You asked
How do I play?
Answered counted as answeredAsked with: Daybreakbg-334986-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 83 ms · ask 4552 ms · total 4637 ms
- single-flight (PR-5)
- queued 0 ms · generation 4637 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 6, "score": 0.04866, "snippet": "Play cards in front of a stack to make their actions available. Here, you might play Long Range Transmission in front because you can use it once per blue Grid tag, which the Clean Electricity Plants card has. When you take actions, you get to use all the tags behind it! Play in front Tuck a card be", "headingPath": "Play cards in 3 ways", "sharpsignalDocId": 521}, {"page": 10, "score": 0.048139, "snippet": "Daybreak is played in rounds, until everyone wins or loses together. There is no player order: you will all play simultaneously. Rounds have 5 stages: Players hold a global summit to review the Forecast Crisis card and select a Global Project card. Players focus on their own boards, drawing and play", "headingPath": "How to play · Global stage · Local stage · Emissions stage · Crisis stage · Growth stage · …", "sharpsignalDocId": 521}, {"page": 9, "score": 0.04741, "snippet": "Depending on the number of players, distribute the player boards and Reference cards below. Between yourselves, decide who is going to play which World Power. | Players | World Powers used | | 4 | All | | 3 | Majority World, Europe, & US | | 2 | China & US | | 1 | Any (see Reference card) | If you a", "headingPath": "Choose World Powers · Prepare player boards", "sharpsignalDocId": 521}, {"page": 5, "score": 0.046875, "snippet": "Reach Drawdown : the moment you collectively remove more Carbon from the atmosphere than you produce. You'll do that by playing cards that remove Dirty Energy and Emissions tokens from your player board, while adding Clean Energy tokens to keep up with the Energy Demand of your World Power. Everyone", "headingPath": "Here's how you win", "sharpsignalDocId": 521}, {"page": 8, "score": 0.044796, "snippet": "Put the Current Round token with the clock side face up on the space marked 1 on the round tracker. Put the 6 Planetary Effects tokens onto their matching starting locations. Put all 8 Temperature Bands, the Planetary Effects die, and the Geoengineering die onto the bulb of the Thermometer, so they'", "headingPath": "Set up central board · Prepare card decks", "sharpsignalDocId": 521}, {"page": 11, "score": 0.043549, "snippet": "Players focus on their own boards, drawing and playing Local Project cards to remove Emissions and Dirty Energy, add Clean Energy, increase Resilience, and help their fellow players. Each player draws 5 Local Project cards to add to their hand. Your hand is public, and you should keep it face up on ", "headingPath": "Local stage · Draw Local Project cards", "sharpsignalDocId": 521}, {"page": 11, "score": 0.042399, "snippet": "Each Local Project card in your Play Area has an action shown on it underneath its title. Typically, Local Actions only affect your own player board. For example, the card on the left's action is: 'Discard a card from your hand to add one Clean Energy token per Grid tag in this card's stack.' Unless", "headingPath": "Take a Local Action", "sharpsignalDocId": 521}, {"page": 18, "score": 0.030769, "snippet": "Want to make your game more challenging, less difficult, or just add variety? We've included a deck of Challenge cards that let you adjust the difficulty of the game or explore different climate scenarios. Challenge cards each have rules that either affect everyone or just an individual player. To m", "headingPath": "Challenge cards · Other setups", "sharpsignalDocId": 521}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 10, "quote": null, "headingPath": "How to play · Global stage · Local stage · Emissions stage · Crisis stage · Growth stage · …", "sharpsignalDocId": 521}, {"page": 11, "quote": null, "headingPath": "Local stage · Draw Local Project cards", "sharpsignalDocId": 521}, {"page": 11, "quote": null, "headingPath": "Take a Local Action", "sharpsignalDocId": 521}, {"page": 6, "quote": null, "headingPath": "Play cards in 3 ways", "sharpsignalDocId": 521}, {"page": 12, "quote": null, "headingPath": "Start a Local Project · Support a card · Support a Local Project · Support a Global Project", "sharpsignalDocId": 521}, {"page": 5, "quote": null, "headingPath": "", "sharpsignalDocId": 521}, {"page": 5, "quote": null, "headingPath": "Here's how you win", "sharpsignalDocId": 521}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 521 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 521 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 0.90278 of 1872 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 04:43
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 Daybreak — Rulebook (corpus doc 521) | Play cards in 3 ways | p.6 | 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 Daybreak — Rulebook (corpus doc 521) | How to play · Global stage · Local stage · Emissions stage · Crisis stage · Growth stage · … | p.10 | 0.048139 (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 Daybreak — Rulebook (corpus doc 521) | Choose World Powers · Prepare player boards | p.9 | 0.04741 (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 Daybreak — Rulebook (corpus doc 521) | Here's how you win | p.5 | 0.046875 (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 Daybreak — Rulebook (corpus doc 521) | Set up central board · Prepare card decks | p.8 | 0.044796 (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 Daybreak — Rulebook (corpus doc 521) | Local stage · Draw Local Project cards | p.11 | 0.043549 (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 Daybreak — Rulebook (corpus doc 521) | Take a Local Action | p.11 | 0.042399 (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 Daybreak — Rulebook (corpus doc 521) | Challenge cards · Other setups | p.18 | 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 |
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 30 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 Daybreak — Rulebook (corpus doc 521) | Play cards in 3 ways | p.6 | #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 Daybreak — Rulebook (corpus doc 521) | p.5 | #11 | 0.028898 (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 Daybreak — Rulebook (corpus doc 521) | Choose World Powers · Prepare player boards | p.9 | #3 | 0.04741 (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 Daybreak — Rulebook (corpus doc 521) | Local stage · Draw Local Project cards | p.11 | #6 | 0.043549 (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 Daybreak — Rulebook (corpus doc 521) | Start a Local Project · Support a card · Support a Local Project · Support a Global Project | p.12 | #10 | 0.029199 (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 Daybreak — Rulebook (corpus doc 521) | Take a Local Action | p.11 | #7 | 0.042399 (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 Daybreak — Rulebook (corpus doc 521) | How to play · Global stage · Local stage · Emissions stage · Crisis stage · Growth stage · … | p.10 | #2 | 0.048139 (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 |
| #8 | RULEBOOK Daybreak — Rulebook (corpus doc 521) | Here's how you win | p.5 | #4 | 0.046875 (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 Daybreak — Rulebook (corpus doc 521) | How to play · Global stage · Local stage · Emissions stage · Crisis stage · Growth stage · … | p.10 | no quote on the wire |
| [2] | RULEBOOK Daybreak — Rulebook (corpus doc 521) | Local stage · Draw Local Project cards | p.11 | no quote on the wire |
| [3] | RULEBOOK Daybreak — Rulebook (corpus doc 521) | Take a Local Action | p.11 | no quote on the wire |
| [4] | RULEBOOK Daybreak — Rulebook (corpus doc 521) | Play cards in 3 ways | p.6 | no quote on the wire |
| [5] | RULEBOOK Daybreak — Rulebook (corpus doc 521) | Start a Local Project · Support a card · Support a Local Project · Support a Global Project | p.12 | no quote on the wire |
| [6] | RULEBOOK Daybreak — Rulebook (corpus doc 521) | p.5 | no quote on the wire | |
| [7] | RULEBOOK Daybreak — Rulebook (corpus doc 521) | Here's how you win | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 83 ms · first delta 2058 ms · total 4637 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 83 ms · ask 4552 ms · gateway work 4637 ms · total 4637 ms
- tokens in (the prompt the answerer read)
- 2569
- tokens out (what the answerer generated)
- 519
- tok/sec
- 204.4 tok/sec — 519 output tokens in 2.539 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 28s 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 452), 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.