You asked
How do I set up the game?
Answered counted as answeredAsked with: Ark Novabg-342942-en-1e
🔧 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 258 ms · ask 16136 ms · total 517224 ms
- single-flight (PR-5)
- queued 500822 ms · generation 16402 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048172, "snippet": "B 4 1 Place the game board in the center of the table. Take the Break token and place it on the start space of the Break track that corresponds to your player count. If there are three players, place the Break token on the space marked 3 . 2 3 Shuffle the Zoo cards to create a face-down deck on the ", "headingPath": "Other · Global Setup", "sharpsignalDocId": 247}, {"page": 4, "score": 0.047883, "snippet": "For your personal setup, each of you takes the following steps: A Take a random Map A zoo map , and place it with that side up in front of you. Return the remaining zoo maps to the box. They are not used in this game. 4 of the 8 zoo maps have Map A on one side. All 4 copies of Map A are identical an", "headingPath": "Personal Setup", "sharpsignalDocId": 247}, {"page": 5, "score": 0.046898, "snippet": "5 Place the Association board next to the game board, leaving enough room for one row of cards above and one row of cards below the board. 5a Place 1 partner zoo of each continent and 1 university kind on the spaces provided on the Association board. of each Shuffle the Base Conservation Project car", "headingPath": "Personal Setup", "sharpsignalDocId": 247}, {"page": 20, "score": 0.046696, "snippet": "If you play Ark Nova on your own, modify the rules as follows: Lay out 3 basic Conservation Project cards and do not place any tokens of a different color on them (i. e. like a 3-player setup). Do not use the Break token. Instead, place 7 player tokens of any unused color on the spaces in the left c", "headingPath": "SOLO GAME · Setup · Turn / Cards", "sharpsignalDocId": 247}, {"page": 20, "score": 0.046642, "snippet": "Every time you end a turn, move the topmost player token in the left column of the solo tile onto the space to its right (in the right column) (1) . If you move the last token from the left column into the right column (2) (and thus reveal the break icon), you immediately resolve a break. At the beg", "headingPath": "Gameplay / Breaks · Difficulty Levels / Solo Challenge", "sharpsignalDocId": 247}, {"page": 7, "score": 0.03125, "snippet": "The game board has a Break track to count down the time remaining until the next break. At the beginning of the game, and after each break, the Break token goes on the starting space corresponding to your player count (1) . Whenever you advance the Break token, move it the appropriate number of spac", "headingPath": "The Break Track", "sharpsignalDocId": 247}, {"page": 3, "score": 0.029851, "snippet": "3 Setup ................................................ 4 Gameplay ............................................. 6 • Your Zoo Map .................................... 6 • Zoo Cards ........................................ 7 → The Break Track ............................... 7 A Turn / The 5 Action C", "headingPath": "", "sharpsignalDocId": 247}, {"page": 6, "score": 0.029412, "snippet": "Ark Nova does not play in formal rounds; instead, players simply take turns (in clockwise order) taking one turn at a time until the end of the game is triggered. In addition, there are so-called breaks in between, when the game is put on hold for an administration phase. During these breaks you wil", "headingPath": "GAMEPLAY", "sharpsignalDocId": 247}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "Other · Global Setup", "sharpsignalDocId": 247}, {"page": 4, "quote": null, "headingPath": "Personal Setup", "sharpsignalDocId": 247}, {"page": 5, "quote": null, "headingPath": "Personal Setup", "sharpsignalDocId": 247}, {"page": 5, "quote": null, "headingPath": "Personal Setup", "sharpsignalDocId": 247}, {"page": 20, "quote": null, "headingPath": "SOLO GAME · Setup · Turn / Cards", "sharpsignalDocId": 247}, {"page": 20, "quote": null, "headingPath": "Gameplay / Breaks · Difficulty Levels / Solo Challenge", "sharpsignalDocId": 247}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 247 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 247 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 14:16
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. How much wider that pool was is set gateway-side and is NOT REPORTED for this ruling, and neither are the answerer's final rows — so rulesage has nothing of its own to show beside these.
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 Ark Nova — Rulebook (corpus doc 247) | Other · Global Setup | p.4 | 0.048172 (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 Ark Nova — Rulebook (corpus doc 247) | Personal Setup | p.4 | 0.047883 (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 Ark Nova — Rulebook (corpus doc 247) | Personal Setup | p.5 | 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 Ark Nova — Rulebook (corpus doc 247) | SOLO GAME · Setup · Turn / Cards | p.20 | 0.046696 (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 Ark Nova — Rulebook (corpus doc 247) | Gameplay / Breaks · Difficulty Levels / Solo Challenge | p.20 | 0.046642 (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 Ark Nova — Rulebook (corpus doc 247) | The Break Track | p.7 | 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 Ark Nova — Rulebook (corpus doc 247) | p.3 | 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 Ark Nova — Rulebook (corpus doc 247) | GAMEPLAY | p.6 | 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.
the passages the answerer read: NOT RECORDED for this ruling. Any of three things leaves this empty, and they are all different from the answerer having had nothing to read: this ask may never have reached a gateway at all; a multi-book ask keeps each book's own context on that book's own page rather than here; or the gateway build that answered may simply not report it. What this NEVER means is that the answerer read nothing — an answer was composed from passages either way, and their absence here is a gap in what we were told, not in what it read.
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 Ark Nova — Rulebook (corpus doc 247) | Other · Global Setup | p.4 | no quote on the wire |
| [2] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Personal Setup | p.4 | no quote on the wire |
| [3] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Personal Setup | p.5 | no quote on the wire |
| [4] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Personal Setup | p.5 | no quote on the wire |
| [5] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | SOLO GAME · Setup · Turn / Cards | p.20 | no quote on the wire |
| [6] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Gameplay / Breaks · Difficulty Levels / Solo Challenge | p.20 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 258 ms · first delta 9587 ms · total 517224 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 500822 ms · retrieval 258 ms · ask 16136 ms · gateway work 16402 ms · total 517224 ms
- tokens in (the prompt the answerer read)
- 3562
- tokens out (what the answerer generated)
- 928
- tok/sec
- 137.4 tok/sec — 928 output tokens in 6.752 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 43s 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
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
set up
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 173), 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.