You asked
How do I play?
Answered counted as answeredAsked with: Mexicabg-2955-en-1e
Settled. Play 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 128 ms · ask 6866 ms · total 6996 ms
- single-flight (PR-5)
- queued 0 ms · generation 6996 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048916, "snippet": "Beginning with the oldest player (or the player chosen by the players using any method they desire), each player, in clockwise order, places his Mexica on one of the 4 starting spaces. Play then continues in clockwise order. On a player's turn, he may take the following actions: place canal tile bui", "headingPath": "MPLAYING THE GAME", "sharpsignalDocId": 721}, {"page": 10, "score": 0.047643, "snippet": "The first part of the game ends and the players score their positions when: the first 8 districts have been founded. This means that all 8 Calpulli tiles that were placed in the Calpulli bank at the beginning of the game have been placed in districts on the board and at least 1 player has built all ", "headingPath": "MTHE FIRST SCORING", "sharpsignalDocId": 721}, {"page": 11, "score": 0.047619, "snippet": "After the first scoring is complete, place the remaining 7 Calpulli tiles in the Calpulli bank in ascending order from the upper left corner. Each player places his remaining 9 buildings in his play area. If a player has buildings left from the first part of the game, these are also available to be ", "headingPath": "THE SECOND PART OF THE GAMEM · THE SECOND SCORINGM · GAME ENDM", "sharpsignalDocId": 721}, {"page": 5, "score": 0.047163, "snippet": "A player plays canal tile X , building a district of 6 spaces. He then founds the district by placing the #6 Calpulli tile in it (his Mexica is in the district). He scores 3 points for this. As no other players have their Mexica in this district, no other players score for the founding of this distr", "headingPath": "FOUND DISTRICTM", "sharpsignalDocId": 721}, {"page": 10, "score": 0.046402, "snippet": "A player may acquire an action chip for 1 AP. He places the chip in his play area. A player may acquire at most 2 action chips in a turn. On a later turn, if the player wants to use more than 6 AP, he may use the action chips he has acquired. For each extra AP , the player must use 1 action chip.", "headingPath": "MACQUIRE ACTION CHIPS", "sharpsignalDocId": 721}, {"page": 6, "score": 0.045928, "snippet": "per player. The following actions are possible: | Symbol | Action | Cost (number of AP) | What must be considered | | | place 1 canal tile (1 or 2 space tile) | | On any empty land spaces, but not in a founded district, not on the sacred site, a starting space, other canal tiles, the lake, or at the", "headingPath": "MACTIONS", "sharpsignalDocId": 721}, {"page": 3, "score": 0.044557, "snippet": "lake canal land space scoring track bank of Calpulli tiles Each player takes the following in his chosen color: 1 Mexica, 18 buildings, 1 scoring marker, and 1 rule summary card. From his 18 buildings, each player finds the following 9 : 3 @ 1, 3 @ 2, 2 @ 3, 1 @ 4 and places them before him on the t", "headingPath": "CCONTENTS · PREPARATION", "sharpsignalDocId": 721}, {"page": 12, "score": 0.029412, "snippet": "first places 1 canal tile (X) for 1 AP , then builds, also for 1 AP , a bridge (bridge A), next moves his Mexica over bridge A for 2 AP , builds a value 1 building for 1 AP , and finally takes an action chip for 1 AP . first places 2 canal tiles (X) for a total of 2 AP , then builds, for 1 AP , a br", "headingPath": "Player A · Player B · Player C", "sharpsignalDocId": 721}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "CCONTENTS · PREPARATION", "sharpsignalDocId": 721}, {"page": 4, "quote": null, "headingPath": "MPLAYING THE GAME", "sharpsignalDocId": 721}, {"page": 10, "quote": null, "headingPath": "MACQUIRE ACTION CHIPS", "sharpsignalDocId": 721}, {"page": 8, "quote": null, "headingPath": "MMOVE MEXICA", "sharpsignalDocId": 721}, {"page": 9, "quote": null, "headingPath": "MMOVE MEXICA · BUILD BUILDINGM", "sharpsignalDocId": 721}, {"page": 5, "quote": null, "headingPath": "FOUND DISTRICTM", "sharpsignalDocId": 721}, {"page": 11, "quote": null, "headingPath": "THE SECOND PART OF THE GAMEM · THE SECOND SCORINGM · GAME ENDM", "sharpsignalDocId": 721}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 721 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 721 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 0.89690 of 3259 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 15:41 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 Mexica — Rulebook (corpus doc 721) | MPLAYING THE GAME | p.4 | 0.048916 (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 Mexica — Rulebook (corpus doc 721) | MTHE FIRST SCORING | p.10 | 0.047643 (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 Mexica — Rulebook (corpus doc 721) | THE SECOND PART OF THE GAMEM · THE SECOND SCORINGM · GAME ENDM | p.11 | 0.047619 (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 Mexica — Rulebook (corpus doc 721) | FOUND DISTRICTM | p.5 | 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 |
| #5 | RULEBOOK Mexica — Rulebook (corpus doc 721) | MACQUIRE ACTION CHIPS | p.10 | 0.046402 (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)) | 297 |
| #6 | RULEBOOK Mexica — Rulebook (corpus doc 721) | MACTIONS | p.6 | 0.045928 (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 Mexica — Rulebook (corpus doc 721) | CCONTENTS · PREPARATION | p.3 | 0.044557 (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 Mexica — Rulebook (corpus doc 721) | Player A · Player B · Player C | p.12 | 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 |
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 17 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 Mexica — Rulebook (corpus doc 721) | MPLAYING THE GAME | p.4 | #1 | 0.048916 (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 |
| #2 | RULEBOOK Mexica — Rulebook (corpus doc 721) | FOUND DISTRICTM | p.5 | #4 | 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 |
| #3 | RULEBOOK Mexica — Rulebook (corpus doc 721) | MACQUIRE ACTION CHIPS | p.10 | #5 | 0.046402 (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 |
| #4 | RULEBOOK Mexica — Rulebook (corpus doc 721) | MMOVE MEXICA | p.8 | #12 | 0.013889 (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 |
| #5 | RULEBOOK Mexica — Rulebook (corpus doc 721) | MMOVE MEXICA · BUILD BUILDINGM | p.9 | #10 | 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 |
| #6 | RULEBOOK Mexica — Rulebook (corpus doc 721) | MMOVE MEXICA | p.8 | #13 | 0.013699 (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 |
| #7 | RULEBOOK Mexica — Rulebook (corpus doc 721) | CCONTENTS · PREPARATION | p.3 | #7 | 0.044557 (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 Mexica — Rulebook (corpus doc 721) | THE SECOND PART OF THE GAMEM · THE SECOND SCORINGM · GAME ENDM | p.11 | #3 | 0.047619 (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 |
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 Mexica — Rulebook (corpus doc 721) | CCONTENTS · PREPARATION | p.3 | no quote on the wire |
| [2] | RULEBOOK Mexica — Rulebook (corpus doc 721) | MPLAYING THE GAME | p.4 | no quote on the wire |
| [3] | RULEBOOK Mexica — Rulebook (corpus doc 721) | MACQUIRE ACTION CHIPS | p.10 | no quote on the wire |
| [4] | RULEBOOK Mexica — Rulebook (corpus doc 721) | MMOVE MEXICA | p.8 | no quote on the wire |
| [5] | RULEBOOK Mexica — Rulebook (corpus doc 721) | MMOVE MEXICA · BUILD BUILDINGM | p.9 | no quote on the wire |
| [6] | RULEBOOK Mexica — Rulebook (corpus doc 721) | FOUND DISTRICTM | p.5 | no quote on the wire |
| [7] | RULEBOOK Mexica — Rulebook (corpus doc 721) | THE SECOND PART OF THE GAMEM · THE SECOND SCORINGM · GAME ENDM | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 128 ms · first delta 1747 ms · total 6996 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 128 ms · ask 6866 ms · gateway work 6996 ms · total 6996 ms
- tokens in (the prompt the answerer read)
- 3207
- tokens out (what the answerer generated)
- 1024
- tok/sec
- 198.9 tok/sec — 1024 output tokens in 5.148 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 27s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 9s 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 655), 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.