You asked
How do I play?
Answered counted as answeredAsked with: Here I Standbg-17392-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 89 ms · ask 7728 ms · total 7820 ms
- single-flight (PR-5)
- queued 0 ms · generation 7820 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 9, "score": 0.047938, "snippet": "The game is played in nine turns or fewer. The first turn represents the period from 1517 to 1523. Each subsequent turn covers a fouryear period. Each turn consists of nine phases. The sixth phase, the Action Phase, is the most time-consuming phase, for it includes a variable number of rounds where ", "headingPath": "7. SEQUENCE OF PLAY", "sharpsignalDocId": 540}, {"page": 15, "score": 0.047643, "snippet": "During the Action Phase, the powers take impulses in the order described in Section 3.2. The power initiating an activity is referred to as the 'active power' throughout these rules. Each impulse consists of one of the following three activities: Playing a card for Command Points (CP) Playing a card", "headingPath": "11. THE ACTION PHASE", "sharpsignalDocId": 540}, {"page": 5, "score": 0.044468, "snippet": "In the six-player game, each player controls a single major power. In games with three to five players, some players control two major powers so that all major powers are in play. A power is a nation or city-state present in the game. The Protestant reformers and the German princes who defended thei", "headingPath": "3.1 Player · 3.2 Power · Major Power · Minor Power · 3.3 Ruler · Attributes", "sharpsignalDocId": 540}, {"page": 24, "score": 0.044337, "snippet": "Attacker Adds Up Dice: The active player is always considered the attacker in a naval combat. The attacker adds up the number of dice he will roll as follows: 1 die for each corsair 2 dice for each naval squadron 1 die for each Battle Rating point from their highest-rated naval leader in the sea zon", "headingPath": "Naval Combat Procedure", "sharpsignalDocId": 540}, {"page": 21, "score": 0.043369, "snippet": "1. Declare Formation: The active player declares which formation of land units and army leaders will be making the assault. All requirements listed above must be met at this time. 2. Play Response Cards: Other powers may play the Response cards Foul Weather and Gout to disrupt this Assault action. T", "headingPath": "Assault Procedure", "sharpsignalDocId": 540}, {"page": 20, "score": 0.041539, "snippet": "1 die for each land unit in the moving formation 1 die for each Battle Rating point from the highest-rated leader in the attacking force Defender Adds Up Battle Dice: The intercepting player or the player with the stack of units in the destination space is always considered the defender in a field b", "headingPath": "Field Battle Procedure", "sharpsignalDocId": 540}, {"page": 19, "score": 0.040293, "snippet": "Play Response Cards: Both sides (starting with the attacker) have one final chance to play the Response cards Landsknechts or Swiss Mercenaries to change the number of units in the space. If the attacker has more units in the space than allowed in the moving formation, excess units do not contribute", "headingPath": "Field Battle Procedure", "sharpsignalDocId": 540}, {"page": 23, "score": 0.0387, "snippet": "1. Declare Naval Moves: The active power declares which naval units and leaders will be moving and designates the destination for each of these units. Each unit's destination must be adjacent to its current location. 2. Execute Naval Move: The active power executes all naval moves. The order of exec", "headingPath": "Naval Movement Procedure", "sharpsignalDocId": 540}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 9, "quote": null, "headingPath": "7. SEQUENCE OF PLAY", "sharpsignalDocId": 540}, {"page": 15, "quote": null, "headingPath": "11. THE ACTION PHASE", "sharpsignalDocId": 540}, {"page": 7, "quote": null, "headingPath": "Mandatory Event Cards", "sharpsignalDocId": 540}, {"page": 21, "quote": null, "headingPath": "Assault Procedure", "sharpsignalDocId": 540}, {"page": 19, "quote": null, "headingPath": "Field Battle Procedure", "sharpsignalDocId": 540}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 540 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 540 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 0.91088 of 2637 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 12:07
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 Here I Stand — Rulebook (corpus doc 540) | 7. SEQUENCE OF PLAY | p.9 | 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 Here I Stand — Rulebook (corpus doc 540) | 11. THE ACTION PHASE | p.15 | 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 |
| #3 | RULEBOOK Here I Stand — Rulebook (corpus doc 540) | 3.1 Player · 3.2 Power · Major Power · Minor Power · 3.3 Ruler · Attributes | p.5 | 0.044468 (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 Here I Stand — Rulebook (corpus doc 540) | Naval Combat Procedure | p.24 | 0.044337 (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 Here I Stand — Rulebook (corpus doc 540) | Assault Procedure | p.21 | 0.043369 (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 Here I Stand — Rulebook (corpus doc 540) | Field Battle Procedure | p.20 | 0.041539 (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 Here I Stand — Rulebook (corpus doc 540) | Field Battle Procedure | p.19 | 0.040293 (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 Here I Stand — Rulebook (corpus doc 540) | Naval Movement Procedure | p.23 | 0.0387 (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 Here I Stand — Rulebook (corpus doc 540) | 7. SEQUENCE OF PLAY | p.9 | #1 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Here I Stand — Rulebook (corpus doc 540) | Field Battle Procedure | p.19 | #7 | 0.040293 (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 Here I Stand — Rulebook (corpus doc 540) | 1. INTRODUCTION · 2. GAME MAP | p.3 | #13 | 0.02619 (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 Here I Stand — Rulebook (corpus doc 540) | Impulse Example | p.16 | #14 | 0.026137 (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 Here I Stand — Rulebook (corpus doc 540) | English Impulses Under Mary I | p.38 | #17 | 0.025528 (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 Here I Stand — Rulebook (corpus doc 540) | Mandatory Event Cards | p.7 | #18 | 0.025 (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 Here I Stand — Rulebook (corpus doc 540) | 11. THE ACTION PHASE | p.15 | #2 | 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 Here I Stand — Rulebook (corpus doc 540) | Assault Procedure | p.21 | #5 | 0.043369 (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 Here I Stand — Rulebook (corpus doc 540) | 7. SEQUENCE OF PLAY | p.9 | no quote on the wire |
| [2] | RULEBOOK Here I Stand — Rulebook (corpus doc 540) | 11. THE ACTION PHASE | p.15 | no quote on the wire |
| [3] | RULEBOOK Here I Stand — Rulebook (corpus doc 540) | Mandatory Event Cards | p.7 | no quote on the wire |
| [4] | RULEBOOK Here I Stand — Rulebook (corpus doc 540) | Assault Procedure | p.21 | no quote on the wire |
| [5] | RULEBOOK Here I Stand — Rulebook (corpus doc 540) | Field Battle Procedure | p.19 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 89 ms · first delta 4048 ms · total 7820 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 89 ms · ask 7728 ms · gateway work 7820 ms · total 7820 ms
- tokens in (the prompt the answerer read)
- 3042
- tokens out (what the answerer generated)
- 763
- tok/sec
- 204.7 tok/sec — 763 output tokens in 3.727 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s 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 472), 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.