You asked
When does the game end?
Answered counted as answeredAsked with: Evacuationbg-382843-en-1e
The sage rests. The game continues.
🔧 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 145 ms · ask 2232 ms · total 3781 ms
- single-flight (PR-5)
- queued 1402 ms · generation 2379 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 8, "score": 0.048652, "snippet": "Each year has its own year-end bonus card. The pile is face up and you can peek ahead, if you want. In the Bonuses phase, you compare your power level to the numbers shown on the year-end bonus card. If the power level exactly matches one of the numbers, you gain the corresponding bonus. If order is", "headingPath": "STRICT YEAREND BONUSES · GENEROUS BONUS VARIANT · 7 CLEANUP · END OF GAME (RACE MODE) · Race Mode Ending Conditions", "sharpsignalDocId": 765}, {"page": 3, "score": 0.048412, "snippet": "Players will not play clockwise around the table. Instead, they will play in an order specified by the order indicator. At the start of the game, place 1 token from each player on this indicator in a random order. During play, players will be able to compete for order by building stadiums and develo", "headingPath": "STARTING THE GAME · RESOURCES", "sharpsignalDocId": 765}, {"page": 9, "score": 0.046898, "snippet": "In Points Mode, you always play until the end of the fourth year, ignoring the Race Mode win conditions. During setup, after players have randomly placed their technology tiles, shuffle the deck of goal cards and deal 4 to each player. From your set of 4, choose 1 and pass the other 3 along. From th", "headingPath": "POINTS MODE · Setup · End of Game · ADVANCED ACTION VARIANT", "sharpsignalDocId": 765}, {"page": 8, "score": 0.046635, "snippet": "At the end of the game, adjust your lowest production marker: -1 for each penalty chip you took during play. -1 for each Old World site not evacuated. -1 for each stadium you are missing. (You are supposed to have 3 on the New World.) +2 if you have the most happy faces. (Only +1 in a two-player gam", "headingPath": "Penalties and bonuses · Winning", "sharpsignalDocId": 765}, {"page": 9, "score": 0.045724, "snippet": "These modules give you additional ways to score points in Points Mode. They can be used with or without the Advanced Action variant. It is possible to use various combinations of modules with or without the Advanced Action variant. In particular, we recommend these combinations, which were well test", "headingPath": "MODULES", "sharpsignalDocId": 765}, {"page": 10, "score": 0.044103, "snippet": "The solo game is played in Points Mode. You can use the Advanced Action variant, if you want. You will essentially play a two-player game against an opponent whose actions are simulated by the solo deck. Your opponent will build stadiums and colonize New World sites, but will not need a player board", "headingPath": "SOLO GAME · Turn-Order Competition · Choosing Goal cards · Special card", "sharpsignalDocId": 765}, {"page": 7, "score": 0.044002, "snippet": "During this phase, players advance on the progress track. Players advance in the turn order that was just established in the previous phase. The amount they advance is determined by the power levels of the actions they played. Calculate power levels. During the Actions phase, you played a number of ", "headingPath": "5 PROGRESS", "sharpsignalDocId": 765}, {"page": 10, "score": 0.043905, "snippet": "You are playing in Points Mode, with 2-player scoring. (So you get 4 points for having at least as many happy faces and 0 if the other civilization has more.) We think 60 is a good score for a start, but you can probably get 80 once you have mastered the game. Note: You can also use the solo cards i", "headingPath": "Scoring · APPENDIX · YEAR END BONUSES · INFRASTRUCTURE REQUIREMENTS", "sharpsignalDocId": 765}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "STARTING THE GAME · RESOURCES", "sharpsignalDocId": 765}, {"page": 8, "quote": null, "headingPath": "STRICT YEAREND BONUSES · GENEROUS BONUS VARIANT · 7 CLEANUP · END OF GAME (RACE MODE) · Race Mode Ending Conditions", "sharpsignalDocId": 765}, {"page": 9, "quote": null, "headingPath": "POINTS MODE · Setup · End of Game · ADVANCED ACTION VARIANT", "sharpsignalDocId": 765}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 765 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 765 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 0.90630 of 619 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Oct 24, 2026 20:26 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 Evacuation — Rulebook (corpus doc 765) | STRICT YEAREND BONUSES · GENEROUS BONUS VARIANT · 7 CLEANUP · END OF GAME (RACE MODE) · Race Mode Ending Conditions | p.8 | 0.048652 (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 Evacuation — Rulebook (corpus doc 765) | STARTING THE GAME · RESOURCES | p.3 | 0.048412 (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 Evacuation — Rulebook (corpus doc 765) | POINTS MODE · Setup · End of Game · ADVANCED ACTION VARIANT | p.9 | 0.046898 (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 Evacuation — Rulebook (corpus doc 765) | Penalties and bonuses · Winning | p.8 | 0.046635 (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 Evacuation — Rulebook (corpus doc 765) | MODULES | p.9 | 0.045724 (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 Evacuation — Rulebook (corpus doc 765) | SOLO GAME · Turn-Order Competition · Choosing Goal cards · Special card | p.10 | 0.044103 (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 Evacuation — Rulebook (corpus doc 765) | 5 PROGRESS | p.7 | 0.044002 (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 Evacuation — Rulebook (corpus doc 765) | Scoring · APPENDIX · YEAR END BONUSES · INFRASTRUCTURE REQUIREMENTS | p.10 | 0.043905 (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 29 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 Evacuation — Rulebook (corpus doc 765) | STARTING THE GAME · RESOURCES | p.3 | #2 | 0.048412 (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 Evacuation — Rulebook (corpus doc 765) | POINTS MODE · Setup · End of Game · ADVANCED ACTION VARIANT | p.9 | #3 | 0.046898 (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 Evacuation — Rulebook (corpus doc 765) | Penalties and bonuses · Winning | p.8 | #4 | 0.046635 (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 Evacuation — Rulebook (corpus doc 765) | MODULES | p.9 | #5 | 0.045724 (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 Evacuation — Rulebook (corpus doc 765) | 1 INCOME | p.3 | #11 | 0.028083 (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 re-ranker chose it |
| #6 | RULEBOOK Evacuation — Rulebook (corpus doc 765) | Scoring · APPENDIX · YEAR END BONUSES · INFRASTRUCTURE REQUIREMENTS | p.10 | #8 | 0.043905 (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 |
| #7 | RULEBOOK Evacuation — Rulebook (corpus doc 765) | NEW INFRASTRUCTURE, SPACESHIPS, AND STADIUMS | p.5 | #10 | 0.028577 (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 re-ranker chose it |
| #8 | RULEBOOK Evacuation — Rulebook (corpus doc 765) | STRICT YEAREND BONUSES · GENEROUS BONUS VARIANT · 7 CLEANUP · END OF GAME (RACE MODE) · Race Mode Ending Conditions | p.8 | #1 | 0.048652 (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 Evacuation — Rulebook (corpus doc 765) | STARTING THE GAME · RESOURCES | p.3 | no quote on the wire |
| [2] | RULEBOOK Evacuation — Rulebook (corpus doc 765) | STRICT YEAREND BONUSES · GENEROUS BONUS VARIANT · 7 CLEANUP · END OF GAME (RACE MODE) · Race Mode Ending Conditions | p.8 | no quote on the wire |
| [3] | RULEBOOK Evacuation — Rulebook (corpus doc 765) | POINTS MODE · Setup · End of Game · ADVANCED ACTION VARIANT | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 145 ms · first delta 1349 ms · total 3781 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 1402 ms · retrieval 145 ms · ask 2232 ms · gateway work 2379 ms · total 3781 ms
- tokens in (the prompt the answerer read)
- 3812
- tokens out (what the answerer generated)
- 183
- tok/sec
- 198.1 tok/sec — 183 output tokens in 0.924 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 32s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 5h, checked 7s 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 699), 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.