You asked
describe the different factions
Answered counted as answeredAsked with: Scythebg-169786-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 67 ms · ask 4439 ms · total 4507 ms
- single-flight (PR-5)
- queued 0 ms · generation 4507 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 21, "score": 0.032787, "snippet": "Each faction has a special ability indicated at the upper right of the Faction Mat. RUSVIET (RELENTLESS): You may choose the same section on your Player Mat as the previous turn(s). The Rusviets push their people hard, day after day, to achieve their ultimate goal. While other factions let their inf", "headingPath": "F A C T I O N A B I L I T I E S", "sharpsignalDocId": 114}, {"page": 30, "score": 0.032258, "snippet": "You are represented on the board by your character, who has been sent on a mission to make your faction's claim to the uncharted lands surrounding the defunct Factory. Each character unit is comprised of a person and their animal companion. While each of the characters appears to be functionally the", "headingPath": "CHARACTERS", "sharpsignalDocId": 114}, {"page": 21, "score": 0.031746, "snippet": "The Saxon faction may complete both of their objective cards (they don't discard the second card after achieving the first), and they are not limited to 2 combat victory stars. If Saxony has available stars, after winning combat, they must place the star. DESIGNER'S NOTE: One of the subtle benefits ", "headingPath": "F A C T I O N A B I L I T I E S", "sharpsignalDocId": 114}, {"page": 5, "score": 0.03125, "snippet": "Each of the three unit types in the game-characters, mechs, and workers-share two key similarities: They can move around the board (not over rivers or onto lakes, by default). They can transport any number of resource tokens. Each type of unit also has some unique traits that aren't shared by the ot", "headingPath": "TYPES OF UNITS", "sharpsignalDocId": 114}, {"page": 3, "score": 0.030769, "snippet": "FACTION PRIMARY COLOR 1 Faction Mat 1 action token 1 popularity token 1 power token 6 star tokens 4 structure tokens 4 recruit tokens 4 mech miniatures 1 character miniature 8 workers 6 technology cubes 6 x 6 x 4 x 8 x 6 x 4 x 8 x 6 x 8 x 6 x 4 x 8 x 6 x 3", "headingPath": "5 quick-start cards · F A C T I O N C O M P O N E N T S", "sharpsignalDocId": 114}, {"page": 9, "score": 0.030303, "snippet": "Your Faction Mat is where you keep your mechs, stars, and coins. Each Faction Mat also shows a special ability in the upper right corner. STARS: Place your 6 star tokens at the upper left near the faction emblem. Do not put tokens on top of the Recruit One-Time Bonuses (bottom left corner)-you'll ga", "headingPath": "FACTION MAT · QUICK-START CARD · RIVERWALK CARD", "sharpsignalDocId": 114}, {"page": 6, "score": 0.029851, "snippet": "6 ENCOUNTER TOKENS (GREEN COMPASS): Place 1 encounter token on each territory marked with an encounter symbol on the board (11 total tokens). RESOURCES AND COINS: Place the resource tokens (wood, oil, food, and metal), coins, and multiplier tokens in a supply area next to the board. Shuffle the enco", "headingPath": "TYPES OF UNITS · BOARD SETUP · SETUP · ENCOUNTER CARDS (GREEN) : · FACTION SELECTION:", "sharpsignalDocId": 114}, {"page": 17, "score": 0.029412, "snippet": "RIVERWALK: Your character and mechs can move across rivers onto farms and tundra. WAYFARE: Your character and mechs may move from a territory or home base to any inactive faction's home base or your own regardless of the distance. An 'inactive faction' is any faction not currently in the game, inclu", "headingPath": "CRIMEA · POLANIA", "sharpsignalDocId": 114}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 21, "quote": null, "headingPath": "F A C T I O N A B I L I T I E S", "sharpsignalDocId": 114}, {"page": 30, "quote": null, "headingPath": "CHARACTERS", "sharpsignalDocId": 114}, {"page": 21, "quote": null, "headingPath": "F A C T I O N A B I L I T I E S", "sharpsignalDocId": 114}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 114 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 114 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 0.90554 of 1101 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 12, 2026 07:05
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 Scythe — Rulebook (corpus doc 114) | F A C T I O N A B I L I T I E S | p.21 | 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 Scythe — Rulebook (corpus doc 114) | CHARACTERS | p.30 | 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 Scythe — Rulebook (corpus doc 114) | F A C T I O N A B I L I T I E S | p.21 | 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 Scythe — Rulebook (corpus doc 114) | TYPES OF UNITS | 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 Scythe — Rulebook (corpus doc 114) | 5 quick-start cards · F A C T I O N C O M P O N E N T S | 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)) | 256 |
| #6 | RULEBOOK Scythe — Rulebook (corpus doc 114) | FACTION MAT · QUICK-START CARD · RIVERWALK CARD | p.9 | 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 Scythe — Rulebook (corpus doc 114) | TYPES OF UNITS · BOARD SETUP · SETUP · ENCOUNTER CARDS (GREEN) : · FACTION SELECTION: | p.6 | 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 Scythe — Rulebook (corpus doc 114) | CRIMEA · POLANIA | p.17 | 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 |
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 43 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 Scythe — Rulebook (corpus doc 114) | F A C T I O N A B I L I T I E S | p.21 | #1 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Scythe — Rulebook (corpus doc 114) | CHARACTERS | p.30 | #2 | 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 |
| #3 | RULEBOOK Scythe — Rulebook (corpus doc 114) | FACTION MAT · QUICK-START CARD · RIVERWALK CARD | p.9 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Scythe — Rulebook (corpus doc 114) | F A C T I O N C O M P O N E N T S · TERRITORY · HOME BASE · CONTROL · RESOURCES · I M P O R T A N T C O N C E P T S · … | p.4 | #10 | 0.014286 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #5 | RULEBOOK Scythe — Rulebook (corpus doc 114) | CONTROLLED BY WORKERS · CONTROLLED BY A STRUCTURE · CONTROLLED BY CHARACTER AND/OR MECHS | p.11 | #11 | 0.014085 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #6 | RULEBOOK Scythe — Rulebook (corpus doc 114) | BACKSTORY · OBJECT OF THE GAME · GOAL | p.1 | #22 | 0.012195 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #7 | RULEBOOK Scythe — Rulebook (corpus doc 114) | CRIMEA · POLANIA | p.17 | #8 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Scythe — Rulebook (corpus doc 114) | F A C T I O N A B I L I T I E S | p.21 | #3 | 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 |
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 Scythe — Rulebook (corpus doc 114) | F A C T I O N A B I L I T I E S | p.21 | no quote on the wire |
| [2] | RULEBOOK Scythe — Rulebook (corpus doc 114) | CHARACTERS | p.30 | no quote on the wire |
| [3] | RULEBOOK Scythe — Rulebook (corpus doc 114) | F A C T I O N A B I L I T I E S | p.21 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 67 ms · first delta 2249 ms · total 4507 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 67 ms · ask 4439 ms · gateway work 4507 ms · total 4507 ms
- tokens in (the prompt the answerer read)
- 3558
- tokens out (what the answerer generated)
- 323
- tok/sec
- 147.5 tok/sec — 323 output tokens in 2.190 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 28s 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 2), 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.