You asked
What does each player take, and what goes in the middle, before we begin?
Answered counted as answeredAsked with: Near and Farbg-195421-en-1e
Each player takes their 5 basic artifact cards (keeping the 2 advanced artifacts separate) [1]. From these 5, each player selects 1 card for their hand [1]. After selecting the card, players pass their 4 remaining basic artifact cards to the player on their left, who then selects 1 card and passes the stack again, repeating this process until all cards have been selected [1]. At this time, each player must discard 1 of their 2 advanced artifact cards (but may discard both) [1]. At the start of the game, the four chief cards are placed near the town board [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 285 ms · ask 10648 ms · total 10944 ms
- single-flight (PR-5)
- queued 0 ms · generation 10944 ms
- retrieval refs (raw)
- [{"page": 37, "score": 0.032787, "snippet": "You've played some game sessions with the same character and your friend comes and wants to play with a new character. What do you do? Do you have to start over? In most cases, no. In Campaign Mode , you can start a new character late in the campaign with extra experience. Give the new player a char", "headingPath": "Starting a character mid-campaign", "sharpsignalDocId": 361}, {"page": 38, "score": 0.032258, "snippet": "Use this variant if you want to have more quests on the map and more story reading. This increases the game length. During setup, place 4 quest tokens per player on the map. If playing Campaign Mode , characters will gain experience at a faster rate, so you will have to skip three maps of your choic", "headingPath": "Starting a character mid-campaign", "sharpsignalDocId": 361}, {"page": 19, "score": 0.031746, "snippet": "The two arrows in the adventure symbol (picture on the journal on the player boards) are meant as a reminder of this. Each pack bird a player owns gives +1 movement. Each active party member with an arrow symbol also gives +1 movement. A player's total movement represents the maximum number of space", "headingPath": "Each player starts out with a base movement of 2.", "sharpsignalDocId": 361}, {"page": 27, "score": 0.03125, "snippet": "At the start of the game, the four chief cards are placed near the town board. There is one chief for each faction: Outlaws (green), Nomads (yellow), Mystics (blue), and Lizardfolk (red). Each chief is worth 5 journey points at the end of the game to the player that owns the card. The first player t", "headingPath": "Chiefs", "sharpsignalDocId": 361}, {"page": 14, "score": 0.030769, "snippet": "Each player searches for the legendary Last Ruin, a ruined city said to contain the greatest desire of the heart. Players must journey through forgotten, dangerous lands, recruiting the help of four factions: Outlaws (green banner), Mystics (blue banner), Lizards (red banner), and Nomads (yellow ban", "headingPath": "Goal of the Game · Overview · Hearts", "sharpsignalDocId": 361}, {"page": 23, "score": 0.030303, "snippet": "Sometimes a regular quest will trigger a side quest. The side quest will be listed among the rewards (E.g.: Q2 ). The player should mark the side quest number in one of the circles on their character card labeled 'side quest.' The next time the player attempts a quest, the player to their left will ", "headingPath": "Side Quests · Character Quests", "sharpsignalDocId": 361}, {"page": 13, "score": 0.029851, "snippet": "After completing a game and before starting the first turn in the next game, players may purchase talents (permanent abilities used over multiple games in a campaign) by spending experience points. (In Story Mode, players start at 1 experience and gain 1 experience for each completed character quest", "headingPath": "Character Talents", "sharpsignalDocId": 361}, {"page": 9, "score": 0.029412, "snippet": "If this is your first time through the campaign: If a space has a name (on the map, labelled just below the space), make sure that it is one of the spaces that is chosen to have a quest token (as long as it has an open book icon). Use the heart marker to keep track of hearts. Place 14 tent markers s", "headingPath": "Campaign Mode · Character Mode, Campaign Mode", "sharpsignalDocId": 361}]
- citations (raw)
- [{"page": 12, "quote": null, "headingPath": "Drafting Artifact Cards", "sharpsignalDocId": 361}, {"page": 27, "quote": null, "headingPath": "Chiefs", "sharpsignalDocId": 361}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 361 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 361 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 6, 2026 18:20
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 Near and Far — Rulebook (corpus doc 361) | Starting a character mid-campaign | p.37 | 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 Near and Far — Rulebook (corpus doc 361) | Starting a character mid-campaign | p.38 | 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 Near and Far — Rulebook (corpus doc 361) | Each player starts out with a base movement of 2. | p.19 | 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 Near and Far — Rulebook (corpus doc 361) | Chiefs | p.27 | 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 Near and Far — Rulebook (corpus doc 361) | Goal of the Game · Overview · Hearts | p.14 | 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 Near and Far — Rulebook (corpus doc 361) | Side Quests · Character Quests | p.23 | 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 Near and Far — Rulebook (corpus doc 361) | Character Talents | p.13 | 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 Near and Far — Rulebook (corpus doc 361) | Campaign Mode · Character Mode, Campaign Mode | p.9 | 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 Near and Far — Rulebook (corpus doc 361) | Drafting Artifact Cards | p.12 | no quote on the wire |
| [2] | RULEBOOK Near and Far — Rulebook (corpus doc 361) | Chiefs | p.27 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 285 ms · first delta 9926 ms · total 10944 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 285 ms · ask 10648 ms · gateway work 10944 ms · total 10944 ms
- tokens in (the prompt the answerer read)
- 3334
- tokens out (what the answerer generated)
- 131
- tok/sec
- 136.3 tok/sec — 131 output tokens in 0.961 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s 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
- BEGIN — "begin" / "beginning"
- matched words (in the normalized question)
-
begin
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 290), 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.