You asked
How do I play?
Answered counted as answeredAsked with: Fall of Romebg-260428-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 73 ms · ask 7278 ms · total 7352 ms
- single-flight (PR-5)
- queued 0 ms · generation 7352 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 10, "score": 0.048387, "snippet": "When playing Pandemic: Fall of Rome as a single player, you assume the burden of Emperor and command 3 different roles. Set up the game as normal, with the following changes: { Remove the Mercator Role card and the 'Do ut des' Event card from the game. Th ey are not used in the Solitaire challenge. ", "headingPath": "SOLITAIRE CHALLENGE · Setup · Play · Treasury · Plot", "sharpsignalDocId": 483}, {"page": 8, "score": 0.048139, "snippet": "During any turn, any player may play an Event card. Playing an Event card is not an action. Th e player who plays the Event card decides how to use it. Many Event cards present a standard option as well as a more powerful 'corrupt' option that causes decline. If you choose to do the standard option,", "headingPath": "EVENT CARDS", "sharpsignalDocId": 483}, {"page": 4, "score": 0.047493, "snippet": "Each player turn is divided into 3 steps: Do 4 Actions Draw 2 Player Cards (and resolve Revolts) Invade Cities A ft er doing the Invade Cities step, your turn ends. Th e player on your le ft takes the next turn. Players should freely give each other advice, letting everyone offer opinions and ideas.", "headingPath": "PLAY · DO 4 ACTIONS · March · Sail · Fortify · Recruit Army", "sharpsignalDocId": 483}, {"page": 3, "score": 0.044776, "snippet": "49 Barbarian Cards 7 Reference Cards 100 Barbarian Cubes (20 Anglo-Saxons/Franks, 22 Vandals, 20 Huns, 24 Visigoths, 14 Ostrogoths) 3 Battle Dice 16 Legions 1 Board Give 1 Reference card and 1 random Role card with its matching pawn (top le ft of the Role card) to each player. Return the remaining R", "headingPath": "Resolve Initial Invasion · Prepare Player Components 3 · Prepare Player Deck · Begin Play", "sharpsignalDocId": 483}, {"page": 9, "score": 0.03125, "snippet": "Place your cards faceup in front of you, for all players to see. Only City and Event cards count toward your hand limit. Your Role and Reference cards and any Revolt cards you draw are not part of your hand. Note that an icon on each City card shows how many City cards of that color are in the Playe", "headingPath": "PLAYER CARDS · GAME END · GAME END EXAMPLE", "sharpsignalDocId": 483}, {"page": 12, "score": 0.030769, "snippet": "Each player has a role with special abilities to improve your team's chances. { As an action, add 1 legion to any city with a fort. { As an action, add 1 legion to your city. Add 1 legion to your city. { When you do the Battle action, reduce the number of legions you lose by 1. Remove 2 barbarians f", "headingPath": "ROLES · Consul · Magister Militum · Mercator · Praefectus Classis · Praefectus Fabrum · …", "sharpsignalDocId": 483}, {"page": 6, "score": 0.030303, "snippet": "Flip over, one at a time, as many Barbarian cards from the top of the Barbarian deck as the current invasion rate (indicated by the Invasion Rate track on the board). For each card flipped over, invade 1 city and discard the card to the Barbarian discard pile. Each Barbarian card shows the color of ", "headingPath": "INVADE CITIES · Invading a City", "sharpsignalDocId": 483}, {"page": 5, "score": 0.029514, "snippet": "If there is another player in your city and you both agree to it , you can do one of the following: { Give a City card that matches your city to that player. { Take a City card that matches your city from that player. If the player who gets the card now has more than 7 cards, that player must immedi", "headingPath": "Plot · PLOT EXAMPLE · Forge Alliance · Enlist Barbarians · ENLIST BARBARIANS EXAMPLE", "sharpsignalDocId": 483}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 2, "quote": null, "headingPath": "", "sharpsignalDocId": 483}, {"page": 3, "quote": null, "headingPath": "Resolve Initial Invasion · Prepare Player Components 3 · Prepare Player Deck · Begin Play", "sharpsignalDocId": 483}, {"page": 4, "quote": null, "headingPath": "PLAY · DO 4 ACTIONS · March · Sail · Fortify · Recruit Army", "sharpsignalDocId": 483}, {"page": 8, "quote": null, "headingPath": "EVENT CARDS", "sharpsignalDocId": 483}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 483 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 483 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 0.89188 of 3200 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 06:04
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 Fall of Rome — Rulebook (corpus doc 483) | SOLITAIRE CHALLENGE · Setup · Play · Treasury · Plot | p.10 | 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 |
| #2 | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | EVENT CARDS | p.8 | 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 Fall of Rome — Rulebook (corpus doc 483) | PLAY · DO 4 ACTIONS · March · Sail · Fortify · Recruit Army | p.4 | 0.047493 (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 Fall of Rome — Rulebook (corpus doc 483) | Resolve Initial Invasion · Prepare Player Components 3 · Prepare Player Deck · Begin Play | p.3 | 0.044776 (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 Fall of Rome — Rulebook (corpus doc 483) | PLAYER CARDS · GAME END · GAME END EXAMPLE | p.9 | 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 Fall of Rome — Rulebook (corpus doc 483) | ROLES · Consul · Magister Militum · Mercator · Praefectus Classis · Praefectus Fabrum · … | p.12 | 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 Fall of Rome — Rulebook (corpus doc 483) | INVADE CITIES · Invading a City | p.6 | 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 Fall of Rome — Rulebook (corpus doc 483) | Plot · PLOT EXAMPLE · Forge Alliance · Enlist Barbarians · ENLIST BARBARIANS EXAMPLE | p.5 | 0.029514 (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 25 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 Fall of Rome — Rulebook (corpus doc 483) | EVENT CARDS | p.8 | #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 |
| #2 | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | p.2 | #12 | 0.028718 (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 Fall of Rome — Rulebook (corpus doc 483) | p.12 | #13 | 0.014493 (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 | |
| #4 | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | ROLES · Consul · Magister Militum · Mercator · Praefectus Classis · Praefectus Fabrum · … | p.12 | #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 |
| #5 | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | ROMA CAPUT MUNDI CHALLENGE · Setup · Play | p.10 | #11 | 0.029387 (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 Fall of Rome — Rulebook (corpus doc 483) | SOLITAIRE CHALLENGE · Setup · Play · Treasury · Plot | p.10 | #1 | 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 |
| #7 | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | Resolve Initial Invasion · Prepare Player Components 3 · Prepare Player Deck · Begin Play | p.3 | #4 | 0.044776 (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 Fall of Rome — Rulebook (corpus doc 483) | PLAY · DO 4 ACTIONS · March · Sail · Fortify · Recruit Army | p.4 | #3 | 0.047493 (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 Fall of Rome — Rulebook (corpus doc 483) | p.2 | no quote on the wire | |
| [2] | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | Resolve Initial Invasion · Prepare Player Components 3 · Prepare Player Deck · Begin Play | p.3 | no quote on the wire |
| [3] | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | PLAY · DO 4 ACTIONS · March · Sail · Fortify · Recruit Army | p.4 | no quote on the wire |
| [4] | RULEBOOK Fall of Rome — Rulebook (corpus doc 483) | EVENT CARDS | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 73 ms · first delta 2315 ms · total 7352 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 73 ms · ask 7278 ms · gateway work 7352 ms · total 7352 ms
- tokens in (the prompt the answerer read)
- 4016
- tokens out (what the answerer generated)
- 1019
- tok/sec
- 204.2 tok/sec — 1019 output tokens in 4.989 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 13s 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 414), 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.