You asked
How do I set up the game?
Answered counted as answeredTo set up the game, follow these steps: 1. Remove individual tiles from their frames [1]. 2. Unfold the board and place it on the table [2]. 3. Place the number 12 province tile on the province with Agra [2]. 4. Shuffle the remaining 11 octagonal province tiles face down, then place one, randomly and face up, in each of the 11 remaining provinces, ensuring they do not cover roads and cities [2]. 5. Place the Taj Mahal bonus tile face up on the fortress city of Agra [2]. 6. Shuffle the 15 square bonus tiles face down and place one, randomly and face up, on each fortress city [2]. 7. Sort the 24 oval influence tiles by their pictures and place them face up in four stacks beside the upper right corner of the board (court of the Grand Moguls) [2]. 8. Place one of each type of influence tile on the corresponding space in the court of the Grand Moguls [2]. 9. Place the gold ring (the crown) in the court of the Grand Moguls [2]. 1<0xA0>10. Place the 4 special cards face up beside the board [2][3]. 11. Shuffle the 96 remaining cards [2]. 12. Deal 6 cards to each player face down; these are secret starting hands [4]. 13. Lay out the card supply for the first round by drawing and placing a specific number of cards face up to the left of the board: 5 cards for three players, 7 cards for four players, or 9 cards for five players [4]. 14. Place the remaining cards face down in a stack on the left side of the board to serve as the drawing deck [4]. 15. Sort the palace and scoring markers by color [4]. 16. Each player selects a color, places all palaces of that color before them on the table, and places their scoring marker on the zero space of the scoring track [4]. 17. Set up the 2 black figures: place one (current province figure) in the first province (with the number 1 province tile) and move the number 1 province tile to the space provided in the court of the Grand Moguls [4]. 18. Choose a starting player by any method preferred; the starting player places the other black figure (starting player figure) before themselves on the table [4].
🔧 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 222 ms · ask 6802 ms · total 7036 ms
- single-flight (PR-5)
- queued 0 ms · generation 7036 ms
- retrieval refs (raw)
- [{"page": 3, "score": 0.032522, "snippet": "Princess (for control of the social forces) Grand Mogul (for control of the crown) Elephant (for control of the province and its economic yield) Deal 6 cards to each player face down. These are the players‹ starting hands and are kept secret from the other players. Lay out the card supply for the fi", "headingPath": "Preparation · Playing the game", "sharpsignalDocId": 140}, {"page": 6, "score": 0.031099, "snippet": "Bonus tiles: when a player takes a bonus tile, he receives: ... 4 influence points. He then sets the tile aside; it is out of the game. ... 2 influence points and advances his scoring marker on the scoring track two spaces. He then sets the tile aside; it is out of the game. ... the topmost card fro", "headingPath": "Playing the game", "sharpsignalDocId": 140}, {"page": 4, "score": 0.016129, "snippet": "player‹s turn, he must: ·play 1 or 2 cards to influence forces in the current province or ·withdraw from the competition and claim the rewards of his influence in the current province. When a player withdraws, the visit is over for him and he may take no further turns in the current province. When a", "headingPath": "Playing the game", "sharpsignalDocId": 140}, {"page": 8, "score": 0.015873, "snippet": "supply next to the board. 'Return the crown to the court of the Grand Moguls if it is not still there. 'Draw cards from the drawing deck to lay out a new card supply. Draw the same number of cards as in preparation. When the drawing deck is exhausted, shuffle the discard pile and place it face down ", "headingPath": "Ending a visit and starting the next visit", "sharpsignalDocId": 140}, {"page": 9, "score": 0.015625, "snippet": "Free color change · The colored card, which the player plays with this special card, need not match the color required for this visit. Note: This special card applies only to the turn it is played. In the player‹s subsequent turns of this visit, he must use cards of the color he started the visit wi", "headingPath": "Ending a visit and starting the next visit · Game end", "sharpsignalDocId": 140}, {"page": 5, "score": 0.015385, "snippet": "·withdraw When a player withdraws, he may play no more cards during this visit, but compares the cards he has played during this visit with those of his opponents: ' Vizier, General, Monk or Princess: When a withdrawing player has more symbols of one of these four types than any other single player,", "headingPath": "Playing the game", "sharpsignalDocId": 140}, {"page": 7, "score": 0.015152, "snippet": "When the last player in a visit has withdrawn and scored his influence points, discarded the cards he played to the discard pile, and taken the last card from the card supply, the visit ends. Each player, who has two identical oval influence tiles, returns them to the supply near the upper right of ", "headingPath": "Ending a visit and starting the next visit", "sharpsignalDocId": 140}, {"page": 10, "score": 0.014925, "snippet": "'A player‹s strength comes from his cards and cards are scarce. It is less important to win many influence points in one specific visit, but rather to win some influence points in as many visits as possible. Remember that you also score by connecting to palaces in already visited provinces and by ma", "headingPath": "Game tactics · Acknowledgements", "sharpsignalDocId": 140}]
- citations (raw)
- [{"page": 1, "quote": null, "headingPath": "A game of power and influence in India · Overview · Contents", "sharpsignalDocId": 140}, {"page": 2, "quote": null, "headingPath": "Preparation", "sharpsignalDocId": 140}, {"page": 8, "quote": null, "headingPath": "Ending a visit and starting the next visit", "sharpsignalDocId": 140}, {"page": 3, "quote": null, "headingPath": "Preparation · Playing the game", "sharpsignalDocId": 140}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base-rulebook boost: not recorded (this ruling predates it); rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base-rulebook boost: not recorded (this ruling predates it)
- 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
- Oct 31, 2026 14:13
retrieval — what the search arm returned
score = the fused retrieval score (reciprocal-rank fusion over the search arms) — NOT a cosine similarity. How many arms fused this ruling was NOT RECORDED (it predates the boost trail, ran on the path that stored none, or stored one that could not be read), and the ceiling depends on that count (ceiling = arms/(k+1) at k=60): 2 arms top out at 0.03279; 3 arms top out at 0.04918. So a score above 0.03279 here is not an anomaly: it is arithmetic proof a boost arm voted, and the measured band 0.016–0.033 (taken on two-arm asks) is what does not apply. 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 Taj Mahal — Rulebook (corpus doc 140) | Preparation · Playing the game | p.3 | 0.032522 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #2 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Playing the game | p.6 | 0.031099 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #3 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Playing the game | p.4 | 0.016129 (inside the measured healthy band 0.016–0.033 (measured on two-arm asks; this ruling's arm count was never recorded)) | 300 |
| #4 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Ending a visit and starting the next visit | p.8 | 0.015873 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #5 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Ending a visit and starting the next visit · Game end | p.9 | 0.015625 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #6 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Playing the game | p.5 | 0.015385 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #7 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Ending a visit and starting the next visit | p.7 | 0.015152 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 300 |
| #8 | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Game tactics · Acknowledgements | p.10 | 0.014925 (below the measured healthy band (< 0.016) — a weak fuse on a two-arm ask, and this ruling's arm count was never recorded) | 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 Taj Mahal — Rulebook (corpus doc 140) | A game of power and influence in India · Overview · Contents | p.1 | no quote on the wire |
| [2] | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Preparation | p.2 | no quote on the wire |
| [3] | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Ending a visit and starting the next visit | p.8 | no quote on the wire |
| [4] | RULEBOOK Taj Mahal — Rulebook (corpus doc 140) | Preparation · Playing the game | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 222 ms · first delta 3182 ms · total 7036 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 222 ms · ask 6802 ms · gateway work 7036 ms · total 7036 ms
- tokens in (the prompt the answerer read)
- 3170
- tokens out (what the answerer generated)
- 527
- tok/sec
- 138.0 tok/sec — 527 output tokens in 3.819 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 30s 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 62), 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.