You asked
How do I play?
Answered counted as answeredAsked with: Nucleumbg-396790-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 91 ms · ask 4446 ms · total 4540 ms
- single-flight (PR-5)
- queued 0 ms · generation 4540 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 8, "score": 0.04918, "snippet": "You are an industrialist trying to succeed during the economic and technological boom of 19th-century Saxony, fueled by the invention and spread of the Nucleum (what-in another timeline-people of another century would call a nuclear reactor) and its immense powergenerating capabilities. You will str", "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}, {"page": 10, "score": 0.046671, "snippet": "(see ' Actions explained' on page [12] to learn more about actions.) When playing a Special Directive tile (your Starting Action tile with a black background and no railway tracks on the back), you may choose and perform exactly one of the 5 main actions (Urbanize/Industrialize/Develop/Contract/Ener", "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}, {"page": 4, "score": 0.046432, "snippet": "Place the main board in the center of the table with the side matching the number of players facing up, and place the side board next to the main board. Place the Coal Import Wagon tiles with the side showing '-1 Thaler' facing up on the indicated spots of the two coal production areas. Note, when p", "headingPath": "MAIN BOARD", "sharpsignalDocId": 304}, {"page": 14, "score": 0.045743, "snippet": "This action allows you to collect Contracts. Take one Silver or Gold Contract from the offer, and place it on any empty Contract space on the right side of your player board, then receive the corresponding reward shown on that Contract space. If the Action tile shows icon, receive the shown reward t", "headingPath": "CONTRACT", "sharpsignalDocId": 304}, {"page": 20, "score": 0.045055, "snippet": "Retrieve all tiles from the top of your player board (not from the map), and return them face up to your tile pool. These Action tiles are now available for you to use again. TIP: DO NOT BE AFRAID TO TAKE A RECHARGE WITH 0 ACHIEVEMENT TOKENS; AN EXTRA WORKER AND SOME MONEY CAN SERIOUSLY BOOST YOUR E", "headingPath": "RETRIEVING ACTION TILES · ENDGAME CONDITIONS & END OF THE GAME · FINAL SCORING · SCORING MILESTONES · SCORING YOUR ULTIMATE GOAL TECHNOLOGY", "sharpsignalDocId": 304}, {"page": 6, "score": 0.032258, "snippet": "Each player takes: a player board (placing it in the middle of your player area), a player aid, VP token (100/200) and 4 Thaler from the supply. Choose a color, and take all the components in that specific color: 3 Income markers, placing one on the first space of each income track (so that the star", "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}, {"page": 9, "score": 0.029851, "snippet": "The main board shows cities which have a color (green, white, orange, purple, and the multicolored Praha, which is a special case) and a name. In these cities, you will find urban sites (black squares), mining sites (black hexagons), turbine spaces (black circles), and power plants . On the urban si", "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}, {"page": 10, "score": 0.029514, "snippet": "EXAMPLE: Red has three networks: one containing Leipzig and Grimma-but not Freiberg and Riesa (since those links only have Yellow's Workers present) and not Chemnitz (since a gap separates Grimma from Chemnitz). Chemnitz forms a network of its own (because of the presence of the red Worker), despite", "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 8, "quote": null, "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}, {"page": 10, "quote": null, "headingPath": "PLAYER BOARD", "sharpsignalDocId": 304}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 304 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 304 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 0.94480 of 1250 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 13, 2026 20:48
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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.8 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | 300 |
| #2 | RULEBOOK Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.10 | 0.046671 (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 Nucleum — Rulebook (corpus doc 304) | MAIN BOARD | 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 |
| #4 | RULEBOOK Nucleum — Rulebook (corpus doc 304) | CONTRACT | p.14 | 0.045743 (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 Nucleum — Rulebook (corpus doc 304) | RETRIEVING ACTION TILES · ENDGAME CONDITIONS & END OF THE GAME · FINAL SCORING · SCORING MILESTONES · SCORING YOUR ULTIMATE GOAL TECHNOLOGY | p.20 | 0.045055 (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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.6 | 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 |
| #7 | RULEBOOK Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.9 | 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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.10 | 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 45 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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.10 | #2 | 0.046671 (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 Nucleum — Rulebook (corpus doc 304) | MAIN BOARD | p.5 | #10 | 0.029206 (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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.8 | #1 | 0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.9 | #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 |
| #5 | RULEBOOK Nucleum — Rulebook (corpus doc 304) | URBANIZE | p.12 | #28 | 0.011494 (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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.9 | #24 | 0.012195 (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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.6 | #6 | 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 |
| #8 | RULEBOOK Nucleum — Rulebook (corpus doc 304) | MAIN BOARD | p.4 | #3 | 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)) | 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 Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.8 | no quote on the wire |
| [2] | RULEBOOK Nucleum — Rulebook (corpus doc 304) | PLAYER BOARD | p.10 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 91 ms · first delta 2771 ms · total 4540 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 91 ms · ask 4446 ms · gateway work 4540 ms · total 4540 ms
- tokens in (the prompt the answerer read)
- 4140
- tokens out (what the answerer generated)
- 342
- tok/sec
- 198.8 tok/sec — 342 output tokens in 1.720 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 5s 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 232), 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.