You asked
When does the game end?
Answered counted as answeredAsked with: Pulsar 2849bg-228341-en-1e
That settles it — whose turn was it?
🔧 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 170 ms · ask 1422 ms · total 1595 ms
- single-flight (PR-5)
- queued 0 ms · generation 1595 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 17, "score": 0.04866, "snippet": "Players score points at the end of the game, as depicted on the quick reference sheets: Purple patents give you points at the end of the game. Most of these can be scored in this step. Some of them will increase your score in one of the later steps. Score points for goal tiles. Score 1 point for eac", "headingPath": "Final Scoring · Victory", "sharpsignalDocId": 442}, {"page": 17, "score": 0.048139, "snippet": "There are many ways to score points during the game. You can get a bonus for being the first or second player to begin construction of two gyrodynes of the same type. You can get points for flipping over certain transmitters. When your flight ends at a planetary system with an available blue planet,", "headingPath": "SCORING SUMMARY · During the Action Phase: · During the Production Phase: · At the End of the Game: · END OF GAME · Goal Tiles · …", "sharpsignalDocId": 442}, {"page": 16, "score": 0.047883, "snippet": "Once each player has had a turn in the Action Phase, it is time for the Production Phase. Players gain some engineering cubes, score some points, and set up for the next round. Specifically, the steps are performed in this order: Determine the new order of play. Hand out engineering cubes. Take init", "headingPath": "End of Round Summary · Determining Order of Play · Gaining Engineering Cubes · Example: · Penalties · Online Transmitters", "sharpsignalDocId": 442}, {"page": 2, "score": 0.04598, "snippet": "2 At the end of the game, you may choose one goal tile and evaluate it as though you have met the goal. (You can also buy the bonuses.) At the end of the game, score 4 points if you have a spinning gyrodyne, 8 if you have two different types spinning, or 16 if you have all three types spinning. At t", "headingPath": "", "sharpsignalDocId": 442}, {"page": 3, "score": 0.045743, "snippet": "The year is 2849 and an interstellar energy boom is about to begin. Rival corporations have survey ships poised on the edge of a pulsar-rich star cluster, ready to exploit its riches. Players expand the reach of their corporations by building enormous megastructures in space. Gyrodynamic generators ", "headingPath": "SETTING · GAMEPLAY", "sharpsignalDocId": 442}, {"page": 19, "score": 0.044192, "snippet": "Rearrange all four rocket figures according to the four counters on the initiative track. (In the setup for round 1, counters are stacked in reverse order. But at the start of all later rounds, the rocket figures should match the order shown on the initiative track.) This is the new play order. The ", "headingPath": "Production Phase · Final Scoring · TH R EE PL AYER GAME", "sharpsignalDocId": 442}, {"page": 7, "score": 0.042232, "snippet": "Each round begins with a die roll. You use all 9 silver dice in a four-player game. In a two- or three-player game, you use only 7 silver dice. Each player will choose two dice that will be used to buy actions during the Action Phase. The choice of dice affects players' positions on the initiative a", "headingPath": "SUMMARY OF THE DICE PHASE · ROLLING THE DICE · DETERMINING THE MEDIAN", "sharpsignalDocId": 442}, {"page": 8, "score": 0.030769, "snippet": "After each player has taken one die in order, each player takes a second die in reverse order. In the examples on this page, players choose in this order: Green, Yellow, Red, Red, Yellow, Green. The first player will choose his or her second die last. Exception: In a two-player game, each player has", "headingPath": "Second Die · EVEN START VARIANT", "sharpsignalDocId": 442}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 17, "quote": null, "headingPath": "SCORING SUMMARY · During the Action Phase: · During the Production Phase: · At the End of the Game: · END OF GAME · Goal Tiles · …", "sharpsignalDocId": 442}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 442 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 442 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 0.88235 of 34 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Oct 24, 2026 19:52 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 Pulsar 2849 — Rulebook (corpus doc 442) | Final Scoring · Victory | p.17 | 0.04866 (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 Pulsar 2849 — Rulebook (corpus doc 442) | SCORING SUMMARY · During the Action Phase: · During the Production Phase: · At the End of the Game: · END OF GAME · Goal Tiles · … | p.17 | 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 |
| #3 | RULEBOOK Pulsar 2849 — Rulebook (corpus doc 442) | End of Round Summary · Determining Order of Play · Gaining Engineering Cubes · Example: · Penalties · Online Transmitters | p.16 | 0.047883 (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 Pulsar 2849 — Rulebook (corpus doc 442) | p.2 | 0.04598 (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 Pulsar 2849 — Rulebook (corpus doc 442) | SETTING · GAMEPLAY | p.3 | 0.045743 (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 Pulsar 2849 — Rulebook (corpus doc 442) | Production Phase · Final Scoring · TH R EE PL AYER GAME | p.19 | 0.044192 (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 Pulsar 2849 — Rulebook (corpus doc 442) | SUMMARY OF THE DICE PHASE · ROLLING THE DICE · DETERMINING THE MEDIAN | p.7 | 0.042232 (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 Pulsar 2849 — Rulebook (corpus doc 442) | Second Die · EVEN START VARIANT | p.8 | 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 |
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 35 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 Pulsar 2849 — Rulebook (corpus doc 442) | p.2 | #4 | 0.04598 (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 Pulsar 2849 — Rulebook (corpus doc 442) | Final Scoring · Victory | p.17 | #1 | 0.04866 (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 Pulsar 2849 — Rulebook (corpus doc 442) | Planets | p.11 | #11 | 0.027826 (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 |
| #4 | RULEBOOK Pulsar 2849 — Rulebook (corpus doc 442) | End of Round Summary · Determining Order of Play · Gaining Engineering Cubes · Example: · Penalties · Online Transmitters | p.16 | #3 | 0.047883 (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 Pulsar 2849 — Rulebook (corpus doc 442) | ACTION OVERVIEW · FLYING YOUR SURVEY SHIP · Entry Gate · Your Flight · These Are Legal Flights: · These Are Not Legal Flights: | p.10 | #19 | 0.025479 (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 Pulsar 2849 — Rulebook (corpus doc 442) | Transmitters | p.20 | #15 | 0.026199 (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 Pulsar 2849 — Rulebook (corpus doc 442) | SETTING · GAMEPLAY | p.3 | #5 | 0.045743 (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 Pulsar 2849 — Rulebook (corpus doc 442) | SCORING SUMMARY · During the Action Phase: · During the Production Phase: · At the End of the Game: · END OF GAME · Goal Tiles · … | p.17 | #2 | 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 |
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 Pulsar 2849 — Rulebook (corpus doc 442) | SCORING SUMMARY · During the Action Phase: · During the Production Phase: · At the End of the Game: · END OF GAME · Goal Tiles · … | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 170 ms · first delta 1427 ms · total 1595 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 170 ms · ask 1422 ms · gateway work 1595 ms · total 1595 ms
- tokens in (the prompt the answerer read)
- 4149
- tokens out (what the answerer generated)
- 11
- tok/sec
- 177.4 tok/sec — 11 output tokens in 0.062 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 53s 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 6s 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 373), 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.