You asked
How do I setup the game?
Answered counted as answeredAsked with: Atlantis Rising (Second Edition)bg-248490-en-1e
🔧 debug — where this ruling came from
- outcome
- ANSWERED — Answered
- corpus profile
- live
- answerer pin (deploy-frozen, attribution only)
- gemma4:26b think:false 5571076f3d70
- timings
- search 415 ms · ask 8863 ms · total 9289 ms
- single-flight (PR-5)
- queued 0 ms · generation 9289 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048172, "snippet": "8 Place 2 followers of each selected color as well as the volunteers in the supply area of the Wrath of the Gods track. Return any unused player pieces to the box. 9 Place the Cosmic Gate board near the Island board. 10 The player who most recently went swimming becomes the starting player and takes", "headingPath": "introductory game mode", "sharpsignalDocId": 643}, {"page": 4, "score": 0.048131, "snippet": "This setup is for playing with 4 to 7 people. If you'd like to know about the changes to setup for lower player counts, please refer to pages 14 and 15. 1 Set up the island of Atlantis by laying out its tiles as shown. 2 Place the mystic barriers in their plastic stands. Place these, the resources (", "headingPath": "introductory game mode", "sharpsignalDocId": 643}, {"page": 14, "score": 0.047379, "snippet": "During setup, shuffle and create a stack of the unused councilor boards, called the councilor stack. Each round the starting player will receive the Hologram. No changes to setup or gameplay. For a three-player game, adjust the setup and gameplay as follows: during setup, each player receives four A", "headingPath": "The Hologram · 4-7 players · 3 players · 2 players", "sharpsignalDocId": 643}, {"page": 14, "score": 0.047371, "snippet": "For a one-player game, vary the setup and gameplay as follows: During setup, take five Atlanteans of one color (4 followers and 1 Leader), and set another three into the Atlantean supply. You may control up to seven total Atlantean followers. Take the Hologram and Automaton pieces and place them wit", "headingPath": "Solo Variant", "sharpsignalDocId": 643}, {"page": 15, "score": 0.030886, "snippet": "The Automaton is a special worker that counts as one of your Atlanteans, but not as a follower. Unlike other Atlanteans, it does not take actions, and thus never collects resources, mystic energy, or library cards. Instead, it has the special ability of granting a +2 to the die rolls of other Atlant", "headingPath": "The Automaton · ADjuStinG Difficulty · Original design: · Revised edition design: · Development and production: · Illustration: · …", "sharpsignalDocId": 643}, {"page": 11, "score": 0.030769, "snippet": "To build a gate component, players must have placed one or more Atlanteans on one of the spaces in the center of the Cosmic Gate board . One space on this board, and several on completed components, are marked with a '5+'. This means these spaces are only available when playing with 5 or more player", "headingPath": "Build Components", "sharpsignalDocId": 643}, {"page": 6, "score": 0.030303, "snippet": "6 6 To win the game, collect resources and build all the Cosmic Gate components in the Blueprint before all 37 island tiles flood. The game is played over a series of rounds, with each round separated into 4 phases, as outlined below. PLACE ATLANTEANS SUFFER MISFORTUNES TAKE ACTIONS ENDURE THE WRATH", "headingPath": "introductory game mode · Object of P la y · 1. Place Atlanteans · 2. Suffer misfortunes", "sharpsignalDocId": 643}, {"page": 7, "score": 0.029851, "snippet": "The gods are furious with the people of Atlantis, who have embraced technology and mysticism over worship of the divine. But the futile resistance of these mortals, who labor to save themselves, even as their home sinks beneath the waves, merely serves to enrage the gods further. In the Endure the W", "headingPath": "4. Endure the wrath of the gods", "sharpsignalDocId": 643}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "introductory game mode", "sharpsignalDocId": 643}, {"page": 14, "quote": null, "headingPath": "The Hologram · 4-7 players · 3 players · 2 players", "sharpsignalDocId": 643}, {"page": 14, "quote": null, "headingPath": "Solo Variant", "sharpsignalDocId": 643}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 643 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 643 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)
- debug row retained until
- Nov 10, 2026 10:30
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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode | p.4 | 0.048172 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode | p.4 | 0.048131 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | The Hologram · 4-7 players · 3 players · 2 players | p.14 | 0.047379 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | Solo Variant | p.14 | 0.047371 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | The Automaton · ADjuStinG Difficulty · Original design: · Revised edition design: · Development and production: · Illustration: · … | p.15 | 0.030886 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | Build Components | p.11 | 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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode · Object of P la y · 1. Place Atlanteans · 2. Suffer misfortunes | p.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)) | 300 |
| #8 | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | 4. Endure the wrath of the gods | p.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)) | 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 23 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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | The Hologram · 4-7 players · 3 players · 2 players | p.14 | #3 | 0.047379 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | Solo Variant | p.14 | #4 | 0.047371 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | The Automaton · ADjuStinG Difficulty · Original design: · Revised edition design: · Development and production: · Illustration: · … | p.15 | #5 | 0.030886 (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 |
| #4 | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | p.1 | #23 | 0.012048 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | Elf Creek would like to thank our families and our lead playtesters and volunteers: · Q: How do effects like Ancient Atlas, Earthquake, and the Explorer's special ability interact? · Q: How do the cards Cipher of Expertise and Enigma of Alacrity work when a Leader is placed on a double space? · Q. Spirit Seal and Soul Terraformer both refer to followers, rather than Atlanteans. Can I use volunteers or Leaders on these worker locations? · Q: Can I use the Prediction Module to remove misfortune cards from the draw deck and the discard pile? · Q: How does the Priest work at the Cities? · … | p.16 | #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 |
| #6 | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode · Object of P la y · 1. Place Atlanteans · 2. Suffer misfortunes | p.6 | #7 | 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 |
| #7 | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode | p.4 | #1 | 0.048172 (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 |
| #8 | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode | p.4 | #2 | 0.048131 (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 Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | introductory game mode | p.4 | no quote on the wire |
| [2] | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | The Hologram · 4-7 players · 3 players · 2 players | p.14 | no quote on the wire |
| [3] | RULEBOOK Atlantis Rising (Second Edition) — Rulebook (corpus doc 643) | Solo Variant | p.14 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 415 ms · first delta 4429 ms · total 9289 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 415 ms · ask 8863 ms · gateway work 9289 ms · total 9289 ms
- tokens in (the prompt the answerer read)
- 2880
- tokens out (what the answerer generated)
- 634
- tok/sec
- 132.0 tok/sec — 634 output tokens in 4.802 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 28s 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
- 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 576), 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.