You asked
How do I play?
Answered counted as answeredAsked with: Carpe Diembg-245934-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 93 ms · ask 4356 ms · total 4450 ms
- single-flight (PR-5)
- queued 0 ms · generation 4450 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.04918, "snippet": "The game is played in four Building phases, each consisting of seven rounds. Each Building phase is followed by a Forum phase. During the Forum phase, all players calculate victory points for the previous Building phase (see page 8, Forum phase). The starting player begins, then the turn moves to th", "headingPath": "PLAYING THE GAME · Movement Rules · Phases 2-4 · 2- and 3-player Games", "sharpsignalDocId": 481}, {"page": 4, "score": 0.047883, "snippet": "The game consists of 4 building phases of 7 rounds each. At the end of each Building phase, a Forum phase occurs, and victory points for that phase will be calculated. Move your patrician to either of the two adjacent blue rectangle spaces, and choose a tile from the attached blueprint to integrate ", "headingPath": "Playing the Game", "sharpsignalDocId": 481}, {"page": 1, "score": 0.045724, "snippet": "An exciting tile-placement game set in ancient Rome. Players: 2-4 Ages: 10+ Playing Time: 45-75 minutes Rome, 1 BC. As influential patricians-members of the founding families-you set out to improve your city district. Ensure your city's prosperity with profitable buildings and beautiful landscapes. ", "headingPath": "INTRODUCTION · GAME CONTENTS", "sharpsignalDocId": 481}, {"page": 2, "score": 0.031746, "snippet": "Before the first game, carefully punch all pieces out of the component boards. Place the game board in the center of the table. 4 random frame parts. Assemble them into a square frame and place them in front of you. 1 city district board. Place it inside the frame so that the handle of the shovel in", "headingPath": "GAME SETUP · Each player takes: · 3 players · 4 players · Game Setup", "sharpsignalDocId": 481}, {"page": 8, "score": 0.03125, "snippet": "The game consists of four building phases of seven rounds each. At the end of seven rounds, all 28 building tiles will have been chosen or discarded. Each Building phase is followed by a Forum phase. Players visit the forum in order of position on the prestige bar. The player who has progressed fart", "headingPath": "2. F R M P ASE", "sharpsignalDocId": 481}, {"page": 3, "score": 0.030769, "snippet": "Example: 3-player Board Setup Fountain Cards Victory Point Cards Goods Coins Bread Tokens City District Board Starting Player Token Shuffle the 24 fountain cards and place them in a face-down pile next to the game board. Sort the 66 victory point cards into five piles according to their point value.", "headingPath": "Each player takes: · 2 players · 3 players · 4 players", "sharpsignalDocId": 481}, {"page": 11, "score": 0.030303, "snippet": "After all players have completed the fourth Forum phase, the game ends. Using the images in the bottom black rows of the resource board, all players calculate their final victory points. The player with the most victory points is the winner. If multiple players are tied for most victory points, the ", "headingPath": "END OF THE GAME · Scoring Victory Points · End of the Game", "sharpsignalDocId": 481}, {"page": 12, "score": 0.029828, "snippet": "For example, these four fountain cards read as follows: For each completed merchant dwelling in your district, you receive 2 victory points. For each completed garden in your district, you receive 2 victory points. For each market in your district, you receive 2 victory points. For each completed vi", "headingPath": "End of the Game", "sharpsignalDocId": 481}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "Playing the Game", "sharpsignalDocId": 481}, {"page": 4, "quote": null, "headingPath": "PLAYING THE GAME · Movement Rules · Phases 2-4 · 2- and 3-player Games", "sharpsignalDocId": 481}, {"page": 6, "quote": null, "headingPath": "Dwellings · Merchant (yellow roof) · Granary (brown roof) · Administration (gray roof) · Dwellings:", "sharpsignalDocId": 481}, {"page": 8, "quote": null, "headingPath": "2. F R M P ASE", "sharpsignalDocId": 481}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 481 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 481 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 0.90796 of 1934 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 10:51
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 Carpe Diem — Rulebook (corpus doc 481) | PLAYING THE GAME · Movement Rules · Phases 2-4 · 2- and 3-player Games | p.4 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | Playing the Game | p.4 | 0.047883 (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 Carpe Diem — Rulebook (corpus doc 481) | INTRODUCTION · GAME CONTENTS | p.1 | 0.045724 (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 Carpe Diem — Rulebook (corpus doc 481) | GAME SETUP · Each player takes: · 3 players · 4 players · Game Setup | p.2 | 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 |
| #5 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | 2. F R M P ASE | p.8 | 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 |
| #6 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | Each player takes: · 2 players · 3 players · 4 players | p.3 | 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 |
| #7 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | END OF THE GAME · Scoring Victory Points · End of the Game | p.11 | 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 |
| #8 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | End of the Game | p.12 | 0.029828 (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 14 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 Carpe Diem — Rulebook (corpus doc 481) | Playing the Game | p.4 | #2 | 0.047883 (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 Carpe Diem — Rulebook (corpus doc 481) | GAME SETUP · Each player takes: · 3 players · 4 players · Game Setup | p.2 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #3 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | Each player takes: · 2 players · 3 players · 4 players | p.3 | #6 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | INTRODUCTION · GAME CONTENTS | p.1 | #3 | 0.045724 (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 Carpe Diem — Rulebook (corpus doc 481) | Dwellings · Merchant (yellow roof) · Granary (brown roof) · Administration (gray roof) · Dwellings: | p.6 | #11 | 0.014286 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #6 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | Craftsman (green roof) · Villas · Markets, Bakeries, and Fountains · Market · Bakery · Fountain · … | p.7 | #12 | 0.014085 (below 0.016, the low end of the measured band — a weak fuse (that band was taken on two-arm asks; only its low end, one arm's #1 vote, carries over to a 3-arm one)) | vector | the re-ranker chose it |
| #7 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | 2. F R M P ASE | p.8 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | PLAYING THE GAME · Movement Rules · Phases 2-4 · 2- and 3-player Games | p.4 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 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 Carpe Diem — Rulebook (corpus doc 481) | Playing the Game | p.4 | no quote on the wire |
| [2] | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | PLAYING THE GAME · Movement Rules · Phases 2-4 · 2- and 3-player Games | p.4 | no quote on the wire |
| [3] | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | Dwellings · Merchant (yellow roof) · Granary (brown roof) · Administration (gray roof) · Dwellings: | p.6 | no quote on the wire |
| [4] | RULEBOOK Carpe Diem — Rulebook (corpus doc 481) | 2. F R M P ASE | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 93 ms · first delta 1613 ms · total 4450 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 93 ms · ask 4356 ms · gateway work 4450 ms · total 4450 ms
- tokens in (the prompt the answerer read)
- 3687
- tokens out (what the answerer generated)
- 568
- tok/sec
- 204.4 tok/sec — 568 output tokens in 2.779 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 16s 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 412), 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.