocId": 300}, {"page": 10, "score": 0.029851, "snippet": "In this Phase, you gain 1 resource from each source on the Island tile that contains the camp. Each source of food / produces 1 food and each source of wood produces 1 wood . The number of resources produced may be modified by the presence of various markers and/or tokens (see page 13) or Event card", "headingPath": "III. PRODUCTION PHASE · IV. ACTION PHASE", "sharpsignalDocId": 300}, {"page": 24, "score": 0.029412, "snippet": "Many Items built during the game have a permanent effect and need not be used explicitly (e.g. the Medicine Item or Shortcut ). These Items list the effect on both sides of the card. Others have a one-time effect (e.g. Knife or Bow ) that applies as soon as the Item is available. These cards only de", "headingPath": "STARTING EQUIPMENT, ITEMS, AND TREASURES", "sharpsignalDocId": 300}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "4 Character sheets · SETUP", "sharpsignalDocId": 300}, {"page": 5, "quote": null, "headingPath": "SETUP", "sharpsignalDocId": 300}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 300 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 300 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)
- debug row retained until
- Nov 6, 2026 14:16
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. How much wider that pool was is set gateway-side and is NOT REPORTED for this ruling, and neither are the answerer's final rows — so rulesage has nothing of its own to show beside these.
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 Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | 4 Character sheets · SETUP | p.4 | 0.047493 (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 Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | EASIER GAME · HARDER GAME · RANDOM WRECKAGE CARDS | p.27 | 0.046671 (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 Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | SETUP | p.5 | 0.046343 (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 Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | GAME FLOW · HOW TO ASSIGN PAWNS · REQUIREMENTS FOR PLACING ACTION PAWNS | p.11 | 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 |
| #5 | RULEBOOK Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | 3. BUILD · ROLLING THE ACTION DICE | p.16 | 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 |
| #6 | RULEBOOK Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | GAME FLOW · Example: · Examples: | p.12 | 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 |
| #7 | RULEBOOK Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | III. PRODUCTION PHASE · IV. ACTION PHASE | p.10 | 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 Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | STARTING EQUIPMENT, ITEMS, AND TREASURES | p.24 | 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.
the passages the answerer read: NOT RECORDED for this ruling. Any of three things leaves this empty, and they are all different from the answerer having had nothing to read: this ask may never have reached a gateway at all; a multi-book ask keeps each book's own context on that book's own page rather than here; or the gateway build that answered may simply not report it. What this NEVER means is that the answerer read nothing — an answer was composed from passages either way, and their absence here is a gap in what we were told, not in what it read.
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 Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | 4 Character sheets · SETUP | p.4 | no quote on the wire |
| [2] | RULEBOOK Robinson Crusoe: Adventures on the Cursed Island — Rulebook (corpus doc 300) | SETUP | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 260 ms · first delta 15563 ms · total 476043 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 454025 ms · retrieval 260 ms · ask 21749 ms · gateway work 22018 ms · total 476043 ms
- tokens in (the prompt the answerer read)
- 4003
- tokens out (what the answerer generated)
- 874
- tok/sec
- 136.6 tok/sec — 874 output tokens in 6.397 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)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 228), 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.