You asked
How do I play?
Answered counted as answeredAsked with: Oathbg-291572-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 82 ms · ask 9906 ms · total 9990 ms
- single-flight (PR-5)
- queued 0 ms · generation 9990 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.04866, "snippet": "If you're about to teach Oath right now without preparing much beforehand, we recommend using the card-based setup and one-round walkthrough. Set up the game using the card-based walkthrough. Find the three card packets labeled packets a, b, and c . Open Packet A and flip over the first card to begi", "headingPath": "eaching Oath Right Now?", "sharpsignalDocId": 434}, {"page": 4, "score": 0.048387, "snippet": "SEARCH AND PLAY ONE CARD Draw three cards from the world deck. Do not stop drawing if you draw a Vision! If you draw three Visions, keep drawing until you draw a denizen. Reveal the drawn cards except for Visions. Place them in a row in the order you drew them from left to right. For each battle pla", "headingPath": "", "sharpsignalDocId": 434}, {"page": 12, "score": 0.046244, "snippet": "Draw three cards, discard two, and play one. Cost: 2 to 4 Supply, as shown to right Draw three cards. You can draw either from the world deck or from the discard pile of the region that your pawn is in. Then, discard two cards. If your pawn is in the Cradle, discard to the top of the Provinces disca", "headingPath": "seaRch · visions!", "sharpsignalDocId": 434}, {"page": 32, "score": 0.046154, "snippet": "Draw three cards, unless... Whether you're drawing from your region's discard pile or the world deck, draw three cards. Stop drawing if you draw a Vision from the deck or if there are no cards left to draw, but don't stop drawing if you draw a Vision from a discard pile! You can always play a card a", "headingPath": "dRawing, Playing, and discaRding caRds · using caRds", "sharpsignalDocId": 434}, {"page": 5, "score": 0.045928, "snippet": "If you're learning Oath before getting together with your group, there are a few ways you can do this, depending on how you like to learn. If you like learning in a gradual way with lots of examples, read this book. If you mostly play games like Catan and Pandemic , this playbook is for you. If you ", "headingPath": "earning Oath to Teach Later? · tiPs and exPectations", "sharpsignalDocId": 434}, {"page": 10, "score": 0.044246, "snippet": "T T he Broad Strokes of Play On your turn, you'll do three phases-Wake, Act, then Rest. Once you're done, the next player in clockwise order takes their turn. Once each player has taken a turn, the round ends. Keep playing like this until someone wins or you finish the eighth round! Only Exiles do m", "headingPath": "The Exiles have a second path to victory-becoming a Visionary. · the wake Phase · the act Phase", "sharpsignalDocId": 434}, {"page": 29, "score": 0.039871, "snippet": "Don't worry too much about rules mistakes your first time. Oath is a deep, intricate game, so you will get a few things wrong. Unless your group is competitive, we suggest you make rulings that feel right and then find out the correct ruling after you play. If it's about a component, read 'Key Compo", "headingPath": "At the end of the eighth round, the game always ends. · If you do need a precise answer about the rules, read the Law of Oath.", "sharpsignalDocId": 434}, {"page": 30, "score": 0.037959, "snippet": "To set up for games beyond your first, use the Law of Oath (page 2). A few things are different from the setup for your first game. Here are the notable differences: Players can choose to start as Citizens, as long as your game ends with boards on their Citizen side. Citizens do not get a relic duri", "headingPath": "etup for Later Games", "sharpsignalDocId": 434}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 10, "quote": null, "headingPath": "The Exiles have a second path to victory-becoming a Visionary. · the wake Phase · the act Phase", "sharpsignalDocId": 434}, {"page": 4, "quote": null, "headingPath": "", "sharpsignalDocId": 434}, {"page": 4, "quote": null, "headingPath": "", "sharpsignalDocId": 434}, {"page": 20, "quote": null, "headingPath": "traVel to the other cradle site. I spend", "sharpsignalDocId": 434}, {"page": 12, "quote": null, "headingPath": "seaRch · visions!", "sharpsignalDocId": 434}, {"page": 32, "quote": null, "headingPath": "dRawing, Playing, and discaRding caRds · using caRds", "sharpsignalDocId": 434}, {"page": 28, "quote": null, "headingPath": "", "sharpsignalDocId": 434}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 434 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 434 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 0.89356 of 3138 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 12:30
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 Oath — Rulebook (corpus doc 434) | eaching Oath Right Now? | p.5 | 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 Oath — Rulebook (corpus doc 434) | p.4 | 0.048387 (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 Oath — Rulebook (corpus doc 434) | seaRch · visions! | p.12 | 0.046244 (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 Oath — Rulebook (corpus doc 434) | dRawing, Playing, and discaRding caRds · using caRds | p.32 | 0.046154 (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 Oath — Rulebook (corpus doc 434) | earning Oath to Teach Later? · tiPs and exPectations | p.5 | 0.045928 (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 Oath — Rulebook (corpus doc 434) | The Exiles have a second path to victory-becoming a Visionary. · the wake Phase · the act Phase | p.10 | 0.044246 (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 Oath — Rulebook (corpus doc 434) | At the end of the eighth round, the game always ends. · If you do need a precise answer about the rules, read the Law of Oath. | p.29 | 0.039871 (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 Oath — Rulebook (corpus doc 434) | etup for Later Games | p.30 | 0.037959 (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 80 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 Oath — Rulebook (corpus doc 434) | p.4 | #2 | 0.048387 (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 Oath — Rulebook (corpus doc 434) | The Exiles have a second path to victory-becoming a Visionary. · the wake Phase · the act Phase | p.10 | #6 | 0.044246 (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 |
| #3 | RULEBOOK Oath — Rulebook (corpus doc 434) | dRawing, Playing, and discaRding caRds · using caRds | p.32 | #4 | 0.046154 (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 Oath — Rulebook (corpus doc 434) | traVel to the other cradle site. I spend | p.20 | #11 | 0.025808 (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 Oath — Rulebook (corpus doc 434) | p.4 | #10 | 0.027032 (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 Oath — Rulebook (corpus doc 434) | p.28 | #26 | 0.022113 (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 Oath — Rulebook (corpus doc 434) | eaching Oath Right Now? | p.5 | #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 |
| #8 | RULEBOOK Oath — Rulebook (corpus doc 434) | seaRch · visions! | p.12 | #3 | 0.046244 (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 Oath — Rulebook (corpus doc 434) | The Exiles have a second path to victory-becoming a Visionary. · the wake Phase · the act Phase | p.10 | no quote on the wire |
| [2] | RULEBOOK Oath — Rulebook (corpus doc 434) | p.4 | no quote on the wire | |
| [3] | RULEBOOK Oath — Rulebook (corpus doc 434) | p.4 | no quote on the wire | |
| [4] | RULEBOOK Oath — Rulebook (corpus doc 434) | traVel to the other cradle site. I spend | p.20 | no quote on the wire |
| [5] | RULEBOOK Oath — Rulebook (corpus doc 434) | seaRch · visions! | p.12 | no quote on the wire |
| [6] | RULEBOOK Oath — Rulebook (corpus doc 434) | dRawing, Playing, and discaRding caRds · using caRds | p.32 | no quote on the wire |
| [7] | RULEBOOK Oath — Rulebook (corpus doc 434) | p.28 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 82 ms · first delta 4936 ms · total 9990 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 82 ms · ask 9906 ms · gateway work 9990 ms · total 9990 ms
- tokens in (the prompt the answerer read)
- 4201
- tokens out (what the answerer generated)
- 1024
- tok/sec
- 204.4 tok/sec — 1024 output tokens in 5.011 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 34s 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 364), 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.