You asked
How do I play?
Answered counted as answeredAsked with: Ark Novabg-342942-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 78 ms · ask 7120 ms · total 9331 ms
- single-flight (PR-5)
- queued 2130 ms · generation 7201 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 11, "score": 0.047619, "snippet": "Play Animal cards from your hand. Compare the strength of the action with the table on the card. Play up to the indicated number of Animal cards from your hand. Follow the steps below for each animal: Check conditions : Any conditions you must fulfill in order to play the Animal card are indicated o", "headingPath": "ANIMALS", "sharpsignalDocId": 247}, {"page": 20, "score": 0.046964, "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": 12, "score": 0.046394, "snippet": "You perform the Animals action with strength 5 to play 2 animals. First, you play the Eurasian Eagle-Owl (1) . You pay the cost, flip over a 2-space enclosure (2) , gain 4 appeal, and execute the card's effect, putting 2 new cards into your hand (3) . Fortunately, the Eurasian Lynx is among them, wh", "headingPath": "Example: Playing animals (immediate effect)", "sharpsignalDocId": 247}, {"page": 6, "score": 0.0463, "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}, {"page": 4, "score": 0.045743, "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": 13, "score": 0.044337, "snippet": "You are red, and you use the upgraded Animals action to play 2 animals. Because you are performing the action with strength 5, you may first increase the reputation of your zoo by 1 to a reputation of 4 (1) . This means that folders 1-3 are now within reputation range for you. You play the European ", "headingPath": "Example: Playing animals using side II", "sharpsignalDocId": 247}, {"page": 8, "score": 0.042196, "snippet": "One of them allows you to choose an alternative. So be aware that you cannot upgrade all of your Action cards! In each game you will have to decide which upgrades are most important to you. You may not 'do nothing' with your action (e. g. play 0 Animal cards or build 0 buildings). The individual act", "headingPath": "A Turn / The 5 Action Cards", "sharpsignalDocId": 247}, {"page": 4, "score": 0.030303, "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}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 6, "quote": null, "headingPath": "GAMEPLAY", "sharpsignalDocId": 247}, {"page": 11, "quote": null, "headingPath": "ANIMALS", "sharpsignalDocId": 247}, {"page": 13, "quote": null, "headingPath": "Play Animal cards from your hand or within reputation range. · Placing Cards · Animal categories", "sharpsignalDocId": 247}, {"page": 11, "quote": null, "headingPath": "ANIMALS", "sharpsignalDocId": 247}, {"page": 12, "quote": null, "headingPath": "Example: Playing animals (immediate effect)", "sharpsignalDocId": 247}, {"page": 17, "quote": null, "headingPath": "SPONSORS", "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)
- answer fence
- passed — letter density 0.92499 of 2373 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 13, 2026 13:16
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. 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 Ark Nova — Rulebook (corpus doc 247) | ANIMALS | p.11 | 0.047619 (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) | Gameplay / Breaks · Difficulty Levels / Solo Challenge | p.20 | 0.046964 (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) | Example: Playing animals (immediate effect) | p.12 | 0.046394 (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) | GAMEPLAY | p.6 | 0.0463 (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) | Personal Setup | p.4 | 0.045743 (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) | Example: Playing animals using side II | p.13 | 0.044337 (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) | A Turn / The 5 Action Cards | p.8 | 0.042196 (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) | Other · Global Setup | p.4 | 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 |
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 44 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 Ark Nova — Rulebook (corpus doc 247) | Example: Playing animals (immediate effect) | p.12 | #3 | 0.046394 (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 Ark Nova — Rulebook (corpus doc 247) | SPONSORS | p.17 | #10 | 0.029727 (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 Ark Nova — Rulebook (corpus doc 247) | ANIMALS | p.11 | #1 | 0.047619 (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 |
| #4 | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | GAMEPLAY | p.6 | #4 | 0.0463 (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 |
| #5 | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | SOLO GAME · Setup · Turn / Cards | p.20 | #14 | 0.02632 (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 |
| #6 | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | ANIMALS | p.11 | #11 | 0.028309 (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 |
| #7 | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Play Animal cards from your hand or within reputation range. · Placing Cards · Animal categories | p.13 | #9 | 0.030018 (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 |
| #8 | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Example: Playing animals using side II | p.13 | #6 | 0.044337 (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 Ark Nova — Rulebook (corpus doc 247) | GAMEPLAY | p.6 | no quote on the wire |
| [2] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | ANIMALS | p.11 | no quote on the wire |
| [3] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Play Animal cards from your hand or within reputation range. · Placing Cards · Animal categories | p.13 | no quote on the wire |
| [4] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | ANIMALS | p.11 | no quote on the wire |
| [5] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | Example: Playing animals (immediate effect) | p.12 | no quote on the wire |
| [6] | RULEBOOK Ark Nova — Rulebook (corpus doc 247) | SPONSORS | p.17 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 78 ms · first delta 2828 ms · total 9331 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 2130 ms · retrieval 78 ms · ask 7120 ms · gateway work 7201 ms · total 9331 ms
- tokens in (the prompt the answerer read)
- 2985
- tokens out (what the answerer generated)
- 648
- tok/sec
- 149.4 tok/sec — 648 output tokens in 4.337 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 2s 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 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.