You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Ginkgopolisbg-128271-en-1e
1. Place the 9 starting buildings (1–3 of each color) and the 12 Urbanization tokens (A–L) [1][2]. 2. Randomly place the 9 Building tiles numbered 1, 2, and 3 (one such for each color) to form a 3×3 square [3]. 3. Shuffle the remaining Building tiles and make several piles; with 2–3 players, remove 6 tiles from the game [1][3][2]. 4. Place the success points and Construction Site pawns near the Building tiles [1][3][2]. 5. Each player chooses a color and receives a screen and 2 New Hand tokens [1][3][2]. 6. Set up the Resources supply by placing resources of the chosen color in the general supply (25 for 2 players; 20 for 3 players; 18 for 4 players; or 16 for 5 players) [1][3][2]. 7. Form the deck by shuffling together the 12 Urbanization cards (A–L) and the 9 starting Building cards (the cards numbered 1-3) [1][3][2]. 8. With 2–3 players, put 7 cards on the discard [1][3][2]. 9. Form 3 piles of building cards numbered 4–20 [1][3][2]. 10. Each player receives 3 characters (in an introductory game) or drafts 3 characters each (by receiving 4 and choosing one) [1][3][2]. 11. Place the 3 selected Character cards in front of the screen [3]. 12. Take the Building tiles, resources, and success points indicated in the upper-left corner of the Character cards and place them behind the screen [3][2]. 13. The player who last planted a tree receives the First Player card and deals 4 cards from the deck to each player [3][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 309 ms · ask 7675 ms · total 7997 ms
- single-flight (PR-5)
- queued 0 ms · generation 7997 ms
- retrieval refs (raw)
- [{"page": 2, "score": 0.032787, "snippet": "The setup for a 4-player game has been completed up through Step 7 (see illustration below). Because this is an introductory game, each player takes a set of 3 Character cards. Nell receives the #2 set of cards. The three cards she got enable her to start the game with 4 resources, 2 tiles, and 2 su", "headingPath": "EXAMPLE", "sharpsignalDocId": 510}, {"page": 5, "score": 0.032258, "snippet": "Nell played the blue number 5 Building card, and the red number 4 Building tile. The blue 5 building belongs to Faye, so she retrieves the two resources placed there and gets 2 success points. Nell places the number 4 tile on the blue 5 building. She must pay 1 success point because 4 is less than 5", "headingPath": "EXAMPLE · 3. Prepare for the next round", "sharpsignalDocId": 510}, {"page": 3, "score": 0.031746, "snippet": "The game is divided into a variable number of turns. A turn comprises 3 steps: Choose a card Resolve actions Prepare for the next round Everyone does this step simultaneously. Look at your hand of 4 cards, choose one, and place it face-down in front of your screen. This card can be played by itself,", "headingPath": "Playing the game · 1. Choose a card · NEW HAND · 2. Resolve actions · A. Exploiting: Playing a card by itself", "sharpsignalDocId": 510}, {"page": 8, "score": 0.03125, "snippet": "1 Place the 9 starting buildings (1-3 of each color) and the 12 Urbanization tokens (A-L). 2 Shuffle the remaining Building tiles, and make several piles. With 2-3 players, remove 6 tiles from the game. Place the success points and Construction Site pawns near the Building tiles. 3 Each player choos", "headingPath": "Thanks · Setup · Game Turn", "sharpsignalDocId": 510}, {"page": 5, "score": 0.030769, "snippet": "The players have finished their actions, and have taken their right-hand neighbors' unused cards. The first player, Miley, draws the last card from the deck in order to get back to 4 cards in her hand. The deck has been exhausted, and must be reconstituted. She begins by announcing the numbers of th", "headingPath": "EXAMPLE · End of the Game", "sharpsignalDocId": 510}, {"page": 3, "score": 0.030303, "snippet": "Faye played the Red 7 by itself. Thus, she uses red number 7 building, which is a two-floor building. She gains 2 resources from the general supply and puts them behind her screen. Faye has two cards with an Exploiting bonus in her area. The first allows her to gain 1 tile, while the second grants h", "headingPath": "EXAMPLE", "sharpsignalDocId": 510}, {"page": 6, "score": 0.029851, "snippet": "Draw 3 cards for yourself, and then a 4th that you give to Hal, face down. Choose your action (card + possible tile), and apply its effects according to the normal rules. Discard the 2 unplayed cards. Reveal Hal's card, and draw a random tile, since Hal constructs every turn. When Hal urbanizes (he ", "headingPath": "Playing a round of the game : · Specifics: · End of the Game · Expert level", "sharpsignalDocId": 510}, {"page": 8, "score": 0.029412, "snippet": "8 8 Summary Setup G a m e T u r n 1 Place the 9 starting buildings (1–3 of each color) and the 12 Urbanization tokens (A–L). 1 Everyone at the same time: Choose your action by selecting a card and placing it face-down in front of your screen (+ a Building tile if urbanizing or constructing a floor).", "headingPath": "", "sharpsignalDocId": 510}]
- citations (raw)
- [{"page": 8, "quote": null, "headingPath": "", "sharpsignalDocId": 510}, {"page": 8, "quote": null, "headingPath": "Thanks · Setup · Game Turn", "sharpsignalDocId": 510}, {"page": 2, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 510}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 510 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 510 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 7, 2026 06:01
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 Ginkgopolis — Rulebook (corpus doc 510) | EXAMPLE | p.2 | 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 Ginkgopolis — Rulebook (corpus doc 510) | EXAMPLE · 3. Prepare for the next round | p.5 | 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 Ginkgopolis — Rulebook (corpus doc 510) | Playing the game · 1. Choose a card · NEW HAND · 2. Resolve actions · A. Exploiting: Playing a card by itself | p.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)) | 300 |
| #4 | RULEBOOK Ginkgopolis — Rulebook (corpus doc 510) | Thanks · Setup · Game Turn | p.8 | 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 Ginkgopolis — Rulebook (corpus doc 510) | EXAMPLE · End of the Game | 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 Ginkgopolis — Rulebook (corpus doc 510) | EXAMPLE | p.3 | 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 Ginkgopolis — Rulebook (corpus doc 510) | Playing a round of the game : · Specifics: · End of the Game · Expert level | p.6 | 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 Ginkgopolis — Rulebook (corpus doc 510) | 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 Ginkgopolis — Rulebook (corpus doc 510) | p.8 | no quote on the wire | |
| [2] | RULEBOOK Ginkgopolis — Rulebook (corpus doc 510) | Thanks · Setup · Game Turn | p.8 | no quote on the wire |
| [3] | RULEBOOK Ginkgopolis — Rulebook (corpus doc 510) | Setup | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 309 ms · first delta 4692 ms · total 7997 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 309 ms · ask 7675 ms · gateway work 7997 ms · total 7997 ms
- tokens in (the prompt the answerer read)
- 4348
- tokens out (what the answerer generated)
- 450
- tok/sec
- 138.6 tok/sec — 450 output tokens in 3.247 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 55s 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 442), 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.