You asked
How do I set up the game?
Answered counted as answered1. The 30 city tokens are shuffled well and displayed on the game board with their alphabetical characters face up (note that 'D' city tokens are not used on the Italia board) [1]. 2. The city tokens are randomly assigned to the cities on the board according to their characters [1]. 3. The tokens are flipped so that their type of goods becomes visible [1]. 4. For every province, the most valuable type of goods is identified (cloth: 7, wine: 6, tools: 5, food: 4, bricks: 3) [1]. 5. A bonus marker of that identified type is assigned to the respective province inside the bonus markers section on the top left corner of the game board [1]. 6. The 30 cards for sale are arranged according to their Roman numeral on the back (I-V) [1]. 7. Cards with a numeral bigger than the number of players are taken out of the game [1][2]. 8. The remaining cards are sorted by numeral and shuffled well [1]. 9. The cards form one complete face down stack, with the I cards on top, followed by the II cards, etc. [1]. 10. The top 7 cards from the stack are displayed face up inside the display area on the top right corner of the game board [1]. 11. The remaining stack is put near the game board along with the CONCORDIA card [1]. 12. After randomly determining the start player, the last player (the player to the right of the start player) receives the Praefectus Magnus [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 347 ms · ask 9632 ms · total 9992 ms
- single-flight (PR-5)
- queued 0 ms · generation 9992 ms
- retrieval refs (raw)
- [{"page": 1, "score": 0.032522, "snippet": "turn consists of playing 1 card from their hand and executing the related actions. All played cards form a personal discard pile showing only the last card played. With the Tribune, a player takes back all cards previously played. The game ends either after a player purchases the last card from the ", "headingPath": "GAME OVERVIEW · Game end · Scoring victory points · PERSONALITY CARDS · 2. 1 new colonist · Game setup · …", "sharpsignalDocId": 155}, {"page": 1, "score": 0.016393, "snippet": "The 30 city tokens are shuffled well and displayed on the game board with their alphabetical characters face up. (the 'D' city tokens are not used on the Italia board) The city tokens are randomly assigned to the cities on the board according to their characters. The tokens are flipped so that their", "headingPath": "1 . Distribute city tokens · 2 . Assign bonus markers · 3 . Prepare the stack of cards", "sharpsignalDocId": 173}, {"page": 2, "score": 0.015873, "snippet": "Red has 3 colonists, 1 land colonist is located between 'Colonia A.' and The number of colonists a player has on the board determines the number of possible movement steps that a player can freely allocate to his own colonists. Land colonists are moved only along the brown lines and sea colonists on", "headingPath": "PERSONALITY CARDS · 2. Build houses (after all movements) · PrefecT", "sharpsignalDocId": 155}, {"page": 2, "score": 0.015625, "snippet": "The player chooses between two alternatives: The player may place new colonists on the game board each to be paid for with 1 food and 1 tool. New colonists can be placed inside 'Roma' or inside any other city where the player owns a house. or The player receives 5 sestertii plus 1 sestertius for eac", "headingPath": "colonisT", "sharpsignalDocId": 155}, {"page": 4, "score": 0.015385, "snippet": "If a player who currently owns the PRÆFECTUS M. plays a Prefect card (or uses one with the Diplomat) in order to let a province produce, he receives a double bonus (2 units instead of 1). Production inside the cities is not affected. After his turn he hands the PRÆFECTUS M. to the player sitting to ", "headingPath": "PRÆFECTUS MAGNUS · FURTHER RULES · STOREHOUSE · INTERMEDIATE SCORING", "sharpsignalDocId": 155}, {"page": 4, "score": 0.015152, "snippet": "If a player purchases the last personality card and such empties the display on the game board, or if he builds his 15 th house, he receives the Concordia card , which is worth 7 additional VP. Every other player now executes his last turn before the final scoring is done as described below. The pla", "headingPath": "GAME END", "sharpsignalDocId": 155}, {"page": 4, "score": 0.014925, "snippet": "Each personality card is related to an ancient god who rewards its owner with victory points. First players gather all their cards, including the ones from their discard pile, and arrange them according to the different ancient gods. The back of the player aid shows a summary of the gods and in whic", "headingPath": "FINAL SCORING · VESTA · JUPITER · SATURNUS · MERCURIUS · MARS", "sharpsignalDocId": 155}, {"page": 2, "score": 0.014706, "snippet": "In the situation depicted down left a player who chooses the cash bonus would get 6 sestertii out of the bank, because there are 6 coins visible on the bonus markers (given that no other bonus markers show coins) and the bonus markers with coins would be turned over to show their units of goods agai", "headingPath": "colonisT", "sharpsignalDocId": 155}]
- citations (raw)
- [{"page": 1, "quote": null, "headingPath": "1 . Distribute city tokens · 2 . Assign bonus markers · 3 . Prepare the stack of cards", "sharpsignalDocId": 173}, {"page": 1, "quote": null, "headingPath": "GAME OVERVIEW · Game end · Scoring victory points · PERSONALITY CARDS · 2. 1 new colonist · Game setup · …", "sharpsignalDocId": 155}]
- 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 20:25
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 Concordia — Rulebook (corpus doc 155) | GAME OVERVIEW · Game end · Scoring victory points · PERSONALITY CARDS · 2. 1 new colonist · Game setup · … | p.1 | 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 Concordia — Rulebook (corpus doc 173) | 1 . Distribute city tokens · 2 . Assign bonus markers · 3 . Prepare the stack of cards | p.1 | 0.016393 (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 Concordia — Rulebook (corpus doc 155) | PERSONALITY CARDS · 2. Build houses (after all movements) · PrefecT | p.2 | 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 |
| #4 | RULEBOOK Concordia — Rulebook (corpus doc 155) | colonisT | p.2 | 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 |
| #5 | RULEBOOK Concordia — Rulebook (corpus doc 155) | PRÆFECTUS MAGNUS · FURTHER RULES · STOREHOUSE · INTERMEDIATE SCORING | p.4 | 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 |
| #6 | RULEBOOK Concordia — Rulebook (corpus doc 155) | GAME END | p.4 | 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 |
| #7 | RULEBOOK Concordia — Rulebook (corpus doc 155) | FINAL SCORING · VESTA · JUPITER · SATURNUS · MERCURIUS · MARS | p.4 | 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 |
| #8 | RULEBOOK Concordia — Rulebook (corpus doc 155) | colonisT | p.2 | 0.014706 (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 Concordia — Rulebook (corpus doc 173) | 1 . Distribute city tokens · 2 . Assign bonus markers · 3 . Prepare the stack of cards | p.1 | no quote on the wire |
| [2] | RULEBOOK Concordia — Rulebook (corpus doc 155) | GAME OVERVIEW · Game end · Scoring victory points · PERSONALITY CARDS · 2. 1 new colonist · Game setup · … | p.1 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 347 ms · first delta 7572 ms · total 9992 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 347 ms · ask 9632 ms · gateway work 9992 ms · total 9992 ms
- tokens in (the prompt the answerer read)
- 4432
- tokens out (what the answerer generated)
- 349
- tok/sec
- 146.9 tok/sec — 349 output tokens in 2.376 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
- 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 77), 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.