You asked
Walk me through the full setup procedure step by step.
Answered counted as answeredAsked with: Marco Polo II: In the Service of the Khanbg-283948-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 299 ms · ask 11436 ms · total 11745 ms
- single-flight (PR-5)
- queued 0 ms · generation 11745 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.032787, "snippet": "1 Choose a color. Take the player board of that color and place it in front of you. 3 Take the 11 trading posts in your color and place 1 on each space with a trading post in the top-left corner of your board. 4 Draw 1 starting contract and place it faceup on one of the two active contract spaces on", "headingPath": "Player Setup", "sharpsignalDocId": 372}, {"page": 6, "score": 0.032258, "snippet": "Keep the following in mind when resolving actions: You use only your own dice, not other players' dice. You must use as many dice as are shown on the action space you want to use. You can place your dice on either unoccupied spaces or occupied blue spaces, not occupied brown spaces. In order to use ", "headingPath": "Actions · How is an action carried out? · 1. Books · Sequence: · 2. Choose 1 of the available offers.", "sharpsignalDocId": 372}, {"page": 5, "score": 0.031746, "snippet": "for ted cts If you are already familiar with The Voyages of Marco Polo , then you can skip some sections of this rulebook, which are the same as the corresponding rules in the original game. Be sure to read any rules marked with the gold seal ; the rules and actions described in these sections are e", "headingPath": "Player Setup · About The Rules · Introduction · A Game Turn", "sharpsignalDocId": 372}, {"page": 3, "score": 0.03125, "snippet": "(see page 15 for 2-3 player setup rules) Goal card front Offer tile 3 Place the coins (68 coins in denominations of 1, 5, and 10) next to the board to form a supply. Coins are not component-limited; use a substitute if they run out. 5 Randomly place 1 city bonus marker on each of the 6 cities with c", "headingPath": "16 guild", "sharpsignalDocId": 372}, {"page": 5, "score": 0.030769, "snippet": "There are 7 actions you can resolve: Books (pages 6 & 7) Khan ' s Favor (page 7) Guild Seals (page 7) Travel (pages 8-10) Contracts (page 10) Special Cities (page 11) City Cards (page 11) . Additionally, there are 6 Bonus Actions you can resolve, either before or after resolving your normal action (", "headingPath": "The Board", "sharpsignalDocId": 372}, {"page": 14, "score": 0.030303, "snippet": "Whenever a player uses the Travel action, the first player for the next round can change. If you use a Travel action space that is higher than or equal to any previously-used Travel action spaces, you become the first player for the next round. If you are the new first player, take the hourglass to ", "headingPath": "The First Player · Example:", "sharpsignalDocId": 372}, {"page": 8, "score": 0.029851, "snippet": "The Travel action lets you move your figure on the board. The Travel action has 3 separate action spaces. Because these actions are separate, even if you have already used 1 of them this round, you can still use the other two with dice of your color later in the same round. Based on the space used, ", "headingPath": "+4. Travel · Resolving the Travel action · 1. Place your dice. · even if the action space would allow for more . · 2. Pay the action space costs. · 3. Pay the travel costs. · …", "sharpsignalDocId": 372}, {"page": 12, "score": 0.029412, "snippet": "12 Bonus Actions During your turn, you can resolve 1 or more bonus actions before or after your normal action (not during your action). Bonus actions are summarized on your player aid. Bonus Actions 1. Com plete 1 contract 2. Im prove 1 guild seal 3. Mone y bag 4. Rer oll 1 die 5. Chang e 1 die resu", "headingPath": "", "sharpsignalDocId": 372}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "16 guild", "sharpsignalDocId": 372}, {"page": 4, "quote": null, "headingPath": "Player Setup", "sharpsignalDocId": 372}, {"page": 15, "quote": null, "headingPath": "End of Game · Final Scoring · Tiebreakers · 3 Players · 2 Players · Start of a New Round", "sharpsignalDocId": 372}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 372 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 372 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 18:29
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 Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | Player Setup | p.4 | 0.032787 (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 Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | Actions · How is an action carried out? · 1. Books · Sequence: · 2. Choose 1 of the available offers. | 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 Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | Player Setup · About The Rules · Introduction · A Game Turn | 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 |
| #4 | RULEBOOK Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | 16 guild | 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 Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | The Board | p.5 | 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 Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | The First Player · Example: | 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 |
| #7 | RULEBOOK Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | +4. Travel · Resolving the Travel action · 1. Place your dice. · even if the action space would allow for more . · 2. Pay the action space costs. · 3. Pay the travel costs. · … | p.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)) | 300 |
| #8 | RULEBOOK Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | p.12 | 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 Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | 16 guild | p.3 | no quote on the wire |
| [2] | RULEBOOK Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | Player Setup | p.4 | no quote on the wire |
| [3] | RULEBOOK Marco Polo II: In the Service of the Khan — Rulebook (corpus doc 372) | End of Game · Final Scoring · Tiebreakers · 3 Players · 2 Players · Start of a New Round | p.15 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 299 ms · first delta 5327 ms · total 11745 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 299 ms · ask 11436 ms · gateway work 11745 ms · total 11745 ms
- tokens in (the prompt the answerer read)
- 4154
- tokens out (what the answerer generated)
- 874
- tok/sec
- 137.5 tok/sec — 874 output tokens in 6.358 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 3s 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 302), 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.