You asked
How do I play?
Answered counted as answeredAsked with: Kingsburg (Second Edition)bg-199966-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 93 ms · ask 6344 ms · total 6439 ms
- single-flight (PR-5)
- queued 0 ms · generation 6439 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048652, "snippet": "The rules below describe the basic game for 3 to 5 players. For additional rules for a 2-player game, refer to '2-Player Rule Changes' on page 9. The game is played over a series of five rounds called years. Each year is divided into eight phases: four seasons and four special events that occur befo", "headingPath": "Playing the Game · Open Information · Phase 1: The King's Favor · Phase 2: Spring", "sharpsignalDocId": 136}, {"page": 3, "score": 0.047938, "snippet": "3 These are the setup steps for the basic game. If you are playing your first game, follow these steps. If you are using any expansion modules, also follow the setup steps listed under those modules on pages 10-13. Place the game board in the center of the table. On the game board, place the season ", "headingPath": "At the end of each productive Expansion Module Components · Setup", "sharpsignalDocId": 136}, {"page": 9, "score": 0.047131, "snippet": "Cindy's After resolving all battles, return the enemy card to the box and reset each player's disk to space '0' on the soldier track. After winter (phase 8) is finished, the current year ends. If it is the end of year V, the game ends. Otherwise, advance the year marker one space and place the seaso", "headingPath": "Resolving a Battle · End of the Year · Winning the Game · 2-Player Rule Changes", "sharpsignalDocId": 136}, {"page": 2, "score": 0.045285, "snippet": "1 Game Board 6 Bonus Dice 25 Gold 60 Goods 20 Wood A At the end of summer, At the end At the end of 2 K ing Tritus has appointed you, his most trusted governors, to maintain and defend the border provinces from the enemy onslaught. To prosper, you must outmaneuver your rival governors and persuade t", "headingPath": "Object of the Game · Your First Game · Components", "sharpsignalDocId": 136}, {"page": 11, "score": 0.03125, "snippet": "During each phase 8, do not roll a die for the king's reinforcements. Instead, before the enemy card is revealed, each player simultaneously and secretly chooses one of his soldier tokens. When all players have chosen a token, simultaneously reveal the tokens. Each player gains soldiers equal to the", "headingPath": "During the Game · Game End", "sharpsignalDocId": 136}, {"page": 4, "score": 0.030769, "snippet": "Players roll all their dice simultaneously, including any bonus dice. Then, if players have effects that change die results or reroll dice, they may use those effects, following the current turn order. After modifying dice, set the new turn order based on the total value of the dice rolled by each p", "headingPath": "a) Roll Dice and Set Turn Order · Setting the Turn Order", "sharpsignalDocId": 136}, {"page": 10, "score": 0.030303, "snippet": "At the end of setup, before starting the game, shuffle all 14 alternate building strips facedown. If the players are using module 2 but not module 1, remove the A and G strips. Deal two strips to each player. Then each player chooses whether to use both, one, or none of those strips. If a player is ", "headingPath": "Setup", "sharpsignalDocId": 136}, {"page": 5, "score": 0.029851, "snippet": "In turn order, players either influence one advisor or pass. A player who passes cannot influence advisors for the rest of this season. To influence an advisor, a player assigns one or more of his dice to the advisor's space on the board. The total value of the assigned dice must be exactly equal to", "headingPath": "b) Influence the King's Advisors · Influencing the King's Advisors", "sharpsignalDocId": 136}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "Playing the Game · Open Information · Phase 1: The King's Favor · Phase 2: Spring", "sharpsignalDocId": 136}, {"page": 4, "quote": null, "headingPath": "a) Roll Dice and Set Turn Order · Setting the Turn Order", "sharpsignalDocId": 136}, {"page": 7, "quote": null, "headingPath": "d) Construct Buildings · Constructing a Building · Phase 3: The King's Reward · Phase 4: Summer", "sharpsignalDocId": 136}, {"page": 2, "quote": null, "headingPath": "Object of the Game · Your First Game · Components", "sharpsignalDocId": 136}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 136 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 136 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 0.88834 of 1415 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 25, 2026 16:12 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 Kingsburg — Rulebook (corpus doc 136) | Playing the Game · Open Information · Phase 1: The King's Favor · Phase 2: Spring | p.4 | 0.048652 (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 Kingsburg — Rulebook (corpus doc 136) | At the end of each productive Expansion Module Components · Setup | p.3 | 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 |
| #3 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Resolving a Battle · End of the Year · Winning the Game · 2-Player Rule Changes | p.9 | 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 |
| #4 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Object of the Game · Your First Game · Components | p.2 | 0.045285 (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 Kingsburg — Rulebook (corpus doc 136) | During the Game · Game End | p.11 | 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 |
| #6 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | a) Roll Dice and Set Turn Order · Setting the Turn Order | p.4 | 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 |
| #7 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Setup | p.10 | 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 |
| #8 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | b) Influence the King's Advisors · Influencing the King's Advisors | p.5 | 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 |
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 32 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 Kingsburg — Rulebook (corpus doc 136) | At the end of each productive Expansion Module Components · Setup | p.3 | #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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | 8 Treasurer · 9 Master Hunter | p.12 | #16 | 0.013699 (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 |
| #3 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Setup | p.10 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Object of the Game · Your First Game · Components | p.2 | #4 | 0.045285 (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 Kingsburg — Rulebook (corpus doc 136) | Module 6: Alternate Advisor Rewards · Setup · During the Game · 1 Jester · 2 Squire · 3 Architect · … | p.12 | #17 | 0.013514 (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 |
| #6 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | d) Construct Buildings · Constructing a Building · Phase 3: The King's Reward · Phase 4: Summer | p.7 | #15 | 0.013889 (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 |
| #7 | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Playing the Game · Open Information · Phase 1: The King's Favor · Phase 2: Spring | p.4 | #1 | 0.048652 (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 Kingsburg — Rulebook (corpus doc 136) | a) Roll Dice and Set Turn Order · Setting the Turn Order | p.4 | #6 | 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)) | vector + 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 Kingsburg — Rulebook (corpus doc 136) | Playing the Game · Open Information · Phase 1: The King's Favor · Phase 2: Spring | p.4 | no quote on the wire |
| [2] | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | a) Roll Dice and Set Turn Order · Setting the Turn Order | p.4 | no quote on the wire |
| [3] | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | d) Construct Buildings · Constructing a Building · Phase 3: The King's Reward · Phase 4: Summer | p.7 | no quote on the wire |
| [4] | RULEBOOK Kingsburg — Rulebook (corpus doc 136) | Object of the Game · Your First Game · Components | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 93 ms · first delta 3142 ms · total 6439 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 93 ms · ask 6344 ms · gateway work 6439 ms · total 6439 ms
- tokens in (the prompt the answerer read)
- 3182
- tokens out (what the answerer generated)
- 430
- tok/sec
- 132.9 tok/sec — 430 output tokens in 3.236 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 2s 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 58), 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.