You asked
How do I play?
Answered counted as answeredAsked with: Point Citybg-368017-en-1e
Rule found, game on.
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 90 ms · ask 6588 ms · total 6679 ms
- single-flight (PR-5)
- queued 0 ms · generation 6679 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.047875, "snippet": "1 Sort the Buidling/Resource Cards into 3 decks based on tier (tiers are indicated by the number of dots in the bottom left hand corner of the card on the building side of each card). Shuffle each deck and place them in piles with their resource side faceup. Based on the number of players, remove/us", "headingPath": "BUILDING CARDS (FRONT) · SETUP", "sharpsignalDocId": 1035}, {"page": 8, "score": 0.047163, "snippet": "Once you have drafted two cards, paid the required resources to construct any Building Cards, and selected any Civic Tokens you have earned, your turn ends and the Market is refilled. To refill the Market, take 2 cards from the top of the draw pile to refill the spaces in the Market. [Note: if a pla", "headingPath": "TURN END", "sharpsignalDocId": 1035}, {"page": 9, "score": 0.045285, "snippet": "The game ends when the Market is no longer able to be refilled because the Draw Pile has been depleted. [Note: Each player will play exactly 17 turns and the market will have 14 cards remaining in it.] Players add up the points printed on their constructed Building Cards and the points gained by the", "headingPath": "GAME END · SCORING", "sharpsignalDocId": 1035}, {"page": 5, "score": 0.032787, "snippet": "5 Take a number of Ingenuity Starting Cards equal to the number of players and be sure to include the card with the starting player symbol ( ). 6 Each player takes one Ingenuity Starting Card at random and turns it over. The player with the starting player symbol ( ) becomes the starting player. You", "headingPath": "SETUP · 3 PLAYER SETUP EXAMPLE", "sharpsignalDocId": 1035}, {"page": 10, "score": 0.032258, "snippet": "Follow the setup rules for a 2-player game, with the following exceptions: Only give yourself an Ingenuity Starting Card. You take the first turn. Line up the 10 chosen Civic Tokens in a single line - their order is important. Place one token above the top left-most card, and place the other token t", "headingPath": "Setup · Turn Summary · AI opponent turn", "sharpsignalDocId": 1035}, {"page": 6, "score": 0.03125, "snippet": "On your turn, draft any 2 orthogonally adjacent cards from the Market, or draft the top two cards of the Draw Pile. You may always draft a Resource Card. Take the Resource Card and place it in front of you. This card may be used this turn, or on future turns to provide the required resources to cons", "headingPath": "GAMEPLAY · Optional Flip Action", "sharpsignalDocId": 1035}, {"page": 7, "score": 0.030303, "snippet": "Once you have paid the required resources to construct a building (either from Resource Cards, or permanent resources from your previously constructed buildings), place the Building Card into your City (a tableau of cards in front of you). In order to keep track of which permanent resources you have", "headingPath": "Constructing a Building · Constructing a Civic Building", "sharpsignalDocId": 1035}, {"page": 11, "score": 0.029851, "snippet": "[Note: this movement is designed such that the AI opponent will always draft cards in a predictable pattern from left to right, top to bottom. This allows you to strategically plan out which cards the AI opponent will receive by drafting cards in their path.] [Note: the AI opponent is not required t", "headingPath": "AI opponent turn · Scoring · AI opponent scoring", "sharpsignalDocId": 1035}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "BUILDING CARDS (FRONT) · SETUP", "sharpsignalDocId": 1035}, {"page": 5, "quote": null, "headingPath": "SETUP · 3 PLAYER SETUP EXAMPLE", "sharpsignalDocId": 1035}, {"page": 6, "quote": null, "headingPath": "GAMEPLAY · Optional Flip Action", "sharpsignalDocId": 1035}, {"page": 7, "quote": null, "headingPath": "Constructing a Building · Constructing a Civic Building", "sharpsignalDocId": 1035}, {"page": 8, "quote": null, "headingPath": "TURN END", "sharpsignalDocId": 1035}, {"page": 10, "quote": null, "headingPath": "Setup · Turn Summary · AI opponent turn", "sharpsignalDocId": 1035}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1035 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1035 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)
- answer fence
- passed — letter density 0.89114 of 3114 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 6, 2026 13:08 UTC
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. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.
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 Point City — Rulebook (corpus doc 1035) | BUILDING CARDS (FRONT) · SETUP | p.4 | 0.047875 (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 Point City — Rulebook (corpus doc 1035) | TURN END | p.8 | 0.047163 (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 Point City — Rulebook (corpus doc 1035) | GAME END · SCORING | p.9 | 0.045285 (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 Point City — Rulebook (corpus doc 1035) | SETUP · 3 PLAYER SETUP EXAMPLE | p.5 | 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 |
| #5 | RULEBOOK Point City — Rulebook (corpus doc 1035) | Setup · Turn Summary · AI opponent turn | p.10 | 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 |
| #6 | RULEBOOK Point City — Rulebook (corpus doc 1035) | GAMEPLAY · Optional Flip Action | p.6 | 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 |
| #7 | RULEBOOK Point City — Rulebook (corpus doc 1035) | Constructing a Building · Constructing a Civic Building | p.7 | 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 |
| #8 | RULEBOOK Point City — Rulebook (corpus doc 1035) | AI opponent turn · Scoring · AI opponent scoring | p.11 | 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 |
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.
candidate pool: the answering read scored 12 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.
floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.
arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.
| read at | document | heading | page | fused rank | fused RRF score | carried by | how it got its slot |
|---|---|---|---|---|---|---|---|
| #1 | RULEBOOK Point City — Rulebook (corpus doc 1035) | Setup · Turn Summary · AI opponent turn | p.10 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Point City — Rulebook (corpus doc 1035) | BUILDING CARDS (FRONT) · SETUP | p.4 | #1 | 0.047875 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Point City — Rulebook (corpus doc 1035) | Setup · Turn Summary · LOVE POINT CITY? | p.12 | #9 | 0.014493 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #4 | RULEBOOK Point City — Rulebook (corpus doc 1035) | TURN END | p.8 | #2 | 0.047163 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Point City — Rulebook (corpus doc 1035) | GAMEPLAY · Optional Flip Action | p.6 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Point City — Rulebook (corpus doc 1035) | Constructing a Building · Constructing a Civic Building | p.7 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Point City — Rulebook (corpus doc 1035) | GAME END · SCORING | p.9 | #3 | 0.045285 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Point City — Rulebook (corpus doc 1035) | SETUP · 3 PLAYER SETUP EXAMPLE | p.5 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
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 Point City — Rulebook (corpus doc 1035) | BUILDING CARDS (FRONT) · SETUP | p.4 | no quote on the wire |
| [2] | RULEBOOK Point City — Rulebook (corpus doc 1035) | SETUP · 3 PLAYER SETUP EXAMPLE | p.5 | no quote on the wire |
| [3] | RULEBOOK Point City — Rulebook (corpus doc 1035) | GAMEPLAY · Optional Flip Action | p.6 | no quote on the wire |
| [4] | RULEBOOK Point City — Rulebook (corpus doc 1035) | Constructing a Building · Constructing a Civic Building | p.7 | no quote on the wire |
| [5] | RULEBOOK Point City — Rulebook (corpus doc 1035) | TURN END | p.8 | no quote on the wire |
| [6] | RULEBOOK Point City — Rulebook (corpus doc 1035) | Setup · Turn Summary · AI opponent turn | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 90 ms · first delta 1548 ms · total 6679 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 90 ms · ask 6588 ms · gateway work 6679 ms · total 6679 ms
- tokens in (the prompt the answerer read)
- 2776
- tokens out (what the answerer generated)
- 1024
- tok/sec
- 202.0 tok/sec — 1024 output tokens in 5.070 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 20s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 0s ago)
- answerer node (the seat proxy's own header — this probe, not this ask)
- node1
- 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 965), 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.