You asked
When does the game end?
Answered counted as answeredAsked with: Twilight Imperium: Fourth Editionbg-233078-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 157 ms · ask 2815 ms · total 6066 ms
- single-flight (PR-5)
- queued 3091 ms · generation 2975 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 31, "score": 0.048139, "snippet": "• If the players are using the 14-space side of the victory point track, the game ends and a player wins when they have 14 victory points instead of 10. 87. 3 Each player places one of their control tokens on space “0” of the victory point track during setup. 87.4 When a player gains a victory point", "headingPath": "", "sharpsignalDocId": 249}, {"page": 14, "score": 0.047712, "snippet": "14 31.2 When a player becomes eliminated, all of the units, command tokens, control tokens, promissory notes, technologies, command sheets, and the faction sheet that matches that player’s faction or color are returned to the game box, including those in their reinforcements. 31.3 When a player beco", "headingPath": "", "sharpsignalDocId": 249}, {"page": 25, "score": 0.046642, "snippet": "25 70 STATUS PHASE During the status phase, players score objectives and prepare for the next game round. To resolve the status phase, players perform the following steps: 70.1 STEP 1—SCORE OBJECTIVES: Following initiative order, each player may score up to one public objective and one secret object", "headingPath": "", "sharpsignalDocId": 249}, {"page": 19, "score": 0.045476, "snippet": "19 • Forcing a player to remove a unit from the board by reducing the number of command tokens in their fleet pool is not treated as destroying a unit. 52.10 Players can score some objectives by spending resources, influence, or tokens, as described by the objective card. To score such an objective,", "headingPath": "", "sharpsignalDocId": 249}, {"page": 24, "score": 0.032258, "snippet": "• During the last round of a combat, “end of combat” and “end of combat round” effects occur during the same timing window. 67.10 After a combat ends, the player with one or more ships remaining in the system is the winner of the combat; the other player is the loser of the combat. If neither player", "headingPath": "", "sharpsignalDocId": 249}, {"page": 25, "score": 0.03125, "snippet": "The speaker is always the last player to vote and decides which outcome to resolve if the outcomes are tied. 69.3 During setup, the speaker prepares the objectives. 69.4 During the status phase, the speaker reveals a public objective. 69.5 A random player gains the speaker token during setup before ", "headingPath": "", "sharpsignalDocId": 249}, {"page": 24, "score": 0.030303, "snippet": "24 - The attacker makes all of their combat rolls during this step before the defender. This procedure is important for abilities that allow a player to reroll an opponent’s die. 67.6 STEP 4—ASSIGN HITS: Each player in the combat must choose and destroy one of their own ships in the active system fo", "headingPath": "", "sharpsignalDocId": 249}, {"page": 14, "score": 0.029412, "snippet": "30.3 After the active player resolves the primary ability of the “Diplomacy” strategy card, each other player, beginning with the player to the left of the active player and proceeding clockwise, may spend one command token from their strategy pool to ready up to two exhausted planets they control. ", "headingPath": "", "sharpsignalDocId": 249}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 31, "quote": null, "headingPath": "", "sharpsignalDocId": 249}, {"page": 31, "quote": null, "headingPath": "", "sharpsignalDocId": 249}, {"page": 24, "quote": null, "headingPath": "", "sharpsignalDocId": 249}, {"page": 24, "quote": null, "headingPath": "", "sharpsignalDocId": 249}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 249 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 249 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 0.91688 of 770 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Oct 29, 2026 03:12 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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.31 | 0.048139 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.14 | 0.047712 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.25 | 0.046642 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.19 | 0.045476 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.24 | 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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.25 | 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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.24 | 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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.14 | 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 80 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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.31 | #1 | 0.048139 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.14 | #2 | 0.047712 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.14 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it | |
| #4 | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.24 | #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 | |
| #5 | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.36 | #45 | 0.009709 (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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.31 | #10 | 0.026879 (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 | |
| #7 | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.36 | #44 | 0.009804 (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 | |
| #8 | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.24 | #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 |
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 Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.31 | no quote on the wire | |
| [2] | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.31 | no quote on the wire | |
| [3] | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.24 | no quote on the wire | |
| [4] | RULEBOOK Twilight Imperium: Fourth Edition — Rulebook (corpus doc 249) | p.24 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 157 ms · first delta 1698 ms · total 6066 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 3091 ms · retrieval 157 ms · ask 2815 ms · gateway work 2975 ms · total 6066 ms
- tokens in (the prompt the answerer read)
- 4121
- tokens out (what the answerer generated)
- 236
- tok/sec
- 197.5 tok/sec — 236 output tokens in 1.195 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 33s 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 175), 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.