Ruling — Earthborne Rangers

You asked

Before anyone takes a turn, how is everything laid out on the table?

Abstained — no grounded answer; closest passages below counted as honest abstain

Asked with: Earthborne Rangersbg-342900-en-1e

The answerer couldn't ground a confident answer in the rulebook. The closest rulebook passages are below — check them before ruling.

RULEBOOK Earthborne Rangers — Rulebook · p.13 · TOKENS · REST

Many cards make use of unique tokens to track the number of times they can be used. These cards are marked with a number and name for the tokens in a box on the right side of the card. When one of these cards comes into play, place a number of general use tokens on this card equal to that number. Wh

RULEBOOK Earthborne Rangers — Rulebook · p.18 · CLEARING CARDS

You'll often be instructed to place two different kinds of tokens on cards: progress (  ) and harm (  ). Both are abstractions-stand-ins for the narrative outcomes of the tests you perform and the cards you play from your hand. Progress (  ) is a measure of time spent. For example, progress place

RULEBOOK Earthborne Rangers — Rulebook · p.22 · EXHAUST/READY

To exhaust a card, turn it ninety degrees. To ready a card, turn it upright. Exhausted cards do not fatigue you. Exhausted cards are not active, so you do not resolve challenge effects on them. You can interact with exhausted cards. If a text effect is prefaced by 'exhaust [this card],' you must be

RULEBOOK Earthborne Rangers — Rulebook · p.8 · TESTS · A NOTE ON STYLE · THE GOLDEN RULE · THE DELIGHTFUL RULE

Tests are shown on cards as narrative equations. They tell you what you can attempt in the world of the game, how to do it, and what will happen if you succeed or fail. You'll find tests on the gear you equip, some on beings, features, and locations in the environment, and four common tests found on

RULEBOOK Earthborne Rangers — Rulebook · p.12 · PERFORM A TEST

Tests represent your Ranger's interactions with their environment. They appear on cards as an aspect, plus an approach icon, followed by both a thematic and mechanical description of what your Ranger does if the test is successful. You always have access to four common tests which you can reference

🔧 debug — where this ruling came from

outcome: ABSTAINED — Abstained — no grounded answer; closest passages below
corpus profile: live
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 284 ms · ask 14617 ms · total 14914 ms
single-flight (PR-5): queued 0 ms · generation 14914 ms
retrieval refs (raw): [{"page": 13, "score": 0.032787, "snippet": "Many cards make use of unique tokens to track the number of times they can be used. These cards are marked with a number and name for the tokens in a box on the right side of the card. When one of these cards comes into play, place a number of general use tokens on this card equal to that number. Wh", "headingPath": "TOKENS · REST", "sharpsignalDocId": 511}, {"page": 18, "score": 0.032258, "snippet": "You'll often be instructed to place two different kinds of tokens on cards: progress (  ) and harm (  ). Both are abstractions-stand-ins for the narrative outcomes of the tests you perform and the cards you play from your hand. Progress (  ) is a measure of time spent. For example, progress place", "headingPath": "CLEARING CARDS", "sharpsignalDocId": 511}, {"page": 22, "score": 0.031746, "snippet": "To exhaust a card, turn it ninety degrees. To ready a card, turn it upright. Exhausted cards do not fatigue you. Exhausted cards are not active, so you do not resolve challenge effects on them. You can interact with exhausted cards. If a text effect is prefaced by 'exhaust [this card],' you must be ", "headingPath": "EXHAUST/READY", "sharpsignalDocId": 511}, {"page": 8, "score": 0.03125, "snippet": "Tests are shown on cards as narrative equations. They tell you what you can attempt in the world of the game, how to do it, and what will happen if you succeed or fail. You'll find tests on the gear you equip, some on beings, features, and locations in the environment, and four common tests found on", "headingPath": "TESTS · A NOTE ON STYLE · THE GOLDEN RULE · THE DELIGHTFUL RULE", "sharpsignalDocId": 511}, {"page": 12, "score": 0.030769, "snippet": "Tests represent your Ranger's interactions with their environment. They appear on cards as an aspect, plus an approach icon, followed by both a thematic and mechanical description of what your Ranger does if the test is successful. You always have access to four common tests which you can reference ", "headingPath": "PERFORM A TEST", "sharpsignalDocId": 511}, {"page": 12, "score": 0.030303, "snippet": "Each session of Earthborne Rangers represents one day of your campaign and is played in rounds. There is no limit to the number of rounds in a day. Each round is divided into four phases: \u0010 Phase 1: Path Cards \u0010 Phase 2: Ranger Turns \u0010 Phase 3: Travel \u0010 Phase 4: Refresh Each round, the Rangers spend", "headingPath": "PLAYING THE GAME · PHASE 1: PATH CARDS · PHASE 2: RANGER TURNS", "sharpsignalDocId": 511}, {"page": 8, "score": 0.029851, "snippet": "The circumstances of your tests are not always entirely under your control. There may be a loose rock in the cliff face you're attempting to scale, a sudden gust of wind that throws you off balance, or a surprisingly sure handhold that hastens your ascent. To represent unforeseen events, after you'v", "headingPath": "THE CHALLENGE DECK", "sharpsignalDocId": 511}, {"page": 9, "score": 0.029412, "snippet": "The play area is broken up into four distinct areas: The Surroundings: The surroundings set the stage for the game. They contain the cards representing the current location, the weather, and any missions the Rangers are trying to accomplish. Along the Way: When path cards are drawn, they are either ", "headingPath": "THE PLAY AREA · GETTING STARTED", "sharpsignalDocId": 511}]
citations (raw): []
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 511 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 511 boosted
answered-before recall: no past answered ruling for this game matched closely enough
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 06:00

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 Earthborne Rangers — Rulebook (corpus doc 511)	TOKENS · REST	p.13	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 Earthborne Rangers — Rulebook (corpus doc 511)	CLEARING CARDS	p.18	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 Earthborne Rangers — Rulebook (corpus doc 511)	EXHAUST/READY	p.22	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 Earthborne Rangers — Rulebook (corpus doc 511)	TESTS · A NOTE ON STYLE · THE GOLDEN RULE · THE DELIGHTFUL RULE	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 Earthborne Rangers — Rulebook (corpus doc 511)	PERFORM A TEST	p.12	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 Earthborne Rangers — Rulebook (corpus doc 511)	PLAYING THE GAME · PHASE 1: PATH CARDS · PHASE 2: RANGER TURNS	p.12	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 Earthborne Rangers — Rulebook (corpus doc 511)	THE CHALLENGE DECK	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 Earthborne Rangers — Rulebook (corpus doc 511)	THE PLAY AREA · GETTING STARTED	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

#	document	heading	page	quote chars

generation — timing and the path taken

timing split: retrieval 284 ms · first delta 14771 ms · total 14914 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 284 ms · ask 14617 ms · gateway work 14914 ms · total 14914 ms
tokens in (the prompt the answerer read): 3210
tokens out (what the answerer generated): 9
tok/sec: 147.5 tok/sec — 9 output tokens in 0.061 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 37s 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: ABSTAINED — Abstained — no grounded answer; closest passages below
abstain rationale: I don't have enough information.
the answerer's own words, verbatim — hostile corpus/LLM text, rendered escaped

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 440), 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.