You asked
How do I play?
Answered counted as answeredAsked with: Gutenbergbg-339958-en-1e
Settled. Play on.
🔧 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 127 ms · ask 4708 ms · total 4836 ms
- single-flight (PR-5)
- queued 0 ms · generation 4836 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04918, "snippet": "Place the main board in the center of the table, with the correct side up for the number of players. Use the spaces with the symbol only when playing with 4 players. When playing with 2 players, use the board side marked: Shuffle both decks of order cards (printing cards and refinement cards) separa", "headingPath": "Game Preparation", "sharpsignalDocId": 1229}, {"page": 16, "score": 0.047379, "snippet": "The automa simulates an abstracted additional player in the Plan and Execute Plans steps. When the automa acts, it will randomly discard resources from the main board. The automa enables solitaire play. It can also be added to a game with 2 or 3 players. Components for the automa: Initiative board (", "headingPath": "Automa · Game preparation · Game rules", "sharpsignalDocId": 1229}, {"page": 5, "score": 0.047131, "snippet": "f2 16 g2 13 f1 15 c e a 5 b 14 i 2 6 8 d h 17 Each player chooses their player color and takes: a printing house board ; an initiative board ; a screen ; a set of initiative markers according to this table: 3 gray cylinders , which should be pushed into the 3 gear axle holes on the printing house bo", "headingPath": "Game Preparation", "sharpsignalDocId": 1229}, {"page": 7, "score": 0.046642, "snippet": "Players plan actions for the current round. Each player hides their initiative board and initiative markers behind their screen. They simultaneously allocate their markers among the 5 actions. Markers go on empty slots (from left to right) on a desired action's row. A row can have at most 6 markers.", "headingPath": "2. PLAN", "sharpsignalDocId": 1229}, {"page": 6, "score": 0.045455, "snippet": "Printing technology enabled the spread of knowledge, thoughts, and ideas. For this reason, the invention of printing is considered one of the pivotal global events ending the Middle Ages. At the local level, talented craftsmen and efficient entrepreneurs have a great opportunity to develop a profita", "headingPath": "Sequence of Play · 1. TURN GEARS", "sharpsignalDocId": 1229}, {"page": 4, "score": 0.032258, "snippet": "Guilders and types are unlimited. In case they run out, players may improvise as needed, e.g. using spare type tokens included in the game as substitutes. Each player says which book they most recently read; whoever's book is the thickest will be the first player and receives the first player token.", "headingPath": "Game Preparation", "sharpsignalDocId": 1229}, {"page": 8, "score": 0.029851, "snippet": "For each action, players do that action in the order determined by how they planned on their initiative boards. Each acting player may choose one printing card and one refinement card from the main board, creating an order, then places this order in a free slot beside their printing house. The 2 car", "headingPath": "3. EXECUTE PLANS · a. Take Orders · Order as a Reward · Example:", "sharpsignalDocId": 1229}, {"page": 17, "score": 0.029412, "snippet": "- the action with the most initiative markers. If there is a tie for minimum or for maximum, then scan the actions, starting at the action printed in the middle of the planning card F , then scanning downward, possibly wrapping around to the top action and continuing, until you reach one of the tied", "headingPath": "Actions", "sharpsignalDocId": 1229}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "Sequence of Play · 1. TURN GEARS", "sharpsignalDocId": 1229}, {"page": 7, "quote": null, "headingPath": "2. PLAN", "sharpsignalDocId": 1229}, {"page": 8, "quote": null, "headingPath": "3. EXECUTE PLANS · a. Take Orders · Order as a Reward · Example:", "sharpsignalDocId": 1229}, {"page": 8, "quote": null, "headingPath": "b. Take Inks", "sharpsignalDocId": 1229}, {"page": 9, "quote": null, "headingPath": "c. Develop Specialties · Example:", "sharpsignalDocId": 1229}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1229 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1229 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 0.92254 of 1420 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 03:10 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 Gutenberg — Rulebook (corpus doc 1229) | Game Preparation | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | Automa · Game preparation · Game rules | p.16 | 0.047379 (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 Gutenberg — Rulebook (corpus doc 1229) | Game Preparation | p.5 | 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 Gutenberg — Rulebook (corpus doc 1229) | 2. PLAN | p.7 | 0.046642 (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 Gutenberg — Rulebook (corpus doc 1229) | Sequence of Play · 1. TURN GEARS | p.6 | 0.045455 (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 Gutenberg — Rulebook (corpus doc 1229) | Game Preparation | p.4 | 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 |
| #7 | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | 3. EXECUTE PLANS · a. Take Orders · Order as a Reward · Example: | p.8 | 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 Gutenberg — Rulebook (corpus doc 1229) | Actions | p.17 | 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 |
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 34 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 Gutenberg — Rulebook (corpus doc 1229) | Game Preparation | p.4 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | Game Preparation | p.4 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | 2. PLAN | p.7 | #4 | 0.046642 (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 Gutenberg — Rulebook (corpus doc 1229) | Sequence of Play · 1. TURN GEARS | p.6 | #5 | 0.045455 (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 Gutenberg — Rulebook (corpus doc 1229) | c. Develop Specialties · Example: | p.9 | #13 | 0.014085 (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 Gutenberg — Rulebook (corpus doc 1229) | 3. EXECUTE PLANS · a. Take Orders · Order as a Reward · Example: | p.8 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | Automa · Game preparation · Game rules | p.16 | #2 | 0.047379 (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 Gutenberg — Rulebook (corpus doc 1229) | b. Take Inks | p.8 | #18 | 0.012987 (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 |
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 Gutenberg — Rulebook (corpus doc 1229) | Sequence of Play · 1. TURN GEARS | p.6 | no quote on the wire |
| [2] | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | 2. PLAN | p.7 | no quote on the wire |
| [3] | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | 3. EXECUTE PLANS · a. Take Orders · Order as a Reward · Example: | p.8 | no quote on the wire |
| [4] | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | b. Take Inks | p.8 | no quote on the wire |
| [5] | RULEBOOK Gutenberg — Rulebook (corpus doc 1229) | c. Develop Specialties · Example: | p.9 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 127 ms · first delta 2753 ms · total 4836 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 127 ms · ask 4708 ms · gateway work 4836 ms · total 4836 ms
- tokens in (the prompt the answerer read)
- 3103
- tokens out (what the answerer generated)
- 399
- tok/sec
- 201.2 tok/sec — 399 output tokens in 1.983 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 26s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 8s 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 1159), 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.