You asked
Before anyone takes a turn, how is everything laid out on the table?
Answered counted as answeredAsked with: Knarrbg-379629-en-1e
1. Place the board in the center of the table [1]. 2. Form a deck with the Trading Lands cards and place it face down to the side of the board, then reveal the first 3 cards on the designated spaces [1]. 3. Shuffle and place the Lands of Influence cards in the same way as the Trading Lands cards [1]. 4. Prepare the Viking cards based on the number of players by removing specific cards (for 3 players, remove cards marked 4; for 2 players, remove cards marked 3 and 4), shuffle them, form a deck, place it face down to the side of the board, and reveal the first 5 cards on the designated spaces [1]. 5. Each player takes a Ship sheet, 3 Silver Bracelet tokens, and 3 Recruit tokens [1]. 6. Players decide together whether to play with the normal or advanced side of the ships and place them accordingly [1]. 7. Each player takes 2 Viking cards of different colors from the deck and places them face up in front of them in their Crew Zone [1]. 8. Slide 1 Recruit token and 1 Silver Bracelet token onto the designated spaces on each side of the boat [1]. 9. Take the 2 wooden tokens corresponding to the color of each player's ship and place the round one on the starting space of the Score Track and the square one on that of the Reputation Track [2]. 10. Each player draws 3 Viking cards to make up their hand [2]. 11. One player takes the colored Destiny tokens of the ships in play into their hand and draws 1 at random to choose the first player [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 260 ms · ask 5050 ms · total 5319 ms
- single-flight (PR-5)
- queued 0 ms · generation 5319 ms
- retrieval refs (raw)
- [{"page": 9, "score": 0.032787, "snippet": "Once per turn, before or after their action , a player can spend their bracelets to buy assets from their Destination cards. These assets are represented at the top of their ship and at the bottom of the destinations. The player chooses to spend 1, 2, or 3 silver bracelets by removing the correspond", "headingPath": "TRADING", "sharpsignalDocId": 468}, {"page": 5, "score": 0.032258, "snippet": "Crew Zone Take the 2 wooden tokens corresponding to the color of each player’s ship. Place the round one on the starting space of the Score Track and the square one on that of the Reputation Track. Each player draws 3 Viking cards to make up their hand. One of the players takes the colored Destiny t", "headingPath": "", "sharpsignalDocId": 468}, {"page": 6, "score": 0.031746, "snippet": "The players take turns going clockwise. On their turn, each player performs the following steps in order: Reputation Action: Recruit or Explore In addition, once per turn at the beginning or end of their action step, the player may Trade using their silver bracelets. The player moves their Scoring m", "headingPath": "PLAYING THE GAME · REPUTATION", "sharpsignalDocId": 468}, {"page": 8, "score": 0.03125, "snippet": "EXPLORE: The player chooses a Destination card from the 6 face-up cards near the board and pays its exploration cost , shown at the top left of the card. They must discard the vikings of their choice from those in their Crew Zone, matching the required number and colors. The symbols mean any 4 cards", "headingPath": "REPUTATION · Discover a new land · At any time", "sharpsignalDocId": 468}, {"page": 10, "score": 0.030769, "snippet": "The end of the game is triggered when a player reaches 40 Victory Points or more on the Score Track. The current round is finished, ending with the player to the right of the one who took the first turn of the game. The person with the most points on the Score Track wins! In case of a tie, the one w", "headingPath": "END OF THE GAME · ASSETS · PLAYING WITH ARTIFACTS", "sharpsignalDocId": 468}, {"page": 7, "score": 0.030303, "snippet": "Next, the player adds to their hand the Viking card on the board that is in the space matching the color of the viking they just Recruited. For example, if a yellow viking was placed, the Viking card on the yellow space of the board is taken. Important: A player may spend 1 recruit (by removing a Re", "headingPath": "REPUTATION", "sharpsignalDocId": 468}, {"page": 2, "score": 0.029851, "snippet": "KNARR_board.indd 1 KNARR_ KNARR_cards.indd 61 s.indd 61 KNARR_ KNARR_cards.indd 76 s.indd 76 KNARR_cards.indd 82 KNARR_ s.indd 82 KNARR_cards.indd 80 KNARR_ s.indd 80 05/05/2023 10:33:59 05/05/ 0:33:59 05/05/2023 10:33:55 05/05/ 0:33:55 4 Ship sheets (white, beige, brown, black) Normal side 20 Tradi", "headingPath": "1 board · 35 Destination cards", "sharpsignalDocId": 468}, {"page": 4, "score": 0.029412, "snippet": "Place the board Shuffle the Recruit vikings ( víkingar ) to form your band ( félag ). Make your fortune by sending them to discover new territories on your ship ( knarr ). Establish trade routes and, in some cases, settle down for good. At the same time, increase your reputation and make your name r", "headingPath": "COMPONENTS · GAME OBJECTIVE · SETUP", "sharpsignalDocId": 468}]
- citations (raw)
- [{"page": 4, "quote": null, "headingPath": "COMPONENTS · GAME OBJECTIVE · SETUP", "sharpsignalDocId": 468}, {"page": 5, "quote": null, "headingPath": "", "sharpsignalDocId": 468}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 468 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 468 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 05:50
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 Knarr — Rulebook (corpus doc 468) | TRADING | p.9 | 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 Knarr — Rulebook (corpus doc 468) | p.5 | 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 Knarr — Rulebook (corpus doc 468) | PLAYING THE GAME · REPUTATION | 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 Knarr — Rulebook (corpus doc 468) | REPUTATION · Discover a new land · At any time | p.8 | 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 Knarr — Rulebook (corpus doc 468) | END OF THE GAME · ASSETS · PLAYING WITH ARTIFACTS | p.10 | 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 Knarr — Rulebook (corpus doc 468) | REPUTATION | p.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)) | 300 |
| #7 | RULEBOOK Knarr — Rulebook (corpus doc 468) | 1 board · 35 Destination cards | 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 Knarr — Rulebook (corpus doc 468) | COMPONENTS · GAME OBJECTIVE · SETUP | p.4 | 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 Knarr — Rulebook (corpus doc 468) | COMPONENTS · GAME OBJECTIVE · SETUP | p.4 | no quote on the wire |
| [2] | RULEBOOK Knarr — Rulebook (corpus doc 468) | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 260 ms · first delta 2855 ms · total 5319 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 260 ms · ask 5050 ms · gateway work 5319 ms · total 5319 ms
- tokens in (the prompt the answerer read)
- 2550
- tokens out (what the answerer generated)
- 355
- tok/sec
- 147.3 tok/sec — 355 output tokens in 2.410 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 57s 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 398), 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.