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 Just One — Rulebook (corpus doc 179)	Setup	p.1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK Just One — Rulebook (corpus doc 179)		p.1	0.048387 (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 Just One — Rulebook (corpus doc 179)	End of the round · End of the Game · Variant for 3 and 4 players · CREDITS	p.4	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 Just One — Rulebook (corpus doc 179)	Gameplay · Select the Mystery Word · Write clues · Invalid clues	p.2	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 Just One — Rulebook (corpus doc 179)	Compare clues · Identical clues · Guess	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

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 Just One — Rulebook (corpus doc 179)		p.1	no quote on the wire

generation — timing and the path taken

timing split

retrieval 267 ms · first delta 2099 ms · total 2185167 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)

full breakdown

queued 2182448 ms · retrieval 267 ms · ask 2446 ms · gateway work 2719 ms · total 2185167 ms

tokens in (the prompt the answerer read)

1598

tokens out (what the answerer generated)

77

tok/sec

137.0 tok/sec — 77 output tokens in 0.562 s of generation

live seat (read from the running child)

answering — gemma4:26b think:false · num_ctx 32768 (live-verified 22s 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

NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game

pattern that matched

SETUP — "setup" / "set up"

matched words (in the normalized question)

set up

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 97), 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.