You asked
How do I play?
Answered counted as answeredAsked with: Spyriumbg-137269-en-1e
The table has its answer — dice up.
🔧 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 235 ms · ask 5712 ms · total 5952 ms
- single-flight (PR-5)
- queued 0 ms · generation 5952 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04918, "snippet": "The game lasts for 6 turns, and is divided into 3 periods (A: turns 1 through 3, B: turns 4 and 5, and C: turn 6). Note: during the game, some cards from the A and B periods will not be used. Each player gets revenue from the bank. The amount gained is indicated by the position of their disc on the ", "headingPath": "Game overview · 1) Beginning of the turn · 2) Placement and Activation", "sharpsignalDocId": 975}, {"page": 6, "score": 0.045541, "snippet": "The game ends after the sixth turn of play. Each player then adds the following victory points to those scored during the game (which are indicated by the score track): victory points indicated on the buildings present in their neighborhood (the buildings which have been replaced aren't worth any po", "headingPath": "End of the game", "sharpsignalDocId": 975}, {"page": 3, "score": 0.032258, "snippet": "Spyrium Token Each player leads an industrial conglomerate. During the game, the players will score victory points by constructing buildings, by employing their workers in them, by patenting techniques, and by calling on special characters. At the end of the game, the player who has scored the most ", "headingPath": "Game Rules · Goal of the game · 1 board", "sharpsignalDocId": 975}, {"page": 6, "score": 0.031746, "snippet": "Example: Blue constructs a Factory, and pays £6 (its cost) + £2 (2 workers next to the card). To place it, they can either spend £2 to put it in a new space, or spend nothing more if they replace their Working-Class Neighborhood, or else reduce £3 from the cost of the Factory if they replace their L", "headingPath": "d) Activate a card · e) Use a building · f) Pass · End of the turn", "sharpsignalDocId": 975}, {"page": 4, "score": 0.03125, "snippet": "This action can only be performed during the Place -ment phase. The player takes one of the workers from the Start card and places it in the market between two adjacent cards or between a card and an empty card space . There are no limits to the number of workers which can be placed between any two ", "headingPath": "a) Place a worker", "sharpsignalDocId": 975}, {"page": 5, "score": 0.030769, "snippet": "This action can be taken during the Placement phase or the Activation phase, but each player can only take it once per turn. The player uses the effect of the turn's Event card. They then place the disc of their color on the card to indicate that they've used it and thus won't be able to use it agai", "headingPath": "b) Use the turn's event · c) Gain money", "sharpsignalDocId": 975}, {"page": 5, "score": 0.030303, "snippet": "This action can only be taken during the Activation phase. The player chooses one of their workers in the market. They choose one of the cards adjacent to that worker and activate it: if it is a Character card, they call upon that character, if it is a Building card, they construct that building, if", "headingPath": "d) Activate a card", "sharpsignalDocId": 975}, {"page": 12, "score": 0.029851, "snippet": "Each time the player uses a Mine, they don't use a worker. End of the game: the player scores 1 point for each Spyrium crystal owned. Each time the player removes a worker to gain money, the player gains £2 more. End of the game: the player scores 1 point for each £2 owned. Once per turn , the playe", "headingPath": "Automation · Capitalization · Taylorism · Engineering · Crane · Commerce", "sharpsignalDocId": 975}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "Game Rules · Goal of the game · 1 board", "sharpsignalDocId": 975}, {"page": 4, "quote": null, "headingPath": "a) Place a worker", "sharpsignalDocId": 975}, {"page": 5, "quote": null, "headingPath": "d) Activate a card", "sharpsignalDocId": 975}, {"page": 5, "quote": null, "headingPath": "d) Activate a card", "sharpsignalDocId": 975}, {"page": 6, "quote": null, "headingPath": "End of the game", "sharpsignalDocId": 975}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 975 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 975 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 0.90620 of 2452 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 20, 2026 09:27 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 Spyrium — Rulebook (corpus doc 975) | Game overview · 1) Beginning of the turn · 2) Placement and Activation | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | End of the game | p.6 | 0.045541 (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 Spyrium — Rulebook (corpus doc 975) | Game Rules · Goal of the game · 1 board | 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 |
| #4 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | d) Activate a card · e) Use a building · f) Pass · End of the turn | p.6 | 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 |
| #5 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | a) Place a worker | 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 |
| #6 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | b) Use the turn's event · c) Gain money | p.5 | 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 Spyrium — Rulebook (corpus doc 975) | d) Activate a card | p.5 | 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 Spyrium — Rulebook (corpus doc 975) | Automation · Capitalization · Taylorism · Engineering · Crane · Commerce | p.12 | 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 18 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 Spyrium — Rulebook (corpus doc 975) | a) Place a worker | p.4 | #5 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | d) Activate a card | p.5 | #15 | 0.013333 (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 Spyrium — Rulebook (corpus doc 975) | Working-Class Neighborhood | p.11 | #17 | 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 |
| #4 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | End of the game | p.6 | #2 | 0.045541 (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 Spyrium — Rulebook (corpus doc 975) | d) Activate a card | p.5 | #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 |
| #6 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | End of the game | p.7 | #10 | 0.014286 (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 Spyrium — Rulebook (corpus doc 975) | Mine · Workshop · Factory | p.10 | #16 | 0.013158 (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 |
| #8 | RULEBOOK Spyrium — Rulebook (corpus doc 975) | Game Rules · Goal of the game · 1 board | p.3 | #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)) | 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 Spyrium — Rulebook (corpus doc 975) | Game Rules · Goal of the game · 1 board | p.3 | no quote on the wire |
| [2] | RULEBOOK Spyrium — Rulebook (corpus doc 975) | a) Place a worker | p.4 | no quote on the wire |
| [3] | RULEBOOK Spyrium — Rulebook (corpus doc 975) | d) Activate a card | p.5 | no quote on the wire |
| [4] | RULEBOOK Spyrium — Rulebook (corpus doc 975) | d) Activate a card | p.5 | no quote on the wire |
| [5] | RULEBOOK Spyrium — Rulebook (corpus doc 975) | End of the game | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 235 ms · first delta 2070 ms · total 5952 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 235 ms · ask 5712 ms · gateway work 5952 ms · total 5952 ms
- tokens in (the prompt the answerer read)
- 2823
- tokens out (what the answerer generated)
- 747
- tok/sec
- 196.4 tok/sec — 747 output tokens in 3.804 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 32s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, 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 905), 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.