You asked
How do I play?
Answered counted as answeredAsked with: Faiyumbg-318983-en-1e
So says the rulebook. So plays the table.
🔧 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 188 ms · ask 2215 ms · total 2406 ms
- single-flight (PR-5)
- queued 0 ms · generation 2406 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 5, "score": 0.048652, "snippet": "In Faiyum , unlike in deck-building games, you do not have the familiar personal draw pile. Instead, at the start of the game, you have all your cards in hand and can play them one after another. After you play a card, place it face up on top of your discard stack. Play a card from your hand by plac", "headingPath": "a) Play a card from your hand", "sharpsignalDocId": 1029}, {"page": 5, "score": 0.04728, "snippet": "The general rules of Faiyum are easy, but the game as a whole is complex thanks to the wide spectrum of different actions on the cards. These actions are all explained in detail in the separate glossary, so good news! After learning the general rules and discovering the actions of your starting card", "headingPath": "How to play", "sharpsignalDocId": 1029}, {"page": 8, "score": 0.046898, "snippet": "When you are playing solo, the pharaoh commands you to take charge of the whole urbanization yourself. You can play single games in which you attempt to beat your personal high score. You can also accept the pharaoh's challenge and play a campaign in which you try to fulfill different goals and unlo", "headingPath": "The solo game · Game preparation · How to play · The challenge of the pharaoh · Starting goal", "sharpsignalDocId": 1029}, {"page": 6, "score": 0.046875, "snippet": "Example: Chris plays a harvest action and places a worker on the undeveloped resource space to harvest a grape and remove the crocodile to gain $1 . Nicole plays a build action and places a settlement on the crocodile-free resource space . As that space is already directly connected to the building ", "headingPath": "a) Play a card from your hand", "sharpsignalDocId": 1029}, {"page": 2, "score": 0.046671, "snippet": "Place the game board on the table. Place a settlement on the red space and a road on the dam between the two peninsulas. A Place a crocodile on every wheat (yellow) space and grape (purple) space. B J Everybody chooses a color and takes the matching colored starting cards , reputation disc , and '50", "headingPath": "Game Set-up · Example for 4 players", "sharpsignalDocId": 1029}, {"page": 5, "score": 0.045009, "snippet": "'YES, Ronald, you can pay a single action with 2 or more roses, and each rose can then replace any other required resource because they are WILD!' The cards offer four types of actions: harvest actions, build actions, commerce actions, and 'other' actions. Resources generally come from cards that of", "headingPath": "a) Play a card from your hand", "sharpsignalDocId": 1029}, {"page": 4, "score": 0.045002, "snippet": "For games with 2 to 5 players, we already explained the game preparation on the previous pages and will explain all rules on the following pages. When playing the solo game, you need to make only a few changes during game set-up and while playing the game. You will find these changes on the final pa", "headingPath": "Playing with 2 to 5 players vs. solo games", "sharpsignalDocId": 1029}, {"page": 4, "score": 0.029572, "snippet": "The game board shows a map of Faiyum, a card market, and a reputation track. The channel divides Faiyum into two separate peninsulas connected only by the dam . Also, the peninsulas are surrounded by the lake . Spaces on a peninsula can be adjacent to other spaces on the same peninsula, but spaces o", "headingPath": "The game board · The cards", "sharpsignalDocId": 1029}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 5, "quote": null, "headingPath": "a) Play a card from your hand", "sharpsignalDocId": 1029}, {"page": 5, "quote": null, "headingPath": "How to play", "sharpsignalDocId": 1029}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1029 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1029 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 0.91416 of 699 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row recorded
- Sep 7, 2026 02:58 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 Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.5 | 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 Faiyum — Rulebook (corpus doc 1029) | How to play | p.5 | 0.04728 (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 Faiyum — Rulebook (corpus doc 1029) | The solo game · Game preparation · How to play · The challenge of the pharaoh · Starting goal | p.8 | 0.046898 (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 Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.6 | 0.046875 (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 Faiyum — Rulebook (corpus doc 1029) | Game Set-up · Example for 4 players | p.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)) | 300 |
| #6 | RULEBOOK Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.5 | 0.045009 (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 Faiyum — Rulebook (corpus doc 1029) | Playing with 2 to 5 players vs. solo games | p.4 | 0.045002 (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 Faiyum — Rulebook (corpus doc 1029) | The game board · The cards | p.4 | 0.029572 (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 18 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 Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.5 | #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 |
| #2 | RULEBOOK Faiyum — Rulebook (corpus doc 1029) | The solo game · Game preparation · How to play · The challenge of the pharaoh · Starting goal | p.8 | #3 | 0.046898 (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 Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.6 | #4 | 0.046875 (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 |
| #4 | RULEBOOK Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.5 | #6 | 0.045009 (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 Faiyum — Rulebook (corpus doc 1029) | Playing with 2 to 5 players vs. solo games | p.4 | #7 | 0.045002 (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 |
| #6 | RULEBOOK Faiyum — Rulebook (corpus doc 1029) | Game Set-up · Example for 4 players | p.2 | #5 | 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 |
| #7 | RULEBOOK Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.5 | #15 | 0.026334 (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 Faiyum — Rulebook (corpus doc 1029) | How to play | p.5 | #2 | 0.04728 (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 Faiyum — Rulebook (corpus doc 1029) | a) Play a card from your hand | p.5 | no quote on the wire |
| [2] | RULEBOOK Faiyum — Rulebook (corpus doc 1029) | How to play | p.5 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 188 ms · first delta 1326 ms · total 2406 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 188 ms · ask 2215 ms · gateway work 2406 ms · total 2406 ms
- tokens in (the prompt the answerer read)
- 3022
- tokens out (what the answerer generated)
- 207
- tok/sec
- 199.4 tok/sec — 207 output tokens in 1.038 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 43s 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
- 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 959), 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.