You asked
How do I play
Answered counted as answeredAsked with: Heroes of Land, Air & Seabg-198830-en-1e
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live,vps
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 72 ms · ask 6530 ms · total 6605 ms
- single-flight (PR-5)
- queued 0 ms · generation 6605 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 17, "score": 0.045928, "snippet": "You may Follow a successful Solo Action as if it were a normal action ( except for Attack ). HOWEVER, if the Enemy's Action has failed, it may not be Followed. The Enemy does not Follow your actions. In this epic variant, players gather in groups of 2 ( or 3 with the Order & Chaos Expansion ) in a w", "headingPath": "Following a Solo Action Card · Team Play Variant · Components and Setup · Player Seat Positions · Recruit", "sharpsignalDocId": 847}, {"page": 6, "score": 0.045724, "snippet": "After one player achieves any one of the 4 “X-Objectives,” then players finish the current round as normal and play one additional full round which will be the final round (see End of Game, pg.13). These \"X-Objectives\" are: ✴ eXplore – All Land Exploration Tokens in the game have been revealed. ✴ eX", "headingPath": "", "sharpsignalDocId": 847}, {"page": 6, "score": 0.044835, "snippet": "Each round has 3 Phases , performed in order: Action Selection - Starting with the first player ( with the First Player Token ), and then going clockwise in turn, each player selects and performs one action. The player places one of their Action Tokens onto an open Action Slot at the top of their Ca", "headingPath": "Playing a Round", "sharpsignalDocId": 847}, {"page": 14, "score": 0.044283, "snippet": "Solo Play Variant In this variant, you go head-to-head with an A.I.-controlled Faction, called the Enemy. The Enemy controls 3 armies, each led by one of its powerful Heroes. These Heroes each have powerful abilities, and will offer you a serious challenge! Components and Setup Changes 8 Solo Action", "headingPath": "", "sharpsignalDocId": 847}, {"page": 30, "score": 0.043301, "snippet": "✴ eXplore - All Land Exploration Tokens in the game have been revealed. ✴ eXpand - All of a player's Serfs and Warriors are in play . ✴ eXploit - All 3 of a player's Towers are in play. ✴ eXterminate - A player has destroyed another player's Capital City (C.C). Each round has 3 phases performed in o", "headingPath": "The 4 \"X-Objectives\" · Playing a Round", "sharpsignalDocId": 847}, {"page": 4, "score": 0.042744, "snippet": "Then, deal 1 Spell Card to each player to be placed in their \"hand,\" also referred to as a player's \"Spell Library.\" Always keep cards in your Spell Library secret from other players. 4. Take 3 Resource Tokens (1 Ore, 1 Mana, 1 Food), which have not yet been used, and while cupped in a player’s hand", "headingPath": "", "sharpsignalDocId": 847}, {"page": 4, "score": 0.032258, "snippet": "Game Setup 1. P lace the Game Board in the center of the table. For a 1-4 player game, use the side of the board with the “1-4” in the upper-left corner. The reverse side of the board with the \"5-6\" requires the Order & Chaos Expansion. 2. Each player selects a Faction and collects its Faction Compo", "headingPath": "", "sharpsignalDocId": 847}, {"page": 4, "score": 0.031746, "snippet": "Place the Game Board in the center of the table. For a 1-4 player game, use the side of the board with the ' 1-4 ' in the upper-left corner. The reverse side of the board with the \"5-6\" requires the Order & Chaos Expansion . Each player selects a Faction and collects its Faction Components : Place t", "headingPath": "Game Setup", "sharpsignalDocId": 847}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "Playing a Round", "sharpsignalDocId": 847}, {"page": 31, "quote": null, "headingPath": "The 4 \"X-Objectives\" · Playing a Round", "sharpsignalDocId": 847}, {"page": 30, "quote": null, "headingPath": "The 4 \"X-Objectives\" · Playing a Round", "sharpsignalDocId": 847}, {"page": 17, "quote": null, "headingPath": "Following a Solo Action Card · Team Play Variant · Components and Setup · Player Seat Positions · Recruit", "sharpsignalDocId": 847}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 847 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 847 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)
- answer fence
- passed — letter density 0.90732 of 1284 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 13, 2026 00:27
retrieval — what the passage search returned
what this block IS: the PASSAGE SEARCH's own results — the same search that fills this page's closest-passages list — and NOT the passages the answerer read. Answering runs its OWN retrieval: a far wider candidate pool, re-ranked down to a final handful, plus floors this search never applies — the base rulebook, surviving errata corrections, and one slot per book on a multi-book read. Each of those armed only if THIS ask sent what it needs: the boost block names the ids it forwarded, and the scope line names the books it read. A document the answer CITES that no row here names is therefore EXPECTED, not a defect: two searches, two candidate pools, two orders. The answerer's own final rows are shown in their own block below, beside these and never mixed into them.
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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Following a Solo Action Card · Team Play Variant · Components and Setup · Player Seat Positions · Recruit | p.17 | 0.045928 (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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | p.6 | 0.045724 (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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Playing a Round | p.6 | 0.044835 (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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | p.14 | 0.044283 (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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | The 4 "X-Objectives" · Playing a Round | p.30 | 0.043301 (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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | p.4 | 0.042744 (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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | p.4 | 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 | |
| #8 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Game Setup | p.4 | 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 |
what the answerer read — the passages it actually had in front of it
what this block IS: the passages the ANSWERING read put in front of the answerer, in the order it read them — the other half of the two reads described above, and the one that decides what the answer could possibly say. Each row names the book it came from and where in that book it sits, what it scored when the search arms were fused, which arm carried it there, and whether the re-ranker chose it or a floor guaranteed it a slot. A row here that no passage-search row names is EXPECTED: a far wider pool, re-ranked, with floors the passage search never applies.
candidate pool: the answering read scored 80 passages, out of a ceiling of 80 set gateway-side. Both figures are reported by the gateway for THIS ask — measurements of what actually happened, not constants read out of anyone's source and printed here on faith.
floors armed for this ask: the base rulebook — armed · surviving errata corrections — not armed · one slot per book on a multi-book read — not armed. Every floor is stated on every ask, armed or not, so a floor that did not apply here is never mistaken for one this app does not know about.
arms fused for this ask: vector + full-text + the doc-priority boost arm. Stated separately from the rows because an arm that ran and carried nothing is a different fact from an arm that never ran.
| read at | document | heading | page | fused rank | fused RRF score | carried by | how it got its slot |
|---|---|---|---|---|---|---|---|
| #1 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Playing a Round | p.6 | #3 | 0.044835 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Select a Tactic Card to Play: | p.11 | #9 | 0.029907 (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)) | vector + full-text | the re-ranker chose it |
| #3 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | The 4 "X-Objectives" · Playing a Round | p.31 | #12 | 0.027984 (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)) | vector + full-text | the re-ranker chose it |
| #4 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Game Setup | p.4 | #8 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Following a Solo Action Card · Team Play Variant · Components and Setup · Player Seat Positions · Recruit | p.17 | #1 | 0.045928 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #6 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | The 4 "X-Objectives" · Playing a Round | p.30 | #5 | 0.043301 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #7 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | p.4 | #7 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it | |
| #8 | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | p.14 | #4 | 0.044283 (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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
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 Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Playing a Round | p.6 | no quote on the wire |
| [2] | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | The 4 "X-Objectives" · Playing a Round | p.31 | no quote on the wire |
| [3] | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | The 4 "X-Objectives" · Playing a Round | p.30 | no quote on the wire |
| [4] | RULEBOOK Heroes of Land, Air & Sea — Rulebook (corpus doc 847) | Following a Solo Action Card · Team Play Variant · Components and Setup · Player Seat Positions · Recruit | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 72 ms · first delta 4017 ms · total 6605 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 72 ms · ask 6530 ms · gateway work 6605 ms · total 6605 ms
- tokens in (the prompt the answerer read)
- 3640
- tokens out (what the answerer generated)
- 379
- tok/sec
- 149.6 tok/sec — 379 output tokens in 2.533 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 8s 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 782), 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.