You asked
How do I setup the game?
Answered counted as answeredAsked with: Imperium: Horizonsbg-367518-en-1e
The table has its answer — dice up.
🔧 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 160 ms · ask 9408 ms · total 9571 ms
- single-flight (PR-5)
- queued 0 ms · generation 9571 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 13, "score": 0.047883, "snippet": "13 Commons Setup 1. Place the remaining , , , , , and tokens on the table, easily accessible to all players. This is the Supply. 2. Place the Market board in the middle of the table, easily accessible to all players. For a normal game, place it so that the side without icons is showing. If you are p", "headingPath": "", "sharpsignalDocId": 771}, {"page": 3, "score": 0.04612, "snippet": "28 SETUP .....................................................29 HOW TO PLAY .........................................29 CHANGES TO GAMEPLAY DURING SOLO PLAY ...............................30 GAME END ..............................................32 DIFFICULTY LEVELS ...............................3", "headingPath": "", "sharpsignalDocId": 771}, {"page": 33, "score": 0.045541, "snippet": "On the next campaign game you play, start with twice as many Resources as normal (6 , 4 , and 2 ) If playing with the Trade Routes expansion, you will start with 2 instead of 2 . If you win the next game, go back to your normal Resources. If you lose the next game, do not double this bonus. If you e", "headingPath": "", "sharpsignalDocId": 771}, {"page": 5, "score": 0.04526, "snippet": "5 Using this Rulebook Imperium is a game meant to be played many times. It has a large number of possible game combinations available in each box (especially Horizons) and it can be daunting to learn the rules while also choosing between so many options and reading so many exceptions to the rules. T", "headingPath": "", "sharpsignalDocId": 771}, {"page": 29, "score": 0.044136, "snippet": "Check difficulty levels on page 32 for what these are. If playing with the Trade Routes expansion, place the Merchants card besides their State card to indicate its Merchant state. You will also need the Trade Routes table (see back page). All symbols and text on the Bot’s Merchant Power card (inclu", "headingPath": "", "sharpsignalDocId": 771}, {"page": 33, "score": 0.042263, "snippet": "33 Overlord The same as Sovereign level, but during Bot setup, add Slot marker 6 to the right of Slot marker 5. During setup and during the Bot’s turn, place a card face down below this Slot marker. If you roll a 6 at the start of Bot’s turn, place the die on the card in Slot 6 as normal, but do not", "headingPath": "", "sharpsignalDocId": 771}, {"page": 29, "score": 0.03125, "snippet": "29 Setup 1. Place Slot markers 1–5 below the cards in the Market, so that each card has one marker below it. The markers should be placed in ascending order, from left to right. Slot marker 6 can be returned to the box unless playing in Supreme Ruler mode (see page 33). 2. Choose a nation for the Bo", "headingPath": "", "sharpsignalDocId": 771}, {"page": 11, "score": 0.030303, "snippet": "11 5. Place a State card with the side up underneath your Player organiser. If you’re playing as the Atlanteans, instead place your State card with the side up. If you’re playing as the Cultists, place your State card with the side up, on top of your custom State card that has the Corrupted side up.", "headingPath": "", "sharpsignalDocId": 771}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 13, "quote": null, "headingPath": "", "sharpsignalDocId": 771}, {"page": 29, "quote": null, "headingPath": "", "sharpsignalDocId": 771}, {"page": 25, "quote": null, "headingPath": "", "sharpsignalDocId": 771}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 771 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 771 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 0.87599 of 3282 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 3, 2026 21:39 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 Imperium: Horizons — Rulebook (corpus doc 771) | p.13 | 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 | |
| #2 | RULEBOOK Imperium: Horizons — Rulebook (corpus doc 771) | p.3 | 0.04612 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.33 | 0.045541 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.5 | 0.04526 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.29 | 0.044136 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.33 | 0.042263 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.29 | 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 | |
| #8 | RULEBOOK Imperium: Horizons — Rulebook (corpus doc 771) | 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 |
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 80 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 Imperium: Horizons — Rulebook (corpus doc 771) | p.13 | #1 | 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 Imperium: Horizons — Rulebook (corpus doc 771) | p.25 | #16 | 0.025894 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.29 | #7 | 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 | |
| #4 | RULEBOOK Imperium: Horizons — Rulebook (corpus doc 771) | p.29 | #5 | 0.044136 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.24 | #13 | 0.026547 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.33 | #6 | 0.042263 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.24 | #9 | 0.02879 (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 | |
| #8 | RULEBOOK Imperium: Horizons — Rulebook (corpus doc 771) | p.5 | #4 | 0.04526 (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 Imperium: Horizons — Rulebook (corpus doc 771) | p.13 | no quote on the wire | |
| [2] | RULEBOOK Imperium: Horizons — Rulebook (corpus doc 771) | p.29 | no quote on the wire | |
| [3] | RULEBOOK Imperium: Horizons — Rulebook (corpus doc 771) | p.25 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 160 ms · first delta 4317 ms · total 9571 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 160 ms · ask 9408 ms · gateway work 9571 ms · total 9571 ms
- tokens in (the prompt the answerer read)
- 4564
- tokens out (what the answerer generated)
- 1024
- tok/sec
- 198.8 tok/sec — 1024 output tokens in 5.151 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 58s ago)
- answerer host (measured by rulesage)
- reachable (for 22h, checked 4s 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
- NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
- pattern that matched
- SETUP — "setup" / "set up"
- matched words (in the normalized question)
-
setup
errata registry — what the gate above had to match against
this game registers NO errata cards (edition 705), 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.