You asked
How do I play?
Answered counted as answeredAsked with: Wabash Cannonballbg-31730-en-1e
So says the rulebook. So plays the table.
🔧 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 87 ms · ask 9846 ms · total 13471 ms
- single-flight (PR-5)
- queued 3537 ms · generation 9934 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 2, "score": 0.047643, "snippet": "1 2 2 3 Next, one share of the C&O is put up for auction, the player who purchased the B&O stock starts the bidding. The minimum bid is the railroad's current Dividend, $5. Bidding continues clockwise. If a player passes, they may not re-enter the bidding. The money paid for the stock is put in the ", "headingPath": "Initial Auctions · Ending/Winning the game · SEQUENCE OF PLAY SYRACUSE", "sharpsignalDocId": 611}, {"page": 4, "score": 0.046432, "snippet": "Immediately after the first railroad builds track into Chicago and pays out the Chicago Dividends, play is momentarily suspended while the Wabash Railroad opens. Place a black cube in Fort Wayne. Place a black cube on the Income track: $1 if Fort Wayne is not developed or $3 if Fort Wayne is develop", "headingPath": "Wabash Opens · General Dividends", "sharpsignalDocId": 611}, {"page": 1, "score": 0.032787, "snippet": "Bidding continues clockwise. If a player passes, they may not re-enter the bidding. The money paid for the stock is put in the B&O Railroad’s Treasury, next to the Game Board.", "headingPath": "", "sharpsignalDocId": 611}, {"page": 2, "score": 0.032258, "snippet": "2 | 2 5 2 During their turn, a player must make an available Decision on the Decision track and slide the corresponding cube to the next box to the right. If the Tan cube for that Decision is already in the End box, that Decision is not available. 1 | 2 2 | 1 | 2 1 2 28 29 PITTSBURGH 4 6 8 ALTOONA F", "headingPath": "Available Decisions · Expansion", "sharpsignalDocId": 611}, {"page": 1, "score": 0.031746, "snippet": "If a player passes, they may not re-enter the bidding. The money paid for the stock is put in the B&O Railroad’s Treasury, next to the Game Board.", "headingPath": "", "sharpsignalDocId": 611}, {"page": 1, "score": 0.030769, "snippet": "1 GAME PARTS: 1 Game Board 1 Railroad Income Display 6 tan Display cubes 20 purple Development cubes 21 red PA cubes 3 PA stocks 23 blue B&O cubes 4 B&O stocks 25 green NYC cubes 5 NYC stocks 27 yellow C&O cubes 6 C&O stocks 12 black Wabash cubes 2 Wabash stocks Paper Money (44 x $1, 24 x $5, 24 x $", "headingPath": "", "sharpsignalDocId": 611}, {"page": 3, "score": 0.029851, "snippet": "1 PENNSYLVANIA 2 RAILROAD TREASURY, STOCK, AND TRACK DEVELOPMENT 38 24 START END The Development Decision allows a player to commercially develop one hex. A hex may only be developed if at least one railroad has built track into that hex, although Detroit is automatically developed after each Genera", "headingPath": "Development 2 2", "sharpsignalDocId": 611}, {"page": 1, "score": 0.029412, "snippet": "Place all 20 purple Development cubes next to the unused Development cubes box on the Game Board. Initial Auctions One share of the PA is put up for auction, the Banker starts the bidding. The minimum bid is the PA Railroad’s current Dividend, $7. Bidding continues clockwise. If a player passes, the", "headingPath": "", "sharpsignalDocId": 611}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 1, "quote": null, "headingPath": "Wabash Cannonball · Setting Up", "sharpsignalDocId": 611}, {"page": 1, "quote": null, "headingPath": "", "sharpsignalDocId": 611}, {"page": 1, "quote": null, "headingPath": "Initial Auctions", "sharpsignalDocId": 611}, {"page": 1, "quote": null, "headingPath": "", "sharpsignalDocId": 611}, {"page": 2, "quote": null, "headingPath": "Initial Auctions · Ending/Winning the game · SEQUENCE OF PLAY SYRACUSE", "sharpsignalDocId": 611}, {"page": 2, "quote": null, "headingPath": "Available Decisions · Expansion", "sharpsignalDocId": 611}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 611 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 611 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 0.88065 of 3033 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 23, 2026 16:13 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 Wabash Cannonball — Rulebook (corpus doc 611) | Initial Auctions · Ending/Winning the game · SEQUENCE OF PLAY SYRACUSE | p.2 | 0.047643 (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 Wabash Cannonball — Rulebook (corpus doc 611) | Wabash Opens · General Dividends | p.4 | 0.046432 (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 Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | 0.032787 (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)) | 175 | |
| #4 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | Available Decisions · Expansion | p.2 | 0.032258 (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 Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | 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)) | 146 | |
| #6 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | 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 Wabash Cannonball — Rulebook (corpus doc 611) | Development 2 2 | p.3 | 0.029851 (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 Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | 0.029412 (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 Wabash Cannonball — Rulebook (corpus doc 611) | Initial Auctions · Ending/Winning the game · SEQUENCE OF PLAY SYRACUSE | p.2 | #1 | 0.047643 (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 Wabash Cannonball — Rulebook (corpus doc 611) | Wabash Cannonball · Setting Up | p.1 | #9 | 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 |
| #3 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | #3 | 0.032787 (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 Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | #13 | 0.013699 (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 | |
| #5 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | Initial Auctions | p.1 | #11 | 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 |
| #6 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | Available Decisions · Expansion | p.2 | #4 | 0.032258 (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 |
| #7 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | #5 | 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 | |
| #8 | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | #8 | 0.029412 (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 |
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 Wabash Cannonball — Rulebook (corpus doc 611) | Wabash Cannonball · Setting Up | p.1 | no quote on the wire |
| [2] | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | no quote on the wire | |
| [3] | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | Initial Auctions | p.1 | no quote on the wire |
| [4] | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | p.1 | no quote on the wire | |
| [5] | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | Initial Auctions · Ending/Winning the game · SEQUENCE OF PLAY SYRACUSE | p.2 | no quote on the wire |
| [6] | RULEBOOK Wabash Cannonball — Rulebook (corpus doc 611) | Available Decisions · Expansion | p.2 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 87 ms · first delta 2217 ms · total 13471 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 3537 ms · retrieval 87 ms · ask 9846 ms · gateway work 9934 ms · total 13471 ms
- tokens in (the prompt the answerer read)
- 2200
- tokens out (what the answerer generated)
- 1024
- tok/sec
- 133.7 tok/sec — 1024 output tokens in 7.659 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 2s ago)
- gateway schema (read from the running child)
- schema head 0042_definer_search_path (live revision not readable by this principal)
- answerer host (measured by rulesage)
- reachable (for 60h, checked 7s 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 543), 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.