You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Mariabg-40354-en-1e
Before anyone takes a turn, everything is laid out as follows: 1. Players decide who plays which role [1]. 2. The turn marker is placed on space 1 on the time track [1]. 3. One army sheet is divided into four quarters, with one quarter given to each player and the fourth set aside for Winter Scoring [1]. 4. All pieces are set up as indicated on the game board [1]. 5. Generals are placed on set-up cities marked with their rank number in their colour, and supply trains are placed on set-up cities marked with a "T" in their colour [1]. 6. The two Austrian hussars are placed beside the board [1]. 7. One Prussian general is placed in the off-map box Ostpreussen and one Prussian supply train is placed in the victory box Silesia [1]. 8. Victory markers are put into each major power's corresponding pool: Prussia 13, France 11, Pragmatic Army 8, and Austria 8 [1]. 9. One of the four Tactical Card decks is shuffled for immediate use as the draw deck, while the other three decks are set aside [1]. 10. Prussia puts 1 victory marker each on its fortresses in Silesia (Liegnitz and Glogau), and Austria puts victory markers on the other 5 Silesian fortresses [1]. 11. Each power draws its initial hand of Tactical Cards: Prussia 9, Saxony 3, France 2, Bavaria 5, Pragmatic Army 3, and Austria 5 [1]. 12. Each player secretly assigns all of a power's troops to its generals by writing numbers in the boxes next to the names of the generals (each general must receive at least 1 troop, unless otherwise indicated on the army sheets, and no more than 8) [1]. 13. The fortresses Köln and Mannheim are marked with French elector markers, and the fortresses Mainz and Trier are marked with Austrian-Pragmatic elector markers [1].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 231 ms · ask 10207 ms · total 10446 ms
- single-flight (PR-5)
- queued 0 ms · generation 10446 ms
- retrieval refs (raw)
- [{"page": 8, "score": 0.032787, "snippet": "At the beginning of every turn, the political stage takes place. Only major powers may engage in politics. To do so, each turn they can choose to place 1 TC on the political display. According to the values of the placed cards, the order of in uence is determined. In this order the major powers are ", "headingPath": "17 POLITICS · 17.1 Reveal 2 Political Cards · 17.2 Determine the political trump suit · 17.3 Place TCs on the political display · 17.4 Determine order of in uence", "sharpsignalDocId": 460}, {"page": 3, "score": 0.032258, "snippet": "The game is played in turns. Each turn consists of 5 stages, which are carried out in strict order: Major Powers conduct politics (advanced game only). Austria places its hussars. Action stage of Prussia and Saxony. Action stage of France and Bavaria. Action stage of Austria and Pragmatic Army. The ", "headingPath": "5 SEQUENCE OF PLAY", "sharpsignalDocId": 460}, {"page": 9, "score": 0.031746, "snippet": "Card on which its coat of arms are depicted. If there is no such Political Card, a power must conserve its TC. Furthermore, a major power does not participate at all in this phase, if it currently has no TCs on the political display. If a major power decides to conserve its TC, all its TCs on the po", "headingPath": "17.5 Select Political Cards", "sharpsignalDocId": 460}, {"page": 4, "score": 0.03125, "snippet": "At the beginning of its action stage, every active power draws a certain number of Tactical Cards (TCs) from the draw deck: | France | 4 (5) | TCs | Bavaria | 2 (1) | TCs | | Prussia | 3 | TCs | Saxony | 1 | TC | | Pragm. Army | 3 | TCs | Austria | 5 | TCs | NOTE : In the rst 3 turns, France draws 4", "headingPath": "8 TACTICAL CARDS PHASE", "sharpsignalDocId": 460}, {"page": 3, "score": 0.030769, "snippet": "Players can decide randomly or by mutual agreement who is playing which role. Put the turn marker on the space 1 on the time track (see the top-right corner of the board). Divide one army sheet into four quarters. Give one quarter to each player. Set aside the fourth quarter (called Winter Scoring )", "headingPath": "4 HOWTOSTART", "sharpsignalDocId": 460}, {"page": 9, "score": 0.030303, "snippet": "If the power selecting a Political Card decides to execute it, then: follow the instruction on it; and shift the marker on the Italy, Russia, and/or Saxony track according to the depicted arrows. Some cards allow the shifting of the political marker to the left or to the right; in this case the play", "headingPath": "Execution of Political Cards", "sharpsignalDocId": 460}, {"page": 11, "score": 0.029851, "snippet": "A major power wins immediately, ending the game, if its pool of victory markers is empty at the end of any action stage (its own or of another power) or at the end of any political stage. If more than one power has an empty victory pool, award victory to the power with an empty pool that could have ", "headingPath": "23 VICTORY CONDITIONS", "sharpsignalDocId": 460}, {"page": 3, "score": 0.029412, "snippet": "In compliance with the minimum set-up values, Friedrich receives 8 troops, Schwerin 4, Erbprinz Leopold 4, der Alte Dessauer 6. Mark the fortresses K ln and Mannheim with French elector markers, and the fortresses Mainz and Trier with Austrian-Pragmatic elector markers. In the Electoral College, put", "headingPath": "4 HOWTOSTART", "sharpsignalDocId": 460}]
- citations (raw)
- [{"page": 3, "quote": null, "headingPath": "4 HOWTOSTART", "sharpsignalDocId": 460}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 460 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 460 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)
- debug row retained until
- Nov 7, 2026 05:48
retrieval — what the search arm returned
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 Maria — Rulebook (corpus doc 460) | 17 POLITICS · 17.1 Reveal 2 Political Cards · 17.2 Determine the political trump suit · 17.3 Place TCs on the political display · 17.4 Determine order of in uence | p.8 | 0.032787 (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 Maria — Rulebook (corpus doc 460) | 5 SEQUENCE OF PLAY | p.3 | 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 |
| #3 | RULEBOOK Maria — Rulebook (corpus doc 460) | 17.5 Select Political Cards | p.9 | 0.031746 (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 Maria — Rulebook (corpus doc 460) | 8 TACTICAL CARDS PHASE | p.4 | 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 |
| #5 | RULEBOOK Maria — Rulebook (corpus doc 460) | 4 HOWTOSTART | p.3 | 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 |
| #6 | RULEBOOK Maria — Rulebook (corpus doc 460) | Execution of Political Cards | p.9 | 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 |
| #7 | RULEBOOK Maria — Rulebook (corpus doc 460) | 23 VICTORY CONDITIONS | p.11 | 0.029851 (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 Maria — Rulebook (corpus doc 460) | 4 HOWTOSTART | p.3 | 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 |
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 Maria — Rulebook (corpus doc 460) | 4 HOWTOSTART | p.3 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 231 ms · first delta 7075 ms · total 10446 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 231 ms · ask 10207 ms · gateway work 10446 ms · total 10446 ms
- tokens in (the prompt the answerer read)
- 4036
- tokens out (what the answerer generated)
- 438
- tok/sec
- 133.3 tok/sec — 438 output tokens in 3.285 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 11s 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 390), 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.