You asked
What does each player take, and what goes in the middle, before we begin?
Answered counted as answeredAsked with: Fantasy Realmsbg-223040-en-1e
1. All players receive seven cards [1][2]. 2. All cards in the discard area should be spread out so that they are visible to all [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 325 ms · ask 2870 ms · total 3205 ms
- single-flight (PR-5)
- queued 0 ms · generation 3205 ms
- retrieval refs (raw)
- [{"page": 2, "score": 0.032787, "snippet": "Draw pile Setup: Deal every player seven cards. Choose a starting player randomly and play goes clockwise. Turns: During each player's turn, he or she has a choice of drawing the top card from the deck or taking any one face-up card from the discard area. The player who goes fi rst must draw a card ", "headingPath": "OVERVIEW · GAME PLAY · SCORING HANDS", "sharpsignalDocId": 335}, {"page": 6, "score": 0.032258, "snippet": "Setup: Neither player starts with any cards. On each turn, a player has the choice of taking one face-up card from the discard area, or taking two cards from the deck and discarding one. This continues until both players have seven cards. Turns: After a player has seven cards, he or she continues tu", "headingPath": "1. Two-player Realms · 2. Chaos Realms for 3-7 Players · Q: What happens if two cards contradict each other?", "sharpsignalDocId": 335}, {"page": 5, "score": 0.031746, "snippet": "Card One Card Three Card Five Card Two Card Four Card Six * The scoring sheet includes Card 8 and Additional Points sections to accommodate the Necromancer and exciting new cards coming in future expansions. Note that you have to use the Book of Changes to change any of these cards into a Wizard ( a", "headingPath": "This is one of the highest scoring hands possible:", "sharpsignalDocId": 335}, {"page": 4, "score": 0.03125, "snippet": "Card One When scoring, the player announces that the Mirage takes on the name and suit of the Rainstorm . Note that the actual Rainstorm would put out the Wildfi re - but the ersatz Rainstorm doesn't give this penalty. The penalty for the Great Flood would normally blank the Wildfi re . However, the", "headingPath": "SCORING EXAMPLES · Card Four", "sharpsignalDocId": 335}, {"page": 3, "score": 0.030769, "snippet": "If a card receives a bonus WITH a certain other card or type of card, then it may only receive that bonus once. EXAMPLE: You have the Magic Wand (Bonus: +25 with any one Wizard) and two Wizards. You only get the +25 bonus once. A card that receives a bonus or penalty FOR EACH of a particular kind of", "headingPath": "WITH · FOR EACH", "sharpsignalDocId": 335}, {"page": 1, "score": 0.030303, "snippet": "You are the ultimate ruler of a far-away land. Your goal is to build up the mightiest realm in the world. You might build up a massive army to sweep all before you, but that is not the only path to victory. Perhaps your kingdom will take the form 53 Cards (ten suits and three wild cards) 1 Rulebook ", "headingPath": "Components · OVERVIEW", "sharpsignalDocId": 335}, {"page": 8, "score": 0.029851, "snippet": "| Suit | Card Name: | Suit | Card Name: | | Army | Dwarvish Infantry Elven Archers Knights Light Cavalry Rangers | Land | Bell Tower Cavern Earth Elemental Forest Mountain | | Artifact | Book of Changes Gem of Order Protection Rune Shield of Keth World Tree | Leader | Empress King Princess Queen War", "headingPath": "Q: Can you explain the Shapeshifter and Mirage?", "sharpsignalDocId": 335}, {"page": 7, "score": 0.029412, "snippet": "EXAMPLE: You have a Blizzard (blanks Floods ), a Great Flood (blanks Flames and Lands ), a Wildfi re (blanks Lands ), and Cavern (clears penalties on Weather ). The Cavern clears the penalty from the Blizzard fi rst. Since the penalty is cleared, the Great Flood is unaffected by the Blizzard, so it ", "headingPath": "Q: What happens if two cards contradict each other? · Q: What happens if the Doppelgänger copies the Basilisk? · Q: How does the Book of Changes work? · Q: Do the Rangers protect my armies against Wildfi re? · Q: Can you explain the Shapeshifter and Mirage?", "sharpsignalDocId": 335}]
- citations (raw)
- [{"page": 6, "quote": null, "headingPath": "1. Two-player Realms · 2. Chaos Realms for 3-7 Players · Q: What happens if two cards contradict each other?", "sharpsignalDocId": 335}, {"page": 2, "quote": null, "headingPath": "OVERVIEW · GAME PLAY · SCORING HANDS", "sharpsignalDocId": 335}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 335 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 335 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 Fantasy Realms — Rulebook (corpus doc 335) | OVERVIEW · GAME PLAY · SCORING HANDS | p.2 | 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 Fantasy Realms — Rulebook (corpus doc 335) | 1. Two-player Realms · 2. Chaos Realms for 3-7 Players · Q: What happens if two cards contradict each other? | p.6 | 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 Fantasy Realms — Rulebook (corpus doc 335) | This is one of the highest scoring hands possible: | p.5 | 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 Fantasy Realms — Rulebook (corpus doc 335) | SCORING EXAMPLES · Card Four | p.4 | 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 Fantasy Realms — Rulebook (corpus doc 335) | WITH · FOR EACH | p.3 | 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 Fantasy Realms — Rulebook (corpus doc 335) | Components · OVERVIEW | p.1 | 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 Fantasy Realms — Rulebook (corpus doc 335) | Q: Can you explain the Shapeshifter and Mirage? | p.8 | 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 Fantasy Realms — Rulebook (corpus doc 335) | Q: What happens if two cards contradict each other? · Q: What happens if the Doppelgänger copies the Basilisk? · Q: How does the Book of Changes work? · Q: Do the Rangers protect my armies against Wildfi re? · Q: Can you explain the Shapeshifter and Mirage? | p.7 | 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 Fantasy Realms — Rulebook (corpus doc 335) | 1. Two-player Realms · 2. Chaos Realms for 3-7 Players · Q: What happens if two cards contradict each other? | p.6 | no quote on the wire |
| [2] | RULEBOOK Fantasy Realms — Rulebook (corpus doc 335) | OVERVIEW · GAME PLAY · SCORING HANDS | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 325 ms · first delta 2890 ms · total 3205 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 325 ms · ask 2870 ms · gateway work 3205 ms · total 3205 ms
- tokens in (the prompt the answerer read)
- 2611
- tokens out (what the answerer generated)
- 37
- tok/sec
- 136.0 tok/sec — 37 output tokens in 0.272 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 22s 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 263), 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.