You asked
How do I setup the game?
Answered counted as answeredAsked with: Watson & Holmesbg-182694-en-1e
That settles it — whose turn was it?
🔧 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 172 ms · ask 6835 ms · total 7010 ms
- single-flight (PR-5)
- queued 0 ms · generation 7010 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.048412, "snippet": "8 IMPORTANT : The game components are limited. If, during a game, a player would gain a token and there is no token of that type in the Supply, they simply do not gain the token. No player can have more than 1 Police Token, 1 Call Off Token, and 1 Lockpick Token at any one time. i.e. the most each p", "headingPath": "CASE BOOKLETS · SETUP", "sharpsignalDocId": 1297}, {"page": 4, "score": 0.048139, "snippet": "6 6 Each case comes with its own corresponding booklet which introduces the circumstances of the incident, sets the questions that the players have to solve to win the game, and the solution provided by Sherlock Holmes. The booklet also contains any additional rules that are unique to that particula", "headingPath": "CASE BOOKLETS", "sharpsignalDocId": 1297}, {"page": 5, "score": 0.046751, "snippet": "In games where there are more than 5 players, only the fi rst 5 players are given Police Tokens (the Start Player and the 4 players continuing in a clockwise direction). The sixth and seventh players, if any, start the game with a Call Off Token each. Lastly, and unless indicated differently in the ", "headingPath": "6- AND 7-PLAYER GAMES · GAMES WITH FEWER THAN 4 PLAYERS · PLAYING THE GAME · 1. VISITING PHASE", "sharpsignalDocId": 1297}, {"page": 4, "score": 0.04598, "snippet": "CALL OFF TOKENS Call Off Tokens are obtained at Scotland Yard or any other location marked with this symbol: These represent a police order calling off the surveillance at that location. i.e. they are used to remove Police Tokens. The Call Off Token removes the Police Token perma- nently and for all", "headingPath": "", "sharpsignalDocId": 1297}, {"page": 6, "score": 0.045956, "snippet": "If a player decides to go to 221B Baker Street, they must write their answers to all of the questions set by the Case Booklet on their paper. They should answer the questions as fully as possible. Once written, the player checks if their answers are correct by comparing them with the answers on the ", "headingPath": "SOLVING THE CASE · WATSON AND HOLMES CARDS", "sharpsignalDocId": 1297}, {"page": 4, "score": 0.045688, "snippet": "• WATSON & HOLMES • • RULEBOOK •6 7• WATSON & HOLMES •6 7 CASE BOOKLETS Each case comes with its own corresponding booklet which introduces the circumstances of the incident, sets the questions that the players have to solve to win the game, and the solution provided by Sherlock Holmes. The booklet ", "headingPath": "", "sharpsignalDocId": 1297}, {"page": 7, "score": 0.044337, "snippet": "During the Visiting Phase, on a player's turn, they can pay 4 Carriages to take the Watson Card and place it in front of them. Only one player can do this each round. At the start of the Investigation Phase of this round, the holder of this card may choose the Location Card of another player which i", "headingPath": "DR WATSON · EXPERT VERSION (without the Watson Card): · SHERLOCK HOLMES", "sharpsignalDocId": 1297}, {"page": 6, "score": 0.030769, "snippet": "If a player does not have enough Carriage Tokens to compete for a particular Location Card, they must visit a different location. During this stage, turns continue from player to player until all pawns have been placed on one of the Location Cards. At this moment, the last player who placed his or h", "headingPath": "1. VISITING PHASE · LOCATIONS WITH POLICE TOKENS · EXAMPLE:", "sharpsignalDocId": 1297}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "CASE BOOKLETS", "sharpsignalDocId": 1297}, {"page": 5, "quote": null, "headingPath": "CASE BOOKLETS · SETUP", "sharpsignalDocId": 1297}, {"page": 5, "quote": null, "headingPath": "6- AND 7-PLAYER GAMES · GAMES WITH FEWER THAN 4 PLAYERS · PLAYING THE GAME · 1. VISITING PHASE", "sharpsignalDocId": 1297}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1297 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1297 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 0.92289 of 1647 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 23, 2026 19:08 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 Watson & Holmes — Rulebook (corpus doc 1297) | CASE BOOKLETS · SETUP | p.5 | 0.048412 (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 Watson & Holmes — Rulebook (corpus doc 1297) | CASE BOOKLETS | p.4 | 0.048139 (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 Watson & Holmes — Rulebook (corpus doc 1297) | 6- AND 7-PLAYER GAMES · GAMES WITH FEWER THAN 4 PLAYERS · PLAYING THE GAME · 1. VISITING PHASE | p.5 | 0.046751 (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 Watson & Holmes — Rulebook (corpus doc 1297) | p.4 | 0.04598 (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 Watson & Holmes — Rulebook (corpus doc 1297) | SOLVING THE CASE · WATSON AND HOLMES CARDS | p.6 | 0.045956 (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 Watson & Holmes — Rulebook (corpus doc 1297) | p.4 | 0.045688 (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 Watson & Holmes — Rulebook (corpus doc 1297) | DR WATSON · EXPERT VERSION (without the Watson Card): · SHERLOCK HOLMES | p.7 | 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 |
| #8 | RULEBOOK Watson & Holmes — Rulebook (corpus doc 1297) | 1. VISITING PHASE · LOCATIONS WITH POLICE TOKENS · EXAMPLE: | p.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)) | 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 20 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 Watson & Holmes — Rulebook (corpus doc 1297) | CASE BOOKLETS | p.4 | #2 | 0.048139 (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 Watson & Holmes — Rulebook (corpus doc 1297) | p.4 | #6 | 0.045688 (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 Watson & Holmes — Rulebook (corpus doc 1297) | CLARIFICATIONS & RECOMMENDATIONS · AUTHOR'S NOTES | p.7 | #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 |
| #4 | RULEBOOK Watson & Holmes — Rulebook (corpus doc 1297) | SOLVING THE CASE · WATSON AND HOLMES CARDS | p.6 | #5 | 0.045956 (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 Watson & Holmes — Rulebook (corpus doc 1297) | END OF GAME · CHARACTER CARDS · IRENE ADLER · WIGGINS (only used in games with 4 or more players) | p.7 | #10 | 0.029644 (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 Watson & Holmes — Rulebook (corpus doc 1297) | 1. VISITING PHASE · LOCATIONS WITH POLICE TOKENS · EXAMPLE: | p.6 | #8 | 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 |
| #7 | RULEBOOK Watson & Holmes — Rulebook (corpus doc 1297) | 6- AND 7-PLAYER GAMES · GAMES WITH FEWER THAN 4 PLAYERS · PLAYING THE GAME · 1. VISITING PHASE | p.5 | #3 | 0.046751 (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 Watson & Holmes — Rulebook (corpus doc 1297) | CASE BOOKLETS · SETUP | p.5 | #1 | 0.048412 (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 Watson & Holmes — Rulebook (corpus doc 1297) | CASE BOOKLETS | p.4 | no quote on the wire |
| [2] | RULEBOOK Watson & Holmes — Rulebook (corpus doc 1297) | CASE BOOKLETS · SETUP | p.5 | no quote on the wire |
| [3] | RULEBOOK Watson & Holmes — Rulebook (corpus doc 1297) | 6- AND 7-PLAYER GAMES · GAMES WITH FEWER THAN 4 PLAYERS · PLAYING THE GAME · 1. VISITING PHASE | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 172 ms · first delta 3351 ms · total 7010 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 172 ms · ask 6835 ms · gateway work 7010 ms · total 7010 ms
- tokens in (the prompt the answerer read)
- 4005
- tokens out (what the answerer generated)
- 475
- tok/sec
- 132.7 tok/sec — 475 output tokens in 3.579 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, 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
- 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)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 1227), 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.