You asked
Before the first turn, what goes on the table and what does each player take?
Answered counted as answeredAsked with: Jaipurbg-54043-en-1e
1. Place 3 camel cards faceup between the players [1]. 2. Shuffle the remaining cards well [1]. 3. Deal 5 cards to each player [1]. 4. Place the remaining cards facedown as a draw pile (deck) [1]. 5. Fill the market by drawing 2 cards from the deck and placing them faceup next to the camels [1]. 6. Players remove any camels from their hands and put them faceup in a stack in front of them to form their herd [1]. 7. Sort tokens by goods type into piles in descending order of value and spread each pile so both players can see all values [2]. 8. Sort bonus tokens by type, shuffle each type separately, and form 3 piles [2]. 9. Place the camel token next to the bonus tokens [2]. 10. Put the 3 Seals of Excellence within easy reach of both players [2].
🔧 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 350 ms · ask 4091 ms · total 4450 ms
- single-flight (PR-5)
- queued 0 ms · generation 4450 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.032787, "snippet": "Sort the tokens by goods type. Make a pile for each goods type in descending order of value. Spread each pile, as depicted above, so that both players can see all the token values. Sort the bonus tokens by type ( , , ). Shuffle each type separately, then form 3 piles (not spread out). Place the came", "headingPath": "SETUP · GAME TURN", "sharpsignalDocId": 187}, {"page": 4, "score": 0.032258, "snippet": "If you take cards, you must choose one of the following options: take 1 single good, take several goods (=the EXCHANGE option), take all the camels. These 3 options are shown in detail below. Take all the goods cards that you want into your hand (they can be of different types) , then... Players may", "headingPath": "TAKE CARDS · B: Take several goods · IMPORTANT", "sharpsignalDocId": 187}, {"page": 7, "score": 0.031746, "snippet": "When you take cards from the market, you either take goods or camels, but never both. If you decide to take camels, you must always take all the camels from the market. When making an exchange: the returned cards can be camels, goods, or a mixture of the two ; the same goods type cannot be both take", "headingPath": "REMINDERS AND NOTES · NB: It is best to read this after your first game.", "sharpsignalDocId": 187}, {"page": 4, "score": 0.03125, "snippet": "Herd If you take cards, you must choose one of the following options: A. take 1 single good, B. take several goods (=the EXCHANGE option), C. take all the camels. Take all the goods cards that you want into your hand (they can be of different types), then... ... exchange the same number of cards. Th", "headingPath": "", "sharpsignalDocId": 187}, {"page": 5, "score": 0.030769, "snippet": "To sell cards, choose one type of goods and discard as many cards of that type as you like into the discard pile. Each sale yields goods tokens and, if the sale is big enough, a bonus. A sale is carried out in 3 steps. Take one token for each card you sold starting with the top of the corresponding ", "headingPath": "SELL CARDS · 2 · Restrictions during a sale", "sharpsignalDocId": 187}, {"page": 6, "score": 0.030303, "snippet": "The player with the most camels in their herd receives the camel token , which is worth 5 rupees. The players turn over their tokens and add them up to determine who is the richest. NB: We suggest that you make piles of 10 rupees as these are easier for children to count, and quicker for adults, as ", "headingPath": "A round ends immediately if: · NEW ROUND · END OF THE GAME", "sharpsignalDocId": 187}, {"page": 2, "score": 0.029851, "snippet": "In Jaipur, you are hoping to become the Maharaja's personal trader by amassing more riches than your opponent at the end of each week (round) . To do so, collect and exchange goods (cards) at the market, then sell them for rupees (flip the tokens over) . If you manage to arrange a larger sale (3 car", "headingPath": "INTRODUCTION AND AIM OF THE GAME · SETUP", "sharpsignalDocId": 187}, {"page": 8, "score": 0.029412, "snippet": "My, oh, my, how time flies! The last decade passed in the blink of an eye. I remember the first ideas that led to Jaipur very well: it all started with the desire of a fast barter phase (hence a 'neutral' central market). I eventually kept it to a 2-player game, for it is in such a configuration tha", "headingPath": "Sébastien Pauchon · Vincent Dutrait · CONTACT INFORMATION", "sharpsignalDocId": 187}]
- citations (raw)
- [{"page": 2, "quote": null, "headingPath": "INTRODUCTION AND AIM OF THE GAME · SETUP", "sharpsignalDocId": 187}, {"page": 3, "quote": null, "headingPath": "SETUP · GAME TURN", "sharpsignalDocId": 187}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 187 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 187 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 18:10
retrieval — what the search arm returned
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 Jaipur — Rulebook (corpus doc 187) | SETUP · GAME TURN | p.3 | 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 Jaipur — Rulebook (corpus doc 187) | TAKE CARDS · B: Take several goods · IMPORTANT | 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 |
| #3 | RULEBOOK Jaipur — Rulebook (corpus doc 187) | REMINDERS AND NOTES · NB: It is best to read this after your first game. | p.7 | 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 Jaipur — Rulebook (corpus doc 187) | p.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)) | 300 | |
| #5 | RULEBOOK Jaipur — Rulebook (corpus doc 187) | SELL CARDS · 2 · Restrictions during a sale | 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 Jaipur — Rulebook (corpus doc 187) | A round ends immediately if: · NEW ROUND · END OF THE GAME | p.6 | 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 Jaipur — Rulebook (corpus doc 187) | INTRODUCTION AND AIM OF THE GAME · SETUP | p.2 | 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 Jaipur — Rulebook (corpus doc 187) | Sébastien Pauchon · Vincent Dutrait · CONTACT INFORMATION | p.8 | 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 |
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 Jaipur — Rulebook (corpus doc 187) | INTRODUCTION AND AIM OF THE GAME · SETUP | p.2 | no quote on the wire |
| [2] | RULEBOOK Jaipur — Rulebook (corpus doc 187) | SETUP · GAME TURN | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 350 ms · first delta 3034 ms · total 4450 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 350 ms · ask 4091 ms · gateway work 4450 ms · total 4450 ms
- tokens in (the prompt the answerer read)
- 2494
- tokens out (what the answerer generated)
- 200
- tok/sec
- 148.4 tok/sec — 200 output tokens in 1.348 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 47s 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
- 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 105), 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.