You asked
How do I play?
Answered counted as answeredAsked with: Imperial Strugglebg-206480-en-1e
The book has spoken.
🔧 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 160 ms · ask 6599 ms · total 6761 ms
- single-flight (PR-5)
- queued 0 ms · generation 6761 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 2, "score": 0.047938, "snippet": "PLAY NOTE: Many players may wish to start with the Extended Example of Play on page 3 of the Playbook and consult these rules only in the context of an actual game's course and flow. Imperial Struggle consists of six Peace Turns, interrupted by four Wars (the War of the Spanish Succession, the War o", "headingPath": "2.0 Summary of Play · 2.1 Turn Types · 2.2 Peace Turns · 2.3 War Turns · 2.4 Victory", "sharpsignalDocId": 464}, {"page": 10, "score": 0.047131, "snippet": "If the game reaches this phase on Turn 6, and neither France nor Britain has won the game, Final Scoring is carried out (see 11.0). After that, France wins if the VP total is 16 or more, and Britain wins if the VP total is 14 or less. If the VP total is 15, the player with more Available Debt wins. ", "headingPath": "4.1.14 Final Scoring Phase · 5.0 Action Rounds · 5.1 Select an Investment Tile · 5.2 Play an Event Card", "sharpsignalDocId": 464}, {"page": 9, "score": 0.046175, "snippet": "Nine Investment tiles from the Investment Tile Stack are turned face up and placed in the Available Investment Tile spaces on the Investment Tile Display. If there are insufficient Investment tiles in the Investment Tile Stack, make available all remaining tiles in the stack, then shuffle all of the", "headingPath": "4.1.6 Deal Cards Phase · 4.1.7 Ministry Phase · 4.1.8 Initiative Phase (skip on Turn 1)", "sharpsignalDocId": 464}, {"page": 11, "score": 0.045928, "snippet": "Event effects that are simply granted without AP expenditure do not need to obey connection requirements. After an Event card is played and resolved, remove it from the game. PLAY NOTE: In many card-driven games, only some Events are removed after play. Not so in Imperial Struggle ! An Event that ge", "headingPath": "5.2 Play an Event Card", "sharpsignalDocId": 464}, {"page": 1, "score": 0.045055, "snippet": "RULES OF PLAY GMT Games, LLC • P.O. Box 1308, Hanford, CA 93232-1308 • www.GMTGames.com 1.0 Introduction ..............................................................2 2.0 Summary of Play ..................................................... 2 3.0 Components ........................................", "headingPath": "", "sharpsignalDocId": 464}, {"page": 16, "score": 0.042509, "snippet": "If one player won every theater of the just-resolved War with the maximum possible Spoils of War, that player wins the game immediately. Otherwise, check the VP total in the same way as in a Peace Turn's Victory Check Phase. If neither player has won the game, the game continues. The players remove ", "headingPath": "7.4 Victory Check Phase · 7.5 Reset Phase (War) · 7.6 War Layout Phase · 8.0 Advantage Tiles · 8.1 Controlling an Advantage Tile", "sharpsignalDocId": 464}, {"page": 10, "score": 0.040523, "snippet": "EXTRA REQUIREMENTS: Note that some Award tiles have an additional requirement, indicated on the tile as a smaller red number. This number indicates that, to win the award, a player must have an even greater edge in total Markets, Forts, Political Spaces, Territories, and Naval spaces. In this case, ", "headingPath": "4.1.12 Scoring Phase · 4.1.13 Victory Check Phase", "sharpsignalDocId": 464}, {"page": 9, "score": 0.032258, "snippet": "The players now take Action Rounds, beginning with whichever player the Initiative player decided would go first, and alternating thereafter until each player has completed four Action Rounds. All actions must be resolved before the other player starts their next Action Round. The player taking an A", "headingPath": "4.1.9 Action Phase · 4.1.10 Reduce Treaty Points Phase · 4.1.11 Resolve Remaining Powers · 4.1.12 Scoring Phase", "sharpsignalDocId": 464}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 10, "quote": null, "headingPath": "4.1.14 Final Scoring Phase · 5.0 Action Rounds · 5.1 Select an Investment Tile · 5.2 Play an Event Card", "sharpsignalDocId": 464}, {"page": 11, "quote": null, "headingPath": "5.2 Play an Event Card", "sharpsignalDocId": 464}, {"page": 11, "quote": null, "headingPath": "5.2 Play an Event Card", "sharpsignalDocId": 464}, {"page": 11, "quote": null, "headingPath": "5.3 Resolve an Investment Tile's Action · 5.3.1 Investment Tile Action Types · 5.3.2 Investment Tile Action Points · 5.3.3 Military Upgrades", "sharpsignalDocId": 464}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 464 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 464 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 0.92960 of 1250 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 24, 2026 14:41 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 Imperial Struggle — Rulebook (corpus doc 464) | 2.0 Summary of Play · 2.1 Turn Types · 2.2 Peace Turns · 2.3 War Turns · 2.4 Victory | p.2 | 0.047938 (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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.14 Final Scoring Phase · 5.0 Action Rounds · 5.1 Select an Investment Tile · 5.2 Play an Event Card | p.10 | 0.047131 (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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.6 Deal Cards Phase · 4.1.7 Ministry Phase · 4.1.8 Initiative Phase (skip on Turn 1) | p.9 | 0.046175 (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 Imperial Struggle — Rulebook (corpus doc 464) | 5.2 Play an Event Card | p.11 | 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 |
| #5 | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | p.1 | 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 | |
| #6 | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | 7.4 Victory Check Phase · 7.5 Reset Phase (War) · 7.6 War Layout Phase · 8.0 Advantage Tiles · 8.1 Controlling an Advantage Tile | p.16 | 0.042509 (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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.12 Scoring Phase · 4.1.13 Victory Check Phase | p.10 | 0.040523 (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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.9 Action Phase · 4.1.10 Reduce Treaty Points Phase · 4.1.11 Resolve Remaining Powers · 4.1.12 Scoring Phase | p.9 | 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 |
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 62 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 Imperial Struggle — Rulebook (corpus doc 464) | 5.2 Play an Event Card | p.11 | #9 | 0.030679 (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 |
| #2 | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | 5.3 Resolve an Investment Tile's Action · 5.3.1 Investment Tile Action Types · 5.3.2 Investment Tile Action Points · 5.3.3 Military Upgrades | p.11 | #10 | 0.029762 (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 |
| #3 | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | p.1 | #5 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it | |
| #4 | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | 5.3.4 Purchases in Multiple Regions | p.11 | #40 | 0.012821 (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 Imperial Struggle — Rulebook (corpus doc 464) | 6.4 Available Debt · 7.0 Wars · 7.1 War Resolution Phase · 7.1.1 Reveal War Tiles | p.14 | #15 | 0.025974 (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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.2 Debt Limit Increase Phase · 4.1.3 Award Phase · 4.1.4 Global Demand Phase · 4.1.5 Reset Phase (Peace) | p.9 | #13 | 0.026014 (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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.14 Final Scoring Phase · 5.0 Action Rounds · 5.1 Select an Investment Tile · 5.2 Play an Event Card | p.10 | #2 | 0.047131 (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 Imperial Struggle — Rulebook (corpus doc 464) | 5.2 Play an Event Card | p.11 | #4 | 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)) | 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 Imperial Struggle — Rulebook (corpus doc 464) | 4.1.14 Final Scoring Phase · 5.0 Action Rounds · 5.1 Select an Investment Tile · 5.2 Play an Event Card | p.10 | no quote on the wire |
| [2] | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | 5.2 Play an Event Card | p.11 | no quote on the wire |
| [3] | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | 5.2 Play an Event Card | p.11 | no quote on the wire |
| [4] | RULEBOOK Imperial Struggle — Rulebook (corpus doc 464) | 5.3 Resolve an Investment Tile's Action · 5.3.1 Investment Tile Action Types · 5.3.2 Investment Tile Action Points · 5.3.3 Military Upgrades | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 160 ms · first delta 4165 ms · total 6761 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 160 ms · ask 6599 ms · gateway work 6761 ms · total 6761 ms
- tokens in (the prompt the answerer read)
- 2996
- tokens out (what the answerer generated)
- 336
- tok/sec
- 133.9 tok/sec — 336 output tokens in 2.509 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 40s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, 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 394), 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.