You asked
How do I play?
Answered counted as answeredAsked with: Innovation Ultimatebg-388367-en-1e
One rule clearer, zero feelings hurt.
🔧 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 148 ms · ask 5259 ms · total 5409 ms
- single-flight (PR-5)
- queued 0 ms · generation 5409 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04866, "snippet": "For most groups, that's sufficient information to begin a playthrough. Shuffle all the cards back into their decks, and start a game for real, as described in Setup (p5). Innovation is often best learned as an 'as you go' game, especially if you set expectations for it to be an interesting journey t", "headingPath": "Reset & Play", "sharpsignalDocId": 1059}, {"page": 3, "score": 0.046394, "snippet": "Innovation can appear daunting at first, but much of its complexity arises from strategy and combinations of cards rather than difficult-to-learn rules. Since we've taught it to countless people over the years, we have some tips for both learning and teaching the game! The first and most important l", "headingPath": "Learning Innovation · LEARNING FROM SCRATCH · GENERAL INFORMATION", "sharpsignalDocId": 1059}, {"page": 5, "score": 0.044758, "snippet": "Set up the Supply Area (1-4) and then each player's area (5-7). For expansion info, see Expansion Setup (p 20). Split the base set cards into their eleven decks, shuffle them, and arrange them like a clock, as shown above. If space is an issue, you can arrange them differently. Take one card from ea", "headingPath": "Setup", "sharpsignalDocId": 1059}, {"page": 5, "score": 0.042649, "snippet": "5 Set up the Supply Area (1-4) and then each player’s area (5-7). For expansion info, see Expansion Setup (p 20). Split the base set cards into their eleven decks, shuffle them, and arrange them like a clock, as shown above. If space is an issue, you can arrange them differently. Take one card from ", "headingPath": "", "sharpsignalDocId": 1059}, {"page": 18, "score": 0.042486, "snippet": "In games with four or more players, Parley rules are in effect. For the purposes of Parley rules, a player is either a neighbor (adjacent to your left or right) or distant. There are three situations where a Parley is relevant. The cost to Parley is to return a card from your hand. When choosing a c", "headingPath": "Parley Rules", "sharpsignalDocId": 1059}, {"page": 4, "score": 0.031746, "snippet": "When teaching Innovation to others, it can be easy to overwhelm new players with information. They don't need to know every single keyword and potential card effect; although, it's good to preface a teaching session by letting them know that their board states can change very rapidly, for better or ", "headingPath": "Teaching · Staging · Overview · Gameplay", "sharpsignalDocId": 1059}, {"page": 20, "score": 0.030679, "snippet": "Once you've played the base game a few times, you can add in expansions. Playing with expansions before learning the base game is not recommended. The rules for each expansion are explained on the next several pages. Once in play, expansion cards behave just like base cards. They can be in score pil", "headingPath": "Playing with Expansions · EXPANSION SETUP · ECHOES OF THE PAST · FIGURES IN THE SAND", "sharpsignalDocId": 1059}, {"page": 8, "score": 0.029851, "snippet": "Each player must take two actions on their turn. There are four types of actions: Draw , Meld , Dogma , and Achieve . You can perform the same type of action twice, or choose two different actions. These are your First Action and Second Action . NOTE 1 : The first player (or first two in a 4+ player", "headingPath": "Your Turn · Draw Action", "sharpsignalDocId": 1059}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 5, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 1059}, {"page": 8, "quote": null, "headingPath": "Your Turn · Draw Action", "sharpsignalDocId": 1059}, {"page": 6, "quote": null, "headingPath": "", "sharpsignalDocId": 1059}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1059 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1059 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 0.88764 of 1246 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 12:42 UTC
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 Innovation Ultimate — Rulebook (corpus doc 1059) | Reset & Play | p.4 | 0.04866 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | Learning Innovation · LEARNING FROM SCRATCH · GENERAL INFORMATION | p.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)) | 300 |
| #3 | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | Setup | p.5 | 0.044758 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | p.5 | 0.042649 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | Parley Rules | p.18 | 0.042486 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | Teaching · Staging · Overview · Gameplay | 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 |
| #7 | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | Playing with Expansions · EXPANSION SETUP · ECHOES OF THE PAST · FIGURES IN THE SAND | p.20 | 0.030679 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | Your Turn · Draw Action | 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 |
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 67 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 Innovation Ultimate — Rulebook (corpus doc 1059) | Reset & Play | p.4 | #1 | 0.04866 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | YOUR BOARD · CAN I LOOK? · UNOWNED CARDS | p.6 | #12 | 0.028814 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | Your Turn · Draw Action | p.8 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | Dogma Keywords | p.12 | #20 | 0.024098 (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 |
| #5 | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | Setup | p.5 | #3 | 0.044758 (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 |
| #6 | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | 19 Strategy Tips | p.19 | #13 | 0.028543 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | Dogma Keywords | p.13 | #21 | 0.02384 (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 Innovation Ultimate — Rulebook (corpus doc 1059) | p.6 | #9 | 0.029644 (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 |
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 Innovation Ultimate — Rulebook (corpus doc 1059) | Setup | p.5 | no quote on the wire |
| [2] | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | Your Turn · Draw Action | p.8 | no quote on the wire |
| [3] | RULEBOOK Innovation Ultimate — Rulebook (corpus doc 1059) | p.6 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 148 ms · first delta 3335 ms · total 5409 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 148 ms · ask 5259 ms · gateway work 5409 ms · total 5409 ms
- tokens in (the prompt the answerer read)
- 3040
- tokens out (what the answerer generated)
- 407
- tok/sec
- 201.3 tok/sec — 407 output tokens in 2.022 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 38s ago)
- answerer host (measured by rulesage)
- reachable (for 24h, checked 0s ago)
- answerer node (the seat proxy's own header — this probe, not this ask)
- node1
- 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 989), 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.