You asked
How do I play?
Answered counted as answeredAsked with: Paths of Glorybg-91-en-1e
🔧 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 98 ms · ask 10078 ms · total 10179 ms
- single-flight (PR-5)
- queued 0 ms · generation 10179 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 12, "score": 0.04741, "snippet": "\u00182.2.\u0018 Each Combat is resolved using the following steps in the order given: Designate the Combat Determine Combat Strengths Play trench-negating Combat Cards Attempt Flank Attack Play Combat Cards Determine DRM Determine Fire Column Determine Results Take Losses Determine Combat Winner Defender Ret", "headingPath": "\u00182.2 Combat Resolution", "sharpsignalDocId": 337}, {"page": 7, "score": 0.046871, "snippet": "8.\u0018.\u0018 There are six Action Rounds per Action Phase. In each Action Round, each player is allowed to take only one of six possible actions. 8.\u0018.2 The Central Powers player conducts the first action in each Action Round. 8.\u0018.3 Each player must take one of six possible actions: Play a Strategy Card as ", "headingPath": "8.\u0018 General Rules · 9.\u0018 General Rules", "sharpsignalDocId": 337}, {"page": 8, "score": 0.043941, "snippet": "9.\u0018.3 Each Strategy Card can be used in one of four possible ways: for Operations (OPS), for Strategic Redeployment (SR), for Replacement Points (RP), or as an Event. The same card can be used either in the same way or in a different way each time it is played during a game, but each card can be use", "headingPath": "9.\u0018 General Rules", "sharpsignalDocId": 337}, {"page": 6, "score": 0.041317, "snippet": "E.\u0018. Check the Victory Point table and make any changes called for under the 'During the War Status Phase' section of the table. E.2. Determine if either player has won an Automatic Victory. E.3. Determine if an Armistice has been declared. E.4. Each player determines if his War Commitment Level has", "headingPath": "E. War Status Phase · F. Replacement Phase · G. Draw Strategy Card Phase · H. End of Turn", "sharpsignalDocId": 337}, {"page": 25, "score": 0.040267, "snippet": "This extended example of play will demonstrate how many of the game's mechanics work and will give you some initial strategy ideas. The game was conducted by email between Gene Billingsley, as the Allied player, and Andy Lewis, the game's developer, as the Central Powers. Neither player was an exper", "headingPath": "Extended Example · August \u00189\u00184 - Mandated Offensive Phase · August \u00189\u00184 - Action Phase Central Powers Action \u0018", "sharpsignalDocId": 337}, {"page": 4, "score": 0.040259, "snippet": "4.3.\u0018 The Central Powers player may choose whether or not to start the game with the Guns of August event Strategy Card in his hand. The Central Powers player must inform the Allied player of his decision. In either case, the Central Powers Mobilization Cards are shuffled and the Central Powers play", "headingPath": "4.3 Initial Strategy Cards", "sharpsignalDocId": 337}, {"page": 1, "score": 0.03885, "snippet": "\u0018.0 Introduction .............................. 2 2.0 Components .............................. 2 2.1 The Game Map ........................ 2 2.2 The Playing Pieces ................. 2 2.3 The Strategy Cards .................. 3 2.4 Unit Abbreviations .................. 3 2.5 Questions? ............", "headingPath": "", "sharpsignalDocId": 337}, {"page": 2, "score": 0.030769, "snippet": "These rules are organized into seventeen numbered sections (1.0 through 17.0) and some sections are further subdivided into subsections (for example, 2.1 and 2.2). In a number of places in the rules, you will see references made to rules sections and subsections that are related to the one you are r", "headingPath": "\u0018.0 Introduction", "sharpsignalDocId": 337}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 7, "quote": null, "headingPath": "8.\u0018 General Rules · 9.\u0018 General Rules", "sharpsignalDocId": 337}, {"page": 12, "quote": null, "headingPath": "\u00182.2 Combat Resolution", "sharpsignalDocId": 337}, {"page": 10, "quote": null, "headingPath": "9.5.4 Combat Event Cards", "sharpsignalDocId": 337}, {"page": 9, "quote": null, "headingPath": "9.5.3 Reinforcement Event Cards", "sharpsignalDocId": 337}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 337 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 337 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 0.89979 of 2874 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 09:54
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 Paths of Glory — Rulebook (corpus doc 337) | 2.2 Combat Resolution | p.12 | 0.04741 (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 Paths of Glory — Rulebook (corpus doc 337) | 8. General Rules · 9. General Rules | p.7 | 0.046871 (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 Paths of Glory — Rulebook (corpus doc 337) | 9. General Rules | p.8 | 0.043941 (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 Paths of Glory — Rulebook (corpus doc 337) | E. War Status Phase · F. Replacement Phase · G. Draw Strategy Card Phase · H. End of Turn | p.6 | 0.041317 (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 Paths of Glory — Rulebook (corpus doc 337) | Extended Example · August 94 - Mandated Offensive Phase · August 94 - Action Phase Central Powers Action | p.25 | 0.040267 (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 Paths of Glory — Rulebook (corpus doc 337) | 4.3 Initial Strategy Cards | p.4 | 0.040259 (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 Paths of Glory — Rulebook (corpus doc 337) | p.1 | 0.03885 (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 Paths of Glory — Rulebook (corpus doc 337) | .0 Introduction | p.2 | 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 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 Paths of Glory — Rulebook (corpus doc 337) | 9.5.3 Reinforcement Event Cards | p.9 | #16 | 0.026084 (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 Paths of Glory — Rulebook (corpus doc 337) | 8. General Rules · 9. General Rules | p.7 | #2 | 0.046871 (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 Paths of Glory — Rulebook (corpus doc 337) | 2.2 Combat Resolution | p.12 | #1 | 0.04741 (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 Paths of Glory — Rulebook (corpus doc 337) | 9.3 Strategic Redeployment · 9.4 Replacement Points (RPs) | p.8 | #12 | 0.02748 (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 |
| #5 | RULEBOOK Paths of Glory — Rulebook (corpus doc 337) | 6.3 US Entry | p.20 | #10 | 0.02901 (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 Paths of Glory — Rulebook (corpus doc 337) | Central Powers Action · Allied Action · Central Powers Action 2 · Allied Action 2 | p.29 | #11 | 0.027623 (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 Paths of Glory — Rulebook (corpus doc 337) | 9.5.4 Combat Event Cards | p.10 | #15 | 0.026519 (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 Paths of Glory — Rulebook (corpus doc 337) | 9. General Rules | p.8 | #3 | 0.043941 (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 Paths of Glory — Rulebook (corpus doc 337) | 8. General Rules · 9. General Rules | p.7 | no quote on the wire |
| [2] | RULEBOOK Paths of Glory — Rulebook (corpus doc 337) | 2.2 Combat Resolution | p.12 | no quote on the wire |
| [3] | RULEBOOK Paths of Glory — Rulebook (corpus doc 337) | 9.5.4 Combat Event Cards | p.10 | no quote on the wire |
| [4] | RULEBOOK Paths of Glory — Rulebook (corpus doc 337) | 9.5.3 Reinforcement Event Cards | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 98 ms · first delta 6118 ms · total 10179 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 98 ms · ask 10078 ms · gateway work 10179 ms · total 10179 ms
- tokens in (the prompt the answerer read)
- 3157
- tokens out (what the answerer generated)
- 827
- tok/sec
- 205.6 tok/sec — 827 output tokens in 4.023 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 47s ago)
- 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 265), 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.