You asked
How do I play?
Answered counted as answeredAsked with: Rex: Final Days of an Empirebg-104363-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 201 ms · ask 8348 ms · total 8551 ms
- single-flight (PR-5)
- queued 0 ms · generation 8551 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.048387, "snippet": "Some rules and abilities refer to the first player and order of play . A player is considered to be the first player while he has the first player token. The order of play for each Phase always begins with the first player and proceeds to the next player clockwise around the table. If two or more pl", "headingPath": "First Player and Order of Play", "sharpsignalDocId": 1167}, {"page": 5, "score": 0.048172, "snippet": "Before playing Rex , perform the following steps to set up the game: Place Game Board: Unfold the game board and place it in the center of the table. Set Up Influence Tokens: Place all influence tokens in the influence area on the edge of the game board. This forms the influence pool . Set Up Decks:", "headingPath": "Game Setup", "sharpsignalDocId": 1167}, {"page": 23, "score": 0.047643, "snippet": "This section contains variations on the rules that modify the game to provide different play experiences. Before each game, players must decide as a group if they would like to use one of the following options, or a combination of both. Rex is a game that relies heavily on diplomacy, deal making, an", "headingPath": "Optional Rules · Playing with Fewer than Six Players · Three-Player Game · Four-Player Game · Five-Player Game", "sharpsignalDocId": 1167}, {"page": 17, "score": 0.045724, "snippet": "When two players have units in the same space during the Battle Phase, a battle must be resolved. In the case in which more than two players' units occupy the same space, multiple two player battles are resolved in the area, one at a time as determined by the order of play (see \"Phase 5: Battle\" on ", "headingPath": "Resolving Battles", "sharpsignalDocId": 1167}, {"page": 5, "score": 0.045635, "snippet": "For example, if players reveal a '3' and a '9' on their battle dials, the dreadnought fleet is placed on sector six (see \"Phase 7: Bombardment\" on page 12). If both players choose the same number, or if the number exceeds 18, place the dreadnought fleet on sector one. Draw Strategy Cards: Each playe", "headingPath": "First Player and Order of Play", "sharpsignalDocId": 1167}, {"page": 7, "score": 0.045055, "snippet": "Race Icon: Identifies which components belong to a specific race. Advantages: Describes the special abilities and advantages the player may use during the game. Free Recruitment: Lists how many units the player may recruit (return from the casualty pool to his reserve) for free during each Recruitme", "headingPath": "Race Sheet · Playing the Game", "sharpsignalDocId": 1167}, {"page": 6, "score": 0.043461, "snippet": "6", "headingPath": "First Player and Order of Play", "sharpsignalDocId": 1167}, {"page": 9, "score": 0.04207, "snippet": "During the Bidding Phase, players bid influence against one another in an attempt to purchase Strategy cards. At the start of this Phase, the first player draws a number of Strategy cards equal to the number of players (excluding players who have reached their hand limit of four cards). These cards ", "headingPath": "Phase 2: Bidding", "sharpsignalDocId": 1167}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 5, "quote": null, "headingPath": "Game Setup", "sharpsignalDocId": 1167}, {"page": 5, "quote": null, "headingPath": "First Player and Order of Play", "sharpsignalDocId": 1167}, {"page": 5, "quote": null, "headingPath": "First Player and Order of Play", "sharpsignalDocId": 1167}, {"page": 20, "quote": null, "headingPath": "Timing Conflicts · Game Board Clarification", "sharpsignalDocId": 1167}, {"page": 17, "quote": null, "headingPath": "Resolving Battles", "sharpsignalDocId": 1167}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1167 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1167 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 0.92859 of 3319 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 6, 2026 13:54 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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.5 | 0.048387 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Game Setup | p.5 | 0.048172 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Optional Rules · Playing with Fewer than Six Players · Three-Player Game · Four-Player Game · Five-Player Game | p.23 | 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 |
| #4 | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Resolving Battles | p.17 | 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 |
| #5 | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.5 | 0.045635 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Race Sheet · Playing the Game | p.7 | 0.045055 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.6 | 0.043461 (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)) | 1 |
| #8 | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Phase 2: Bidding | p.9 | 0.04207 (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 74 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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.5 | #1 | 0.048387 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.5 | #5 | 0.045635 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Timing Conflicts · Game Board Clarification | p.20 | #12 | 0.027651 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Resolving Battles | p.17 | #4 | 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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.6 | #7 | 0.043461 (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 |
| #6 | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Important Terms | p.9 | #15 | 0.026154 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Optional Rules · Playing with Fewer than Six Players · Three-Player Game · Four-Player Game · Five-Player Game | p.23 | #3 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Game Setup | p.5 | #2 | 0.048172 (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 Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Game Setup | p.5 | no quote on the wire |
| [2] | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.5 | no quote on the wire |
| [3] | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | First Player and Order of Play | p.5 | no quote on the wire |
| [4] | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Timing Conflicts · Game Board Clarification | p.20 | no quote on the wire |
| [5] | RULEBOOK Rex: Final Days of an Empire — Rulebook (corpus doc 1167) | Resolving Battles | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 201 ms · first delta 4000 ms · total 8551 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 201 ms · ask 8348 ms · gateway work 8551 ms · total 8551 ms
- tokens in (the prompt the answerer read)
- 2833
- tokens out (what the answerer generated)
- 910
- tok/sec
- 202.4 tok/sec — 910 output tokens in 4.497 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 56s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 2s 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 1097), 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.