You asked
How do I setup the game?
Answered counted as answeredAsked with: Roads & Boatsbg-875-en-1e
So says the rulebook. So plays the table.
🔧 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 171 ms · ask 4721 ms · total 4894 ms
- single-flight (PR-5)
- queued 0 ms · generation 4894 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 7, "score": 0.048412, "snippet": "sources have been used elsewhere. A river may not run off the map. Place the plastic sheet over the map. Make sure the entire map is covered. Fix the sheet in place with adhesive tape that can be removed easily after playing. Covering the Map Put the praying figures in a cup and take them out one by", "headingPath": "SETTING/.notdefUP · DETERMININGTHESTARTINGSEQUENCE · STARTINGPLACESANDRESOURCES · ORDEROFPLAY", "sharpsignalDocId": 680}, {"page": 6, "score": 0.032258, "snippet": "a game board in two parts, featuring the temple row on top (number 1 in the figure on the right), the wonder (2), the phase chart indicating the four phase of the game (3), and the sequence chart (4) with numbers 1 to 6; one more glass stone (to use on the phase chart); rule book and scenario book; ", "headingPath": "SETTING/.notdefUP · FIRST-TIMEPREPARATIONS · SETTINGUP · CREATINGTHEWORLD", "sharpsignalDocId": 680}, {"page": 6, "score": 0.031746, "snippet": "There are two ways to make a map. Inexperienced players are advised to select one of the maps provided in the scenario book. More experienced players may want to makeamapoftheirownusingthefollowingrules. Determine how big the map is going to be. As a rough estimate, use about ten land tiles per play", "headingPath": "SETTING/.notdefUP", "sharpsignalDocId": 680}, {"page": 3, "score": 0.03125, "snippet": "4 In , each player builds up a civi- lization over a long period of time, like in many other games. Unlike most games, however, is not about warfare, population growth, city or statebuilding. The emphasis instead is on logistics, or rather: on transport. Each player starts the game with three donkey", "headingPath": "", "sharpsignalDocId": 680}, {"page": 17, "score": 0.030769, "snippet": "N most cases, all players play simultaneously. However, on some occasions a player may want to perform an action before or after another player, so that conflict arises. In that case it is necessary to determineaplaying sequence. Other types of conflict do not occur. It is impossible under any circu", "headingPath": "CONFLICT · CHOOSINGAPLAYINGSEQUENCE", "sharpsignalDocId": 680}, {"page": 13, "score": 0.030303, "snippet": "Some buildings can only be built after the appropriate research has been performed. See the research rules for details. If a player builds a mine, fill the appropriate bag with 3 gold nuggets and 3 iron ore counters (or 4/0, 0/4, 5/5 if the appropriate research has been performed, see page 16). The ", "headingPath": "BUILDING · MINES · BUILDINGNEWMINESHAFTS · OILRIGS · ROADS", "sharpsignalDocId": 680}, {"page": 5, "score": 0.030159, "snippet": "OADS & BOATS is played in turns. Each turn consists of four phases. In each phase, all players play simultaneously. Players first go through a phase in which all buildings produce goods. There are which produce goods every production phase (such as a woodcutter, which produces one pile of trunks eve", "headingPath": "SUMMARY · MATERIAL", "sharpsignalDocId": 680}, {"page": 18, "score": 0.029851, "snippet": "last, Blue cannot predict which mine will be closed off, and therefore cannot prevent it. Blue moves a donkey with two boards to A. The donkey on the mine stays there and the third Blue donkey moves to the second mine. Yellow moves the donkey with two stones to mine 2. Yellow's other donkeys stay pu", "headingPath": "CONFLICT", "sharpsignalDocId": 680}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "SETTING/.notdefUP · FIRST-TIMEPREPARATIONS · SETTINGUP · CREATINGTHEWORLD", "sharpsignalDocId": 680}, {"page": 7, "quote": null, "headingPath": "SETTING/.notdefUP · DETERMININGTHESTARTINGSEQUENCE · STARTINGPLACESANDRESOURCES · ORDEROFPLAY", "sharpsignalDocId": 680}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 680 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 680 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 0.90935 of 1401 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 26, 2026 00:05 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 Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP · DETERMININGTHESTARTINGSEQUENCE · STARTINGPLACESANDRESOURCES · ORDEROFPLAY | p.7 | 0.048412 (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 Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP · FIRST-TIMEPREPARATIONS · SETTINGUP · CREATINGTHEWORLD | p.6 | 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 |
| #3 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP | p.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)) | 300 |
| #4 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | p.3 | 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 Roads & Boats — Rulebook (corpus doc 680) | CONFLICT · CHOOSINGAPLAYINGSEQUENCE | p.17 | 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 Roads & Boats — Rulebook (corpus doc 680) | BUILDING · MINES · BUILDINGNEWMINESHAFTS · OILRIGS · ROADS | p.13 | 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 Roads & Boats — Rulebook (corpus doc 680) | SUMMARY · MATERIAL | p.5 | 0.030159 (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 Roads & Boats — Rulebook (corpus doc 680) | CONFLICT | 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 |
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 32 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 Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP · FIRST-TIMEPREPARATIONS · SETTINGUP · CREATINGTHEWORLD | p.6 | #2 | 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 |
| #2 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP · DETERMININGTHESTARTINGSEQUENCE · STARTINGPLACESANDRESOURCES · ORDEROFPLAY | p.7 | #1 | 0.048412 (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 Roads & Boats — Rulebook (corpus doc 680) | SUMMARY · MATERIAL | p.5 | #7 | 0.030159 (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 Roads & Boats — Rulebook (corpus doc 680) | CONFLICT | p.18 | #8 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | END/.notdefOF/.notdefTHE/.notdefGAME · VICTORYDETERMINATION | p.19 | #9 | 0.029727 (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 |
| #6 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | p.19 | #11 | 0.029116 (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 | |
| #7 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | p.3 | #4 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it | |
| #8 | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP | p.6 | #3 | 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 |
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 Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP · FIRST-TIMEPREPARATIONS · SETTINGUP · CREATINGTHEWORLD | p.6 | no quote on the wire |
| [2] | RULEBOOK Roads & Boats — Rulebook (corpus doc 680) | SETTING/.notdefUP · DETERMININGTHESTARTINGSEQUENCE · STARTINGPLACESANDRESOURCES · ORDEROFPLAY | p.7 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 171 ms · first delta 2756 ms · total 4894 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 171 ms · ask 4721 ms · gateway work 4894 ms · total 4894 ms
- tokens in (the prompt the answerer read)
- 2998
- tokens out (what the answerer generated)
- 417
- tok/sec
- 199.3 tok/sec — 417 output tokens in 2.092 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 42s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 3s 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
- 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 613), 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.