You asked
How do I play?
Answered counted as answeredAsked with: 18Chesapeakebg-253608-en-1e
The sage rests. The game continues.
🔧 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 6217 ms · total 20500 ms
- single-flight (PR-5)
- queued 14187 ms · generation 6313 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.046964, "snippet": "The map shows cities and terrain that were connected by the first United States railroads. A hex grid is superimposed on the map. Coordinates are printed on the edges for reference purposes. Large open circles represent large cities. Solid black dots represent small cities respectively. Regions beyo", "headingPath": "5. the map", "sharpsignalDocId": 1289}, {"page": 1, "score": 0.045536, "snippet": "1 18 18 rules of play table of contents 1. Introduction 2 1.1 Introduction to These Rules 2 1.2 18xx Overview 2 1.3 18Chesapeake Overview 2 2. Game Components 2 3. Setting Up The Game 3 4. Overview 3 5. The Map 3 6. The Stock Market 4 7. Corporate Entities 4 7.1 Private Companies 4 7.2 Public Compan", "headingPath": "", "sharpsignalDocId": 1289}, {"page": 13, "score": 0.045262, "snippet": "The game end is triggered in one of two ways. The first is when the bank runs out of money ('bank breaks'). If this happens during an operating round, complete the current set of operating rounds and end the game. If the bank breaks during a stock round, complete the stock round and complete one set", "headingPath": "12. ending the game · 13. etiquette", "sharpsignalDocId": 1289}, {"page": 7, "score": 0.032787, "snippet": "A stock round consists of a series of turns, starting with the first player (the holder of the priority deal card) and proceeding clockwise. The game begins with the auction of the private companies. On each turn thereafter, the player may: Sell any number of certificates subject to the constraints ", "headingPath": "10. stock rounds", "sharpsignalDocId": 1289}, {"page": 3, "score": 0.031746, "snippet": "Lay the map board and stock market open on the table near the players. Place the share certificates and trains on the indicated board spaces. Each pile of share certificates should be arranged with the president's certificate on top. Place the money, sorted by denomination, and the track tiles, sort", "headingPath": "3. setting up the game · 4. overview", "sharpsignalDocId": 1289}, {"page": 4, "score": 0.030415, "snippet": "The stock market is used to track the current market value of stock shares for each of the public companies. Commonly, the actions of the companies themselves determines when the value of a company's shares will rise and fall during the game. When a company pays dividends to shareholders, the value ", "headingPath": "5. the map", "sharpsignalDocId": 1289}, {"page": 14, "score": 0.030303, "snippet": "The following rules for a two-player variant are provided for players to become familiar with the game concepts. The game is best with more players. Set up the game as in the multiplayer game. Each player receives $1,200 from the bank. The president's certificate that is associated with P6 Cornelius", "headingPath": "14. two-player variant · 14.1 setup · 14.2 additional rules for company floatation · 14.3 additional rules for non-president purchases · 14.4 additional rule for ending the stock round", "sharpsignalDocId": 1289}, {"page": 2, "score": 0.030118, "snippet": "While this is a relatively simple version of an 18xx game, some parts of these rules are more verbose than other more complex games. These rules have been written and edited to be a good introduction for players that are not familiar with 18xx games. The first use of keywords in these rules are in b", "headingPath": "1.1 introduction to these rules · 1.2 18xx overview", "sharpsignalDocId": 1289}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 3, "quote": null, "headingPath": "3. setting up the game · 4. overview", "sharpsignalDocId": 1289}, {"page": 7, "quote": null, "headingPath": "10. stock rounds", "sharpsignalDocId": 1289}, {"page": 7, "quote": null, "headingPath": "9. private company auction", "sharpsignalDocId": 1289}, {"page": 10, "quote": null, "headingPath": "10.6 ending the stock round", "sharpsignalDocId": 1289}, {"page": 3, "quote": null, "headingPath": "5. the map", "sharpsignalDocId": 1289}, {"page": 13, "quote": null, "headingPath": "12. ending the game · 13. etiquette", "sharpsignalDocId": 1289}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1289 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1289 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 0.91534 of 2764 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 27, 2026 02:47 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 18Chesapeake — Rulebook (corpus doc 1289) | 5. the map | p.3 | 0.046964 (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 18Chesapeake — Rulebook (corpus doc 1289) | p.1 | 0.045536 (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 18Chesapeake — Rulebook (corpus doc 1289) | 12. ending the game · 13. etiquette | p.13 | 0.045262 (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 18Chesapeake — Rulebook (corpus doc 1289) | 10. stock rounds | p.7 | 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)) | 300 |
| #5 | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 3. setting up the game · 4. overview | p.3 | 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 |
| #6 | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 5. the map | p.4 | 0.030415 (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 18Chesapeake — Rulebook (corpus doc 1289) | 14. two-player variant · 14.1 setup · 14.2 additional rules for company floatation · 14.3 additional rules for non-president purchases · 14.4 additional rule for ending the stock round | p.14 | 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 18Chesapeake — Rulebook (corpus doc 1289) | 1.1 introduction to these rules · 1.2 18xx overview | p.2 | 0.030118 (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 37 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 18Chesapeake — Rulebook (corpus doc 1289) | 10. stock rounds | p.7 | #4 | 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 |
| #2 | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 12. ending the game · 13. etiquette | p.13 | #3 | 0.045262 (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 18Chesapeake — Rulebook (corpus doc 1289) | p.1 | #2 | 0.045536 (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 18Chesapeake — Rulebook (corpus doc 1289) | 10.6 ending the stock round | p.10 | #21 | 0.012821 (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 18Chesapeake — Rulebook (corpus doc 1289) | 5. the map | p.3 | #1 | 0.046964 (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 |
| #6 | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 5. the map | p.4 | #6 | 0.030415 (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 18Chesapeake — Rulebook (corpus doc 1289) | 9. private company auction | p.7 | #11 | 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 |
| #8 | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 3. setting up the game · 4. overview | p.3 | #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 |
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 18Chesapeake — Rulebook (corpus doc 1289) | 3. setting up the game · 4. overview | p.3 | no quote on the wire |
| [2] | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 10. stock rounds | p.7 | no quote on the wire |
| [3] | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 9. private company auction | p.7 | no quote on the wire |
| [4] | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 10.6 ending the stock round | p.10 | no quote on the wire |
| [5] | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 5. the map | p.3 | no quote on the wire |
| [6] | RULEBOOK 18Chesapeake — Rulebook (corpus doc 1289) | 12. ending the game · 13. etiquette | p.13 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 93 ms · first delta 2395 ms · total 20500 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 14187 ms · retrieval 93 ms · ask 6217 ms · gateway work 6313 ms · total 20500 ms
- tokens in (the prompt the answerer read)
- 3456
- tokens out (what the answerer generated)
- 773
- tok/sec
- 201.2 tok/sec — 773 output tokens in 3.841 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 56s 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 1s 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 1219), 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.