You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Awkward Guests: The Walton Casebg-188866-en-1e
1. Give every player a tracking sheet and a screen [1]. 2. Each player chooses a case solving token [1]. 3. Place the offer tokens and inquiry tokens in the center of the table within everyone’s reach [1]. 4. Choose a case from the end of the rulebook or from the AWKWARD GUESTS: The Walton Case App, and make a note of the case reference number [1]. 5. Separate the 70 cards specified by the case according to the unique card number on their backs (without looking at the card fronts) to create the game deck, then return any remaining cards to the box [1]. 6. Shuffle the game deck and deal 6 cards to each player [1]. 7. Place the remaining cards in the center of the table within everyone’s reach [1]. 8. Place the discard drawer next to the deck for discarded cards with the “Classified Information” card on top [1]. 9. Leave space for a revealed card pile, which is empty at the beginning of the game [1]. 10. The player considered by the host as the most awkward guest becomes the starting player of the first round; place the starting player standee in front of their player screen [1].
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 320 ms · ask 8720 ms · total 9055 ms
- single-flight (PR-5)
- queued 0 ms · generation 9055 ms
- retrieval refs (raw)
- [{"page": 10, "score": 0.032787, "snippet": "All players still in the game must discard cards from their hands until their hands are each down to 3 cards. Discarded cards are placed FACE DOWN in the discard pile drawer, under the 'Classified Information' card. The starting player then passes the Mr. Walton standee to the player on their right.", "headingPath": "Discard Phase", "sharpsignalDocId": 503}, {"page": 9, "score": 0.032258, "snippet": "AWKWARD GUESTS: The Walton Case is played over several rounds, with each player taking a turn during the round and continuing on in an anticlockwise fashion. Each round starts with the starting player of that round. Each player's turn is divided in 3 phases: Inquiry Phase Offer Phase Exchange Phase ", "headingPath": "Turn Order and Overview · Inquiry Phase · OfferPhase", "sharpsignalDocId": 503}, {"page": 10, "score": 0.031746, "snippet": "All players take their case solving token. They must decide if they want to place the token on the table showing its bright side to solve the mystery or the dark side to continue with the investigation. Once they have made up their mind, they will secretly place the token on the table, covering the ", "headingPath": "Solution Phase", "sharpsignalDocId": 503}, {"page": 9, "score": 0.03125, "snippet": "Once all non-active players have made their offers, the active player decides with whom to exchange cards. They MAY EXCHANGE CARDS WITH AS MANY PLAYERS AS THEY PLEASE. The active player must give each chosen player cards from their hand (regardless of their references) that sum up to a total amount ", "headingPath": "Exchange Phase", "sharpsignalDocId": 503}, {"page": 8, "score": 0.030769, "snippet": "8 Figure 4: Starting player standee. Figure 7: “Classified Information” card. Figure 6: Offer tokens. Game Objective Game Setup Figure 9: Discard pile drawer and its assembly instructions. Investigate clues and exchange information with your opponents to be the first player to solve the mystery of W", "headingPath": "", "sharpsignalDocId": 503}, {"page": 13, "score": 0.030303, "snippet": "AWKWARD GUESTS: The Walton Case is a game of logic and association. If you use your deductive skills, you will be able to extract more information from the cards as a whole than if you focus on them individually. The police, the coroner, the housekeeper and the rest of the Walton Mansion service sta", "headingPath": "Advice", "sharpsignalDocId": 503}, {"page": 11, "score": 0.029851, "snippet": "Let's take a close look at the cards you'll find in AWKWARD GUESTS: The Walton Case and how to jot down their information on your tracking sheet . These cards provide information regarding the suspects' alibis. The room where the MURDERER claims to have been at the time of the murder is the room the", "headingPath": "Game card types and how to use the tracking sheet · Alibi cards · Motive cards", "sharpsignalDocId": 503}, {"page": 10, "score": 0.029412, "snippet": "A 2 player game of AWKWARD GUESTS: The Walton Case is played the same way as the 3-8 player game with the following changes: When making inquiries, you must request information regarding 4 different references instead of 2. Possible references are the same: Mr. Walton's guests: Angelica Albinson , C", "headingPath": "Two-player game variant", "sharpsignalDocId": 503}]
- citations (raw)
- [{"page": 8, "quote": null, "headingPath": "", "sharpsignalDocId": 503}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 503 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 503 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)
- debug row retained until
- Nov 7, 2026 05:59
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 Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Discard Phase | p.10 | 0.032787 (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 Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Turn Order and Overview · Inquiry Phase · OfferPhase | p.9 | 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 |
| #3 | RULEBOOK Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Solution Phase | p.10 | 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 Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Exchange Phase | p.9 | 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 Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | p.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)) | 300 | |
| #6 | RULEBOOK Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Advice | p.13 | 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 |
| #7 | RULEBOOK Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Game card types and how to use the tracking sheet · Alibi cards · Motive cards | p.11 | 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 Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | Two-player game variant | p.10 | 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 |
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 Awkward Guests: The Walton Case — Rulebook (corpus doc 503) | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 320 ms · first delta 7050 ms · total 9055 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 320 ms · ask 8720 ms · gateway work 9055 ms · total 9055 ms
- tokens in (the prompt the answerer read)
- 3029
- tokens out (what the answerer generated)
- 267
- tok/sec
- 136.6 tok/sec — 267 output tokens in 1.954 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 54s 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
- 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 434), 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.