You asked
How do I play?
Answered counted as answeredAsked with: PARKSbg-266524-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 91 ms · ask 6803 ms · total 6896 ms
- single-flight (PR-5)
- queued 0 ms · generation 6896 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 1, "score": 0.04918, "snippet": "celebrates America's national parks and features art from the Fifty-Nine Parks Print Series. Players take on the role of two hikers who will trek trails to see sites, observe wildlife, take photos, and visit national parks over the course of the game. HENRY AUDUBON Watch how to play at PARKSGAME.COM", "headingPath": "", "sharpsignalDocId": 236}, {"page": 3, "score": 0.048131, "snippet": "The four SEASONS of the Year will make up the four rounds of play over the course of the game. Seasons change-up gameplay each round, and a Season ends when all Hikers reach the Trail End. To start, see how the Season affects gameplay for the round and if any immediate action is necessary from its e", "headingPath": "STARTING A SEASON · TAKING TURNS · TRAIL SITES · BASIC SITES · ADVANCED SITES", "sharpsignalDocId": 236}, {"page": 2, "score": 0.046898, "snippet": "CANTEENS · Shuffle the Canteen cards face down. Deal one face up to each player. This is their starting Canteen. Place the remaining Canteen deck onto its area on the top left of the board. YEAR · Shuffle the Year deck. Deal two cards to each player. Players choose one of the two as their Personal B", "headingPath": "SETUP CONTINUED", "sharpsignalDocId": 236}, {"page": 6, "score": 0.045476, "snippet": "When setting up the Trail, place the Trail End on the SOLO side. After choosing your Hiker and Campfire color, choose one for the Rangers. Rangers do not need their Campfire. Place your Hikers and the Rangers at the Trailhead. Place the Ranger Tracker from the SOLO deck next to your play area. Shuff", "headingPath": "SOLO MODE SCORING", "sharpsignalDocId": 236}, {"page": 4, "score": 0.031746, "snippet": "ONGOING ABILITY All Gear cards have ongoing abilities, but this one also has an action that rewards the player with a Canteen when purchased VISIT A PARK · Any number of Hikers can occupy the Visit a Park area. To Visit a Park, choose one of the three available on the board or one you have reserved ", "headingPath": "AT THE TRAIL END", "sharpsignalDocId": 236}, {"page": 4, "score": 0.03125, "snippet": "The TRAIL END gives Hikers a moment to reflect on the journey. When a Hiker arrives here, the player immediately relights their Campfire if it is extinguished, and then chooses one of the available areas for their Hikerplacing it vertically in the farthest right available slot of that area: PLACE RE", "headingPath": "AT THE TRAIL END", "sharpsignalDocId": 236}, {"page": 7, "score": 0.030303, "snippet": "TAKING TURNS · Turns alternate between you and the Rangers. On your turn, choose either of your Hikers and move them down the Trail to visit a Site and take its action-following the same movement rules as multiplayer. For the Rangers' turn, flip over the top Gear card from the deck and place it in a", "headingPath": "SOLO MODE REFERENCE", "sharpsignalDocId": 236}, {"page": 5, "score": 0.029412, "snippet": "7 Once a player's two Hikers reach the Trail End they will no longer take turns for the Season. When only one Hiker is left on the Trail, the player must move the Hiker to the Trail End and choose an action there. This marks the end of the Season, on the board you'll find a reminder of what happens ", "headingPath": "AT THE TRAIL END · END OF A SEASON · LAST HIKER ON THE TRAIL · BEGIN A NEW SEASON · GAME END · PARK + YEAR DETAILS", "sharpsignalDocId": 236}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "STARTING A SEASON · TAKING TURNS · TRAIL SITES · BASIC SITES · ADVANCED SITES", "sharpsignalDocId": 236}, {"page": 4, "quote": null, "headingPath": "WILDLIFE AND TOKEN LIMIT · DETAILS ON ACTIONS · REFERS TO CANTEENS IN A PLAYER'S AREA", "sharpsignalDocId": 236}, {"page": 4, "quote": null, "headingPath": "AT THE TRAIL END", "sharpsignalDocId": 236}, {"page": 4, "quote": null, "headingPath": "AT THE TRAIL END", "sharpsignalDocId": 236}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 236 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 236 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 0.89781 of 2143 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 05:40
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 PARKS — Rulebook (corpus doc 236) | p.1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 | |
| #2 | RULEBOOK PARKS — Rulebook (corpus doc 236) | STARTING A SEASON · TAKING TURNS · TRAIL SITES · BASIC SITES · ADVANCED SITES | p.3 | 0.048131 (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 PARKS — Rulebook (corpus doc 236) | SETUP CONTINUED | p.2 | 0.046898 (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 PARKS — Rulebook (corpus doc 236) | SOLO MODE SCORING | p.6 | 0.045476 (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 PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END | 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 |
| #6 | RULEBOOK PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END | 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 |
| #7 | RULEBOOK PARKS — Rulebook (corpus doc 236) | SOLO MODE REFERENCE | p.7 | 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 |
| #8 | RULEBOOK PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END · END OF A SEASON · LAST HIKER ON THE TRAIL · BEGIN A NEW SEASON · GAME END · PARK + YEAR DETAILS | p.5 | 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 18 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 PARKS — Rulebook (corpus doc 236) | SETUP CONTINUED | p.2 | #3 | 0.046898 (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 PARKS — Rulebook (corpus doc 236) | p.1 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it | |
| #3 | RULEBOOK PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END | p.4 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END | p.4 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #5 | RULEBOOK PARKS — Rulebook (corpus doc 236) | HOW DO SUNSCREEN OR RAIN GEAR WORK? | p.5 | #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 |
| #6 | RULEBOOK PARKS — Rulebook (corpus doc 236) | STARTING A SEASON · TAKING TURNS · TRAIL SITES · BASIC SITES · ADVANCED SITES | p.3 | #2 | 0.048131 (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 PARKS — Rulebook (corpus doc 236) | WILDLIFE AND TOKEN LIMIT · DETAILS ON ACTIONS · REFERS TO CANTEENS IN A PLAYER'S AREA | p.4 | #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 |
| #8 | RULEBOOK PARKS — Rulebook (corpus doc 236) | SOLO MODE SCORING | p.6 | #4 | 0.045476 (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 PARKS — Rulebook (corpus doc 236) | STARTING A SEASON · TAKING TURNS · TRAIL SITES · BASIC SITES · ADVANCED SITES | p.3 | no quote on the wire |
| [2] | RULEBOOK PARKS — Rulebook (corpus doc 236) | WILDLIFE AND TOKEN LIMIT · DETAILS ON ACTIONS · REFERS TO CANTEENS IN A PLAYER'S AREA | p.4 | no quote on the wire |
| [3] | RULEBOOK PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END | p.4 | no quote on the wire |
| [4] | RULEBOOK PARKS — Rulebook (corpus doc 236) | AT THE TRAIL END | p.4 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 91 ms · first delta 1913 ms · total 6896 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 91 ms · ask 6803 ms · gateway work 6896 ms · total 6896 ms
- tokens in (the prompt the answerer read)
- 3012
- tokens out (what the answerer generated)
- 679
- tok/sec
- 137.6 tok/sec — 679 output tokens in 4.936 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s 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 162), 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.