You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Arkham Horrorbg-15987-en-1e
To prepare for a game of Arkham Horror, follow these steps: 1. Unfold the board and place it in the center of the playing area [1]. 2. Ensure there is ample space around the edges of the board to place the investigator sheets and card decks [1]. 3. Place various tokens and dice near the board as shown in the setup diagram [1]. 4. Place the terror track marker on the '0' space on the terror track [1]. 5. Place one Clue token on each location on the board that has a red diamond above it [1]. 6. Select one player at random to be the first player and give that player the first player marker [1]. 7. The first player shuffles the 16 investigator sheets and, without looking, randomly deals out one investigator sheet in front of each player [1]. (Alternatively, players may agree to choose investigators clockwise starting with the first player) [1]. 8. The first player shuffles the eight Ancient One sheets, selects one at random, and places it face up near the board [1]. 9. Separate the various investigator and Ancient One cards into their respective decks and place them near the board [1]. 10. Each player, beginning with the first player and continuing clockwise, receives the items listed on his investigator sheet in the 'Fixed Possessions' area [1]. 11. The players shuffle the Common Item, Unique Item, Spell, and Skill decks, then return them face down to their places next to the board [1]. 12. During setup, players may set their three skill sliders on any of the four stops on their three skill tracks [2].
🔧 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 274 ms · ask 12878 ms · total 13162 ms
- single-flight (PR-5)
- queued 0 ms · generation 13162 ms
- retrieval refs (raw)
- [{"page": 4, "score": 0.032787, "snippet": "It is passed to the left at the end of every turn. Each player takes his investigator sheet and marker, then gains Stamina and Sanity tokens equal to his maximum Stamina and Sanity, respectively. In addition, each player receives his character’s possessions. Finally, each player places his investiga", "headingPath": "", "sharpsignalDocId": 471}, {"page": 24, "score": 0.032258, "snippet": "The phases of the turn are as follows: Phase I: Upkeep Phase II: Movement Phase III: Arkham Encounters Phase IV: Other World Encounters Phase V: Mythos During Upkeep , players perform any upkeep actions that are required of them from turn to turn. This can include collecting their pay, making paymen", "headingPath": "Phase suMMaRy · skill checks", "sharpsignalDocId": 471}, {"page": 6, "score": 0.031746, "snippet": "During the Upkeep Phase, each player takes the following actions, in order. Some cards exhaust themselves when used, which means that they are turned face down for the remainder of the turn. At the start of the Upkeep Phase, each player refreshes those cards by turning them face up. Simply remember ", "headingPath": "Phase I: Upkeep · 1. Refresh Exhausted Cards · 2. Perform Upkeep Actions", "sharpsignalDocId": 471}, {"page": 5, "score": 0.03125, "snippet": "Finally, the first player draws the top card of the Mythos deck and resolves it as described in the Mythos Phase section of the rules. If a Rumor is drawn, discard it and draw again until you draw a Mythos card that isn't a Rumor . The Mythos card will indicate an unstable location where a gate and ", "headingPath": "1 4 . DRaw anD Resolve Mythos caRD · The Game Turn", "sharpsignalDocId": 471}, {"page": 6, "score": 0.030769, "snippet": "During Upkeep , you may adjust your character's skills in order to react to the investigator's situation. Focus represents your character's ability to split his attention between the different tasks at hand. It determines the total number of 'stops' you may adjust your skills each turn. Example 1: A", "headingPath": "aDjusting skills · 3. Adjust Skills · Phase II: Movement", "sharpsignalDocId": 471}, {"page": 17, "score": 0.030303, "snippet": "Any investigator who is lost in time and space is immediately moved to the Lost in Time and Space area of the board. The investigator is now delayed, and the player should place the investigator marker on its side. The investigator loses his next turn, remaining in the Lost in Time and Space area. T", "headingPath": "lost in tiMe anD sPace · DevouReD investigatoRs · blesseD anD cuRseD investigatoRs · Closing and Sealing Gates", "sharpsignalDocId": 471}, {"page": 2, "score": 0.029851, "snippet": "Enclosed in your Arkham Horror box, you will find the following game components: 1 Rule Book (this book) 1 Game Board 1 First Player Marker 5 Dice 16 Investigator Sheets 16 Investigator Markers 16 Plastic Investigator Stands 196 Investigator Status Tokens 56 Money Tokens 34 Sanity Tokens (10 'threes", "headingPath": "Game Components and Preparation · Component Overview · Game Board · FiRst PlayeR MaRkeR · Dice", "sharpsignalDocId": 471}, {"page": 22, "score": 0.029412, "snippet": "Many location and Other World encounters indicate that a monster appears. To resolve such an encounter, the player must draw a monster from the monster cup and resolve the encounter as normal (i.e., the investigator may attempt to evade the monster or fight it). No matter how the encounter is resolv", "headingPath": "MonsteRs in encounteRs", "sharpsignalDocId": 471}]
- citations (raw)
- [{"page": 5, "quote": null, "headingPath": "Game Setup · 1. PRePaRe Playing aRea · 2. Place initial clues · 3. choose FiRst PlayeR · 4. DeteRMine investigatoRs · 5. Reveal ancient one · …", "sharpsignalDocId": 471}, {"page": 6, "quote": null, "headingPath": "aDjusting skills · 3. Adjust Skills · Phase II: Movement", "sharpsignalDocId": 471}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 471 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 471 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 05:51
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 Arkham Horror — Rulebook (corpus doc 471) | p.4 | 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 Arkham Horror — Rulebook (corpus doc 471) | Phase suMMaRy · skill checks | p.24 | 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 Arkham Horror — Rulebook (corpus doc 471) | Phase I: Upkeep · 1. Refresh Exhausted Cards · 2. Perform Upkeep Actions | 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 |
| #4 | RULEBOOK Arkham Horror — Rulebook (corpus doc 471) | 1 4 . DRaw anD Resolve Mythos caRD · The Game Turn | p.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)) | 300 |
| #5 | RULEBOOK Arkham Horror — Rulebook (corpus doc 471) | aDjusting skills · 3. Adjust Skills · Phase II: Movement | 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 |
| #6 | RULEBOOK Arkham Horror — Rulebook (corpus doc 471) | lost in tiMe anD sPace · DevouReD investigatoRs · blesseD anD cuRseD investigatoRs · Closing and Sealing Gates | p.17 | 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 Arkham Horror — Rulebook (corpus doc 471) | Game Components and Preparation · Component Overview · Game Board · FiRst PlayeR MaRkeR · Dice | p.2 | 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 Arkham Horror — Rulebook (corpus doc 471) | MonsteRs in encounteRs | p.22 | 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 Arkham Horror — Rulebook (corpus doc 471) | Game Setup · 1. PRePaRe Playing aRea · 2. Place initial clues · 3. choose FiRst PlayeR · 4. DeteRMine investigatoRs · 5. Reveal ancient one · … | p.5 | no quote on the wire |
| [2] | RULEBOOK Arkham Horror — Rulebook (corpus doc 471) | aDjusting skills · 3. Adjust Skills · Phase II: Movement | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 274 ms · first delta 10504 ms · total 13162 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 274 ms · ask 12878 ms · gateway work 13162 ms · total 13162 ms
- tokens in (the prompt the answerer read)
- 4012
- tokens out (what the answerer generated)
- 353
- tok/sec
- 135.7 tok/sec — 353 output tokens in 2.601 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 0s 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 401), 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.