You asked
How do I play?
Answered counted as answeredAsked with: Sankoré: The Pride of Mansa Musabg-382518-en-1e
Now you know — make it count.
🔧 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 94 ms · ask 3584 ms · total 9335 ms
- single-flight (PR-5)
- queued 5655 ms · generation 3680 ms
- retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read
- [{"page": 20, "score": 0.04741, "snippet": "Set up the game as per a 2-player game, with the following changes for the Scholar's play area and components: \u0007 Choose a difficulty level and locate the player board that shows your chosen difficulty level on the reverse. Difficulty levels are shown on each player board as follows: Easy Medium Hard", "headingPath": "Setup", "sharpsignalDocId": 1166}, {"page": 9, "score": 0.046486, "snippet": "\u0007 Give each player a player board 18a and a resource board 18b . Place the 2 boards side by side to form a complete player board. \u0007 Determine a first player at random and give them the first player marker 19 . Play will proceed clockwise from the first player. \u0007 Give each player all the components o", "headingPath": "Player Setup", "sharpsignalDocId": 1166}, {"page": 8, "score": 0.046239, "snippet": "\u0007 Place the game board in the centre of the play area. It is divided into 4 areas: Astronomy , Theology , Mathematics , and Law . \u0007 Place the Library board next to the game board 2 . For an introductory game, place the Library board with the 3-shelf side face up (pictured). \u0007 For a more advanced gam", "headingPath": "Common Setup", "sharpsignalDocId": 1166}, {"page": 10, "score": 0.045805, "snippet": "10 Sankoré is played over a series of player turns, starting with the first player and proceeding clockwise around the table. On their turn, a player carries out the following steps: Take up to two DIFFERENT main actions and any number of bonus actions, in any order. Perform end of turn checks. Play", "headingPath": "Starting Draft · GAMEPLAY · SANKORÉ TILES\b · BOOKS", "sharpsignalDocId": 1166}, {"page": 9, "score": 0.03125, "snippet": "\u0007 Place a Student meeple of the matching colour from the general supply on top of each Advanced Class tile on the bottom row of the Advanced Class tile market 29 . \u0007 Place a Book token of each colour into the cloth bag and draw them to randomly assign them to each of these Advanced Class tiles so th", "headingPath": "Starting Draft", "sharpsignalDocId": 1166}, {"page": 20, "score": 0.030769, "snippet": "At the start of phase 3, take all the Student meeples from the solo player board and place them in the cloth bag. Each turn, draw a Student from the cloth bag. The discipline of the Student determines the current discipline for this turn. Place the Student on the leftmost empty space of the phase 3 ", "headingPath": "PHASE 3 LASTS UNTIL THE END OF THE GAME, FOR A MAXIMUM OF 7 TURNS", "sharpsignalDocId": 1166}, {"page": 11, "score": 0.030366, "snippet": "This is the most common action that you will take in Sankoré, allowing you to take area actions , placing your pieces in the various areas of the main board. Choose a Class tile with at least 1 Student meeple in the Student spaces directly below it. Then resolve the following steps: \u0007 Activate Stude", "headingPath": "ACTION: Teach a Class · Historical note · PLAY EXAMPLE: PROMOTE ACTIVATED STUDENT", "sharpsignalDocId": 1166}, {"page": 4, "score": 0.030303, "snippet": "4 Skip ahead to page 8 to start learning the game and refer back to this section as needed. 1× Game board 1× Double-sided Library board 24× Objective cards 24× \u0007 Gold tokens 8× \u0007 Inspiration tokens 32× \u0007 Favour tiles 40× Skill tiles 16× \u0007 Salt tokens 1× \u0007 First Player marker 1× \u0007 Cloth bag", "headingPath": "Theology , Law , Mathematics , and Astronomy · You don't need to read this section first!", "sharpsignalDocId": 1166}]
- citations (raw) — what the answer cited, chosen from a retrieval this page cannot show
- [{"page": 10, "quote": null, "headingPath": "Starting Draft · GAMEPLAY · SANKORÉ TILES\b · BOOKS", "sharpsignalDocId": 1166}, {"page": 20, "quote": null, "headingPath": "Gameplay Overview · SELECTING AREAS / DISCIPLINES \b · PHASE 1 PROCEEDS FOR THE FIRST 4 TURNS · PHASE 2 PROCEEDS FOR 5 TURNS", "sharpsignalDocId": 1166}]
- boost provenance — errata + base rulebook (E2/E3)
-
no registered errata card matched this query; base rulebook doc 1166 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 1166 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 0.92036 of 879 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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Setup | p.20 | 0.04741 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Player Setup | p.9 | 0.046486 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Common Setup | p.8 | 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 |
| #4 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Starting Draft · GAMEPLAY · SANKORÉ TILES · BOOKS | p.10 | 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 |
| #5 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Starting Draft | p.9 | 0.03125 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | PHASE 3 LASTS UNTIL THE END OF THE GAME, FOR A MAXIMUM OF 7 TURNS | p.20 | 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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | ACTION: Teach a Class · Historical note · PLAY EXAMPLE: PROMOTE ACTIVATED STUDENT | p.11 | 0.030366 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Theology , Law , Mathematics , and Astronomy · You don't need to read this section first! | 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)) | 290 |
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 46 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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Common Setup | p.8 | #3 | 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 |
| #2 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Setup | p.20 | #1 | 0.04741 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Gameplay Overview · SELECTING AREAS / DISCIPLINES · PHASE 1 PROCEEDS FOR THE FIRST 4 TURNS · PHASE 2 PROCEEDS FOR 5 TURNS | p.20 | #13 | 0.028175 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | PHASE 3 LASTS UNTIL THE END OF THE GAME, FOR A MAXIMUM OF 7 TURNS | p.20 | #6 | 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 |
| #5 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | ACTION: Teach a Class · Historical note · PLAY EXAMPLE: PROMOTE ACTIVATED STUDENT | p.11 | #7 | 0.030366 (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 |
| #6 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | SCORING EXAMPLE: FINAL SCORING · SOLO MODE · Historical Opponents | p.20 | #18 | 0.025278 (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 |
| #7 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Starting Draft · GAMEPLAY · SANKORÉ TILES · BOOKS | p.10 | #4 | 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)) | vector + full-text + the doc-priority boost arm | the re-ranker chose it |
| #8 | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Player Setup | p.9 | #2 | 0.046486 (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 Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Starting Draft · GAMEPLAY · SANKORÉ TILES · BOOKS | p.10 | no quote on the wire |
| [2] | RULEBOOK Sankoré: The Pride of Mansa Musa — Rulebook (corpus doc 1166) | Gameplay Overview · SELECTING AREAS / DISCIPLINES · PHASE 1 PROCEEDS FOR THE FIRST 4 TURNS · PHASE 2 PROCEEDS FOR 5 TURNS | p.20 | no quote on the wire |
generation — timing and the path taken
- timing split
- retrieval 94 ms · first delta 2334 ms · total 9335 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
- full breakdown
- queued 5655 ms · retrieval 94 ms · ask 3584 ms · gateway work 3680 ms · total 9335 ms
- tokens in (the prompt the answerer read)
- 3148
- tokens out (what the answerer generated)
- 259
- tok/sec
- 201.7 tok/sec — 259 output tokens in 1.284 s of generation
- live seat (read from the running child)
- answering — gemma4:26b think:false · num_ctx 32768 (live-verified 41s ago)
- answerer host (measured by rulesage)
- reachable (for 24h, checked 3s 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 1096), 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.