You asked
How do I play?
Answered counted as answeredAsked with: Atiwabg-362452-en-1e
Question closed. Friendships intact.
🔧 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 248 ms · ask 5238 ms · total 5488 ms
- single-flight (PR-5)
- queued 0 ms · generation 5488 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 4, "score": 0.048652, "snippet": "The game is played over the course of seven rounds . Each round comprises a work phase , in which you take three turns each, followed by a maintenance phase , in which you perform multiple mainly automatic tasks. Beginning with the start player and in clockwise order, you each take one turn at a tim", "headingPath": "Course of Play · The Work Phase · 1.\tWorker Action (Mandatory)", "sharpsignalDocId": 1032}, {"page": 2, "score": 0.048412, "snippet": "1 Unfold the action board and place it in the middle of the play area. 2 Attach one of the two action board extensions to the right of the action board: with 1 and 2 players , use the back side of either extension (showing two people in the bottom right corner) ; with 3 and 4 players , use the front", "headingPath": "- Common Play Area -", "sharpsignalDocId": 1032}, {"page": 11, "score": 0.047619, "snippet": "As mentioned in the setup instructions, the solo game is played with the reverse side of the action board extension and with the red, yellow, and blue workers . Play the game as you would the multiplayer game, taking one turn after the other . There is no artificial opponent; instead, workers placed", "headingPath": "Solo Game", "sharpsignalDocId": 1032}, {"page": 3, "score": 0.046635, "snippet": "10 Take a supply board and place it in front of you, leaving enough room for cards below the board. (Two or three rows worth of room should be plenty.) 11 Take 8 wild animals, 13 trees, 8 fruit, 13 families, and 7 goats and place these tokens on the corresponding spaces of your supply board, as indi", "headingPath": "- Personal Play Area -", "sharpsignalDocId": 1032}, {"page": 11, "score": 0.030769, "snippet": "Place any face-up terrain cards remaining beside the action board (and its extension) in a discard pile . Then draw new terrain cards from the deck and place them face up to the right of the deck, one above each action space. If the draw deck ever runs out, shuffle the discard pile to form a new dra", "headingPath": "Step 7: Preparation · Game End and Scoring", "sharpsignalDocId": 1032}, {"page": 4, "score": 0.030303, "snippet": "| Terrain: Draw a terrain card from the face-down deck. | Exchange: Spend the indicated amount of gold to collect the indicated number of tokens (goats or families) . | | Take the face-up terrain card next to that action space. | Carry out the depicted action multiple | | Tokens: Collect the depicte", "headingPath": "Details:", "sharpsignalDocId": 1032}, {"page": 6, "score": 0.029851, "snippet": "When acquiring a location (not terrain) card, you also get the start player marker . It can change hands multiple times during a round. Only the last player to hold it at the end of the work phase becomes start player, beginning with the maintenance phase of that round. The start player marker chang", "headingPath": "Start Player Marker", "sharpsignalDocId": 1032}, {"page": 5, "score": 0.029412, "snippet": "GE ion s in GE ion GE ion Most action spaces let you collect various tokens: animals, trees, families, and gold. Except for gold, all tokens collected in this game must be placed on cards, of which there are two types: locations and terrain . To acquire a card, you need to take the appropriate actio", "headingPath": "Action Space Tiles · Terrain and Location Cards · Details:", "sharpsignalDocId": 1032}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "Course of Play · The Work Phase · 1.\tWorker Action (Mandatory)", "sharpsignalDocId": 1032}, {"page": 4, "quote": null, "headingPath": "Details:", "sharpsignalDocId": 1032}, {"page": 8, "quote": null, "headingPath": "2.\t Fruit Bat Action (Optional) · Details: · Example: · The Maintenance Phase", "sharpsignalDocId": 1032}, {"page": 11, "quote": null, "headingPath": "Solo Game", "sharpsignalDocId": 1032}, {"page": 11, "quote": null, "headingPath": "Step 7: Preparation · Game End and Scoring", "sharpsignalDocId": 1032}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1032 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1032 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 0.88404 of 2406 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 5, 2026 15:08 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 Atiwa — Rulebook (corpus doc 1032) | Course of Play · The Work Phase · 1. Worker Action (Mandatory) | p.4 | 0.048652 (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 Atiwa — Rulebook (corpus doc 1032) | - Common Play Area - | p.2 | 0.048412 (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 Atiwa — Rulebook (corpus doc 1032) | Solo Game | p.11 | 0.047619 (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 Atiwa — Rulebook (corpus doc 1032) | - Personal Play Area - | p.3 | 0.046635 (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 Atiwa — Rulebook (corpus doc 1032) | Step 7: Preparation · Game End and Scoring | 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 |
| #6 | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Details: | p.4 | 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 |
| #7 | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Start Player Marker | p.6 | 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 Atiwa — Rulebook (corpus doc 1032) | Action Space Tiles · Terrain and Location Cards · Details: | p.5 | 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 27 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 Atiwa — Rulebook (corpus doc 1032) | - Common Play Area - | p.2 | #2 | 0.048412 (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 Atiwa — Rulebook (corpus doc 1032) | Solo Game | p.11 | #3 | 0.047619 (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 Atiwa — Rulebook (corpus doc 1032) | Step 7: Preparation · Game End and Scoring | p.11 | #5 | 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)) | vector + the doc-priority boost arm | the re-ranker chose it |
| #4 | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | 2. Fruit Bat Action (Optional) · Details: · Example: · The Maintenance Phase | p.8 | #9 | 0.029199 (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 |
| #5 | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Details: | p.4 | #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 |
| #6 | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Start Player Marker | p.6 | #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 |
| #7 | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | - Personal Play Area - | p.3 | #4 | 0.046635 (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 Atiwa — Rulebook (corpus doc 1032) | Course of Play · The Work Phase · 1. Worker Action (Mandatory) | p.4 | #1 | 0.048652 (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 Atiwa — Rulebook (corpus doc 1032) | Course of Play · The Work Phase · 1. Worker Action (Mandatory) | p.4 | no quote on the wire |
| [2] | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Details: | p.4 | no quote on the wire |
| [3] | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | 2. Fruit Bat Action (Optional) · Details: · Example: · The Maintenance Phase | p.8 | no quote on the wire |
| [4] | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Solo Game | p.11 | no quote on the wire |
| [5] | RULEBOOK Atiwa — Rulebook (corpus doc 1032) | Step 7: Preparation · Game End and Scoring | p.11 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 248 ms · first delta 1870 ms · total 5488 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 248 ms · ask 5238 ms · gateway work 5488 ms · total 5488 ms
- tokens in (the prompt the answerer read)
- 3350
- tokens out (what the answerer generated)
- 719
- tok/sec
- 202.1 tok/sec — 719 output tokens in 3.558 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 48s ago)
- answerer host (measured by rulesage)
- reachable (for 23h, checked 0s 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 962), 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.