You asked
How do I play?
Answered counted as answeredAsked with: Blood on the Clocktowerbg-240980-en-1e
Rule found, game on.
🔧 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 156 ms · ask 5423 ms · total 5581 ms
- single-flight (PR-5)
- queued 0 ms · generation 5581 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 12, "score": 0.046751, "snippet": "Likewise, we recommend you run a game or two with five to ten players to get the hang of things, then try your hand at larger games. 4. PREPARE THE TOWN SQUARE. Put the Town Square board on the floor in the center of the chairs. Put one life token per player on the Town Square matching their seating", "headingPath": "SETUP", "sharpsignalDocId": 159}, {"page": 32, "score": 0.043115, "snippet": "If you let the players make their own choices, they may not be the best choices, but they own them. Dealing with negative behavior is something you may have to do sooner or later. As is the case with all social gatherings, sometimes a player will speak in a disrespectful tone to another player. BLOO", "headingPath": "MAKING THINGS FUN", "sharpsignalDocId": 159}, {"page": 21, "score": 0.042496, "snippet": "W ELCOME TO THE NITTY-GRITTY ...and beyond. You don't need to read further until you've run a game or two or until you run into a thorny rules question. If you have read the previous chapters in this rulebook and the TROUBLE BREWING character almanac but would like a little practice before running y", "headingPath": "DOES THE GAME ALWAYS END WHEN THE", "sharpsignalDocId": 159}, {"page": 39, "score": 0.042068, "snippet": "T HE MORE, THE MERRIER. The larger your CLOCKTOWER group, the more fun everyone will have, and the more varied opponents and allies that everyone will get to play with. Search for local groups on social media if you need more players for your games or want to participate in games that others run. So", "headingPath": "GROWING YOUR GROUP", "sharpsignalDocId": 159}, {"page": 16, "score": 0.041647, "snippet": "D URING THE DAY PHASE, players talk to each other. They may scheme, lie, share information, or stay silent and try to puzzle out who is who. Then, they vote on who will be executed. This is the main part of the game, mostly handled by the players themselves. T O BEGIN, JUST LET THE PLAYERS TALK amon", "headingPath": "THE DAY · DISCUSSION", "sharpsignalDocId": 159}, {"page": 37, "score": 0.04146, "snippet": "A RE YOU READY TO GO FURTHER? This is the final chapter of your personal storytelling saga. It's also the longest one, because it will involve you striking out on your own and having a lifetime of unique games and experiences, many beyond the scope of this rulebook. You've executed a Spy who nominat", "headingPath": "MAKING THINGS FUN", "sharpsignalDocId": 159}, {"page": 5, "score": 0.03125, "snippet": "After running your first game or two, you'll find it handy to read further: THE NITTY-GRITTY (page 19) includes guidelines for interpreting the rules and the characters' abilities as well as a cornucopia of information on the types of characters available. GREAT STORYTELLING (page 27) gives tips and", "headingPath": "CONTENTS", "sharpsignalDocId": 159}, {"page": 31, "score": 0.029911, "snippet": "Even though it goes against the 'You may say whatever you want at any time' rule, stopping good players from using this strategy may be necessary. Most players understand that the game has not really begun until the first night begins, and will not do this. However, if it becomes an issue, either as", "headingPath": "RUNNING THINGS SMOOTHLY", "sharpsignalDocId": 159}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 12, "quote": null, "headingPath": "SETUP", "sharpsignalDocId": 159}, {"page": 12, "quote": null, "headingPath": "SETUP", "sharpsignalDocId": 159}, {"page": 14, "quote": null, "headingPath": "RUNNING THE NIGHT", "sharpsignalDocId": 159}, {"page": 15, "quote": null, "headingPath": "HOW DO ABILITIES WORK?", "sharpsignalDocId": 159}, {"page": 16, "quote": null, "headingPath": "THE DAY · DISCUSSION", "sharpsignalDocId": 159}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 159 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 159 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 0.90691 of 1504 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Aug 27, 2026 02:22 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 Blood on the Clocktower — Rulebook (corpus doc 159) | SETUP | p.12 | 0.046751 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | MAKING THINGS FUN | p.32 | 0.043115 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | DOES THE GAME ALWAYS END WHEN THE | p.21 | 0.042496 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | GROWING YOUR GROUP | p.39 | 0.042068 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | THE DAY · DISCUSSION | p.16 | 0.041647 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | MAKING THINGS FUN | p.37 | 0.04146 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | CONTENTS | p.5 | 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 |
| #8 | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | RUNNING THINGS SMOOTHLY | p.31 | 0.029911 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | GROWING YOUR GROUP | p.39 | #22 | 0.024615 (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 |
| #2 | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | HOW DO ABILITIES WORK? | p.15 | #28 | 0.022195 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | ADDING TRAVELLERS | p.26 | #15 | 0.027146 (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 |
| #4 | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | RUNNING THINGS SMOOTHLY | p.30 | #30 | 0.021605 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | SETUP | p.12 | #23 | 0.024265 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | THE DAY · DISCUSSION | p.16 | #5 | 0.041647 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | SETUP | p.12 | #1 | 0.046751 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | RUNNING THE NIGHT | p.14 | #17 | 0.027013 (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 Blood on the Clocktower — Rulebook (corpus doc 159) | SETUP | p.12 | no quote on the wire |
| [2] | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | SETUP | p.12 | no quote on the wire |
| [3] | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | RUNNING THE NIGHT | p.14 | no quote on the wire |
| [4] | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | HOW DO ABILITIES WORK? | p.15 | no quote on the wire |
| [5] | RULEBOOK Blood on the Clocktower — Rulebook (corpus doc 159) | THE DAY · DISCUSSION | p.16 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 156 ms · first delta 3260 ms · total 5581 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 156 ms · ask 5423 ms · gateway work 5581 ms · total 5581 ms
- tokens in (the prompt the answerer read)
- 3157
- tokens out (what the answerer generated)
- 455
- tok/sec
- 201.4 tok/sec — 455 output tokens in 2.259 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 33s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 2s 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 81), 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.