You asked
How do I play?
Answered counted as answeredAsked with: Imhotepbg-191862-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 89 ms · ask 5118 ms · total 5208 ms
- single-flight (PR-5)
- queued 0 ms · generation 5208 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 3, "score": 0.048172, "snippet": "Place the 5 site boards in the center of the table as shown in the illustration. All site boards have an A side and a B side . In your first few games, use the A side. You can use the B sides in later games as a variant to the standard game play. So be sure that the A sides of the boards are showing", "headingPath": "GAME PREPARATION", "sharpsignalDocId": 633}, {"page": 4, "score": 0.048131, "snippet": "The game is played over 6 rounds . Each round proceeds as follows: At the start of the round, turn over the top round card . It will indicate which 4 ship tokens are available in this round. Arrange these tokens spaced not too closely together to the left of the site boards. There are ships with var", "headingPath": "COURSE OF PLAY · COURSE OF A ROUND · TURN · Get new stones · Place 1 stone on a ship", "sharpsignalDocId": 633}, {"page": 9, "score": 0.046402, "snippet": "All site boards have an A side and a B side . You should always start playing with just the A sides. Later on, you can try the B sides. You can also play with a mix of A and B sides . Why not try various combinations? The B side works just like the A side, except for the following difference: At the", "headingPath": "THE B SIDES OF THE SITES · B) Market · B) Pyramids · B) Temple", "sharpsignalDocId": 633}, {"page": 2, "score": 0.046239, "snippet": "Each player assumes the role of an Egyptian master builder. You will have 6 rounds to transport your stones to the various sites and to erect monuments in such a way that you earn the most points. Whenever your turn comes up, you will select one of the following 4 action options: Get new stones Plac", "headingPath": "GAME OBJECTIVE · GAME MATERIALS", "sharpsignalDocId": 633}, {"page": 5, "score": 0.045805, "snippet": "At each of the 5 sites, there are different rules for what the stone's owner will receive for each stone delivered, and when they will receive it. The market and the pyramid are assessed immediately . The temple is assessed at the end of each round . The burial chamber and the obelisks are not asses", "headingPath": "Sail 1 ship to a site · Play 1 blue market card · END OF ROUND", "sharpsignalDocId": 633}, {"page": 7, "score": 0.045476, "snippet": "For each stone delivered here, the owner of the stone can immediately take any 1 face-up market card . Explanations of the various market cards can be found on page 12 of this manual. Important: The delivered stones must be returned to the quarry after taking the card. Drawn cards must be placed fac", "headingPath": "A) Market · A) Pyramids", "sharpsignalDocId": 633}, {"page": 5, "score": 0.030769, "snippet": "Return the 4 ships to the pile of other ships . Gather up any market cards still remaining on the market board and place them on the discard pile . All stones already placed on site boards and supply sled tokens stay in place. The next round begins. Turn over the next round card from the pile, get t", "headingPath": "Prepare FOR THE NEXT ROUND · END OF GAME · Final point assessment (scoring) · Obelisks' heading . · The player with the most points is the winner .", "sharpsignalDocId": 633}, {"page": 7, "score": 0.030303, "snippet": "For each stone delivered here, the owner of the stone earns points at the end of the round if the stone is visible from above. Place the stone on the next free space in the temple. Placement of the stones begins from the left, until the first level is full. With 3 and 4 players, all 5 spaces of the ", "headingPath": "A) Temple · A) Burial Chamber", "sharpsignalDocId": 633}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 4, "quote": null, "headingPath": "COURSE OF PLAY · COURSE OF A ROUND · TURN · Get new stones · Place 1 stone on a ship", "sharpsignalDocId": 633}, {"page": 2, "quote": null, "headingPath": "GAME OBJECTIVE · GAME MATERIALS", "sharpsignalDocId": 633}, {"page": 3, "quote": null, "headingPath": "GAME PREPARATION", "sharpsignalDocId": 633}, {"page": 12, "quote": null, "headingPath": "action a single time: · Sail (3x) · Chisel (3x)", "sharpsignalDocId": 633}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 633 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 633 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 0.88767 of 2003 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
- debug row retained until
- Nov 15, 2026 04:51
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 Imhotep — Rulebook (corpus doc 633) | GAME PREPARATION | p.3 | 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 Imhotep — Rulebook (corpus doc 633) | COURSE OF PLAY · COURSE OF A ROUND · TURN · Get new stones · Place 1 stone on a ship | 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 Imhotep — Rulebook (corpus doc 633) | THE B SIDES OF THE SITES · B) Market · B) Pyramids · B) Temple | p.9 | 0.046402 (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 Imhotep — Rulebook (corpus doc 633) | GAME OBJECTIVE · GAME MATERIALS | p.2 | 0.046239 (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 Imhotep — Rulebook (corpus doc 633) | Sail 1 ship to a site · Play 1 blue market card · END OF ROUND | p.5 | 0.045805 (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 Imhotep — Rulebook (corpus doc 633) | A) Market · A) Pyramids | p.7 | 0.045476 (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 Imhotep — Rulebook (corpus doc 633) | Prepare FOR THE NEXT ROUND · END OF GAME · Final point assessment (scoring) · Obelisks' heading . · The player with the most points is the winner . | p.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)) | 300 |
| #8 | RULEBOOK Imhotep — Rulebook (corpus doc 633) | A) Temple · A) Burial Chamber | p.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)) | 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 20 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 Imhotep — Rulebook (corpus doc 633) | THE B SIDES OF THE SITES · B) Market · B) Pyramids · B) Temple | p.9 | #3 | 0.046402 (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 Imhotep — Rulebook (corpus doc 633) | GAME PREPARATION | p.3 | #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 |
| #3 | RULEBOOK Imhotep — Rulebook (corpus doc 633) | COURSE OF PLAY · COURSE OF A ROUND · TURN · Get new stones · Place 1 stone on a ship | 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 |
| #4 | RULEBOOK Imhotep — Rulebook (corpus doc 633) | A) Market · A) Pyramids | p.7 | #6 | 0.045476 (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 Imhotep — Rulebook (corpus doc 633) | A) Temple · A) Burial Chamber | p.7 | #8 | 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 Imhotep — Rulebook (corpus doc 633) | GAME OBJECTIVE · GAME MATERIALS | p.2 | #4 | 0.046239 (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 Imhotep — Rulebook (corpus doc 633) | B) Obelisks · Variant: WRATH OF THE PHARAOH | p.11 | #10 | 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 |
| #8 | RULEBOOK Imhotep — Rulebook (corpus doc 633) | action a single time: · Sail (3x) · Chisel (3x) | p.12 | #9 | 0.030018 (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 |
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 Imhotep — Rulebook (corpus doc 633) | COURSE OF PLAY · COURSE OF A ROUND · TURN · Get new stones · Place 1 stone on a ship | p.4 | no quote on the wire |
| [2] | RULEBOOK Imhotep — Rulebook (corpus doc 633) | GAME OBJECTIVE · GAME MATERIALS | p.2 | no quote on the wire |
| [3] | RULEBOOK Imhotep — Rulebook (corpus doc 633) | GAME PREPARATION | p.3 | no quote on the wire |
| [4] | RULEBOOK Imhotep — Rulebook (corpus doc 633) | action a single time: · Sail (3x) · Chisel (3x) | p.12 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 89 ms · first delta 1969 ms · total 5208 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 89 ms · ask 5118 ms · gateway work 5208 ms · total 5208 ms
- tokens in (the prompt the answerer read)
- 3202
- tokens out (what the answerer generated)
- 659
- tok/sec
- 206.3 tok/sec — 659 output tokens in 3.195 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 17s 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 566), 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.