You asked
What does each player take, and what goes in the middle, before we begin?
Answered counted as answeredAsked with: Chaos in the Old Worldbg-43111-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 90 ms · ask 4857 ms · total 4949 ms
- single-flight (PR-5)
- queued 0 ms · generation 4949 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 11, "score": 0.032787, "snippet": "During the Summoning PhaSe , the players summon followers and play Chaos cards to the board's nine regions. In each summoning phase, most players will summon a number of figures and play several cards. In the summoning phase, the players take turns acting, following the standard order (Khorne, Nurgl", "headingPath": "Summoning Phase", "sharpsignalDocId": 347}, {"page": 17, "score": 0.032258, "snippet": "A player may not assign fewer hits to a figure than are necessary to kill it and thereby 'store them up' in order to combine hits with other players. That is, different players may not 'gang up' on the same powerful figure within a region. Excess rolled hits - i.e., those without a legal target are ", "headingPath": "Combat Example: A Three-way Battle · BeGinninG oF Battle anD enD oF Battle eFFectS · Combat Example: Fighting Peasants", "sharpsignalDocId": 347}, {"page": 12, "score": 0.031746, "snippet": "To play a Chaos card, a player simply does the following: Chooses a card from his hand of Chaos cards. Pays the selected card's cost. Places the card on an empty card space on any of the board's nine regions and carries out its effects. To pay a card's cost, the player simply adjusts his power point", "headingPath": "PlayinG chaoS carDS", "sharpsignalDocId": 347}, {"page": 11, "score": 0.03125, "snippet": "During the draW PhaSe , each player draws cards from his own Chaos card deck according to the draw phase instructions on his Power sheet. If a player's deck is ever exhausted, he shuffles his discards to create a fresh deck. Note that each player only ever draws cards from his own Chaos deck, and ne", "headingPath": "The Draw Phase", "sharpsignalDocId": 347}, {"page": 15, "score": 0.030769, "snippet": "In the baTTle PhaSe , the Chaos Powers' followers in each region fight against one another, as well as against Peasant tokens. Battle is carried out region by region in the standard region order (see 'Region Order' on page 25). It occurs in every region where one player is entitled to roll battle di", "headingPath": "The Battle Phase · calculatinG Battle Dice · aSSiGninG hitS", "sharpsignalDocId": 347}, {"page": 19, "score": 0.030303, "snippet": "The corruPTion PhaSe has two steps. In the dominaTion STeP , which takes place first, players score conquest points for dominating the board regions. In the corruPTion STeP , which is second, players place corruption tokens in the regions where they have one or more Cultist followers.", "headingPath": "The Corruption Phase", "sharpsignalDocId": 347}, {"page": 16, "score": 0.029851, "snippet": "Some Chaos cards and upgrade powers give players battle dice to roll at the beginning of the battle phase or - in the case of upgraded Bloodletter figures - 'before other figures roll their dice.' Such battle dice can kill adversary figures before those figures roll their own battle dice. Such casua", "headingPath": "Early Hits", "sharpsignalDocId": 347}, {"page": 9, "score": 0.029412, "snippet": "In the old World PhaSe , a single card is drawn from the top of the Old World deck and its italicized instructions carried out immediately. These actions should be carried out by the player with the lowest Threat (see 'Threat' on page 22). If the card requires any decisions to be made, such as in wh", "headingPath": "The Old World Phase", "sharpsignalDocId": 347}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 8, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 347}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 347 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 347 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 0.90368 of 789 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 12, 2026 21:03
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 Chaos in the Old World — Rulebook (corpus doc 347) | Summoning Phase | p.11 | 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 |
| #2 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | Combat Example: A Three-way Battle · BeGinninG oF Battle anD enD oF Battle eFFectS · Combat Example: Fighting Peasants | p.17 | 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 |
| #3 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | PlayinG chaoS carDS | p.12 | 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 |
| #4 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | The Draw Phase | p.11 | 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 |
| #5 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | The Battle Phase · calculatinG Battle Dice · aSSiGninG hitS | p.15 | 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 |
| #6 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | The Corruption Phase | p.19 | 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)) | 285 |
| #7 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | Early Hits | p.16 | 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 Chaos in the Old World — Rulebook (corpus doc 347) | The Old World Phase | p.9 | 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 58 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 Chaos in the Old World — Rulebook (corpus doc 347) | Summoning Phase | p.11 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #2 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | PlacinG corruPtion tokenS | p.19 | #20 | 0.0125 (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 Chaos in the Old World — Rulebook (corpus doc 347) | Setup | p.8 | #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 |
| #4 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | The Draw Phase | p.11 | #4 | 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 |
| #5 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | calculatinG DoMination | p.19 | #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 |
| #6 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | Combat Example: A Three-way Battle | p.16 | #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 |
| #7 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | The Corruption Phase | p.19 | #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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Chaos in the Old World — Rulebook (corpus doc 347) | Early Hits | p.16 | #7 | 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)) | 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 Chaos in the Old World — Rulebook (corpus doc 347) | Setup | p.8 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 90 ms · first delta 3188 ms · total 4949 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 90 ms · ask 4857 ms · gateway work 4949 ms · total 4949 ms
- tokens in (the prompt the answerer read)
- 3012
- tokens out (what the answerer generated)
- 236
- tok/sec
- 138.3 tok/sec — 236 output tokens in 1.706 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 17s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- BEFORE_FIRST_PLAY — "before the first turn" / "before we begin"
- matched words (in the normalized question)
-
before we begin
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 275), 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.