Ruling — Splendor

You asked

How do I play?

Answered counted as answered

Asked with: Splendorbg-148228-en-1e

1. Shuffle each Development card deck separately, then place them facedown in a column in the middle of the table in increasing order from bottom to top (;; ).[1]

2. Reveal 4 cards from each level deck, placing them in a row to the right of their respective decks.[1]

3. Shuffle the Noble tiles and reveal 5.[1]

4. Line the nobles in a row above the cards.[1]

5. Return the remaining Noble tiles to the box; they will not be used during this game.[1]

6. Sort the pieces by color and place them within reach of all players to form the supply, creating 6 distinct stacks.[1]

7. The youngest player takes the First Player marker.[1]

8. The player with the First Player marker takes the first turn.[2]

9. Play then proceeds clockwise.[2]

10. On your turn, you must perform exactly 1 of these four actions: [2]

- Take 3 Gem pieces of different colors (If there are not enough available pieces to take 3 of different colors from the supply, you may take 2 pieces or even 1. You can never take a Gold piece with this action).[2]

- Take 2 Gem pieces of the same color (This action is only available if there are at least 4 pieces available in that color in the supply before you take the 2 pieces. You can never take Gold pieces with this action).[2]

- [Note: The sources mention "these four actions" but only explicitly list two].[2]

11. Each time a card from the middle of the table is reserved or purchased, draw the top card from the corresponding deck to replace it.[3]

12. At the end of your turn, check if you meet the swaying requirement for acquiring a Noble.[4]

13. To acquire a Noble, you must have the number and color of bonuses indicated on the tile.[4]

14. If you meet the requirement, take the Noble tile and place it in your play area.[4]

15. You may only acquire 1 Noble tile per turn.[4]

16. At the end of your turn, if you have more than 10 pieces, you must return excess pieces of your choice to the supply until you have 10.[5]

17. The end of the game is triggered when a player reaches 15 or more Prestige points at the end of their turn.[6]

18. When the end of the game is triggered, continue playing until all players have had the same number of turns; the player to the right of the First Player will take the final turn of the game.[6]

19. The player with the most Prestige points wins.[6]

20. If there is a tie, the tied player who purchased the FEWEST Development cards wins.[6]

21. If it's still tied, the tied players share the victory.[6]

[1] RULEBOOK Splendor — Rulebook · p.2 · 4-Player game

[2] RULEBOOK Splendor — Rulebook · p.2 · Actions

[3] RULEBOOK Splendor — Rulebook · p.2 · Replace cards

[4] RULEBOOK Splendor — Rulebook · p.2 · NOBLE TILES

[5] RULEBOOK Splendor — Rulebook · p.2 · Piece pool limit

[6] RULEBOOK Splendor — Rulebook · p.2 · END OF THE GAME

🔧 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 91 ms · ask 4202 ms · total 4295 ms
single-flight (PR-5): queued 0 ms · generation 4295 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 2, "score": 0.047883, "snippet": "The player with the First Player marker takes the first turn. Play then proceeds clockwise. On your turn, you must perform exactly 1 of these four actions: Take 3 Gem pieces of different colors If there are not enough available pieces to take 3 of different colors from the supply, you may take 2 pie", "headingPath": "Actions", "sharpsignalDocId": 99}, {"page": 2, "score": 0.047712, "snippet": "Watch this how-to-play video instead!", "headingPath": "Don't want to read the rules?", "sharpsignalDocId": 99}, {"page": 1, "score": 0.047643, "snippet": "Play for free with the players around the world using the BOARD GAME ARENA platform. Join our community and get EXCLUSIVE REWARDS . TO LEARN HOW TO PLAY scan this QR Code. gift.unboxnow.com/splendor", "headingPath": "DISCOVER THE BEST OF BOARD GAMING", "sharpsignalDocId": 99}, {"page": 2, "score": 0.045475, "snippet": "Y our score is the sum of all Prestige points from the Development cards you purchased and the Noble tiles you've acquired. Your score must be visible at all times. When a player reaches 15 or more Prestige points at the end of their turn, the end of the game is triggered. When this happens, continu", "headingPath": "END OF THE GAME", "sharpsignalDocId": 99}, {"page": 2, "score": 0.045455, "snippet": "D uring the game, you can also obtain Noble tiles. At the end of your turn, check if you meet the swaying requirement for acquiring a Noble. To do so, you must have the number and color of bonuses indicated on the tile. If so, take the Noble tile and place it in your play area, where it will remain ", "headingPath": "NOBLE TILES", "sharpsignalDocId": 99}, {"page": 2, "score": 0.031746, "snippet": "1 Shuffle each Development card deck separately, then place them facedown in a column in the middle of the table in increasing order from bottom to top ( ; ; ). 2 Reveal 4 cards from each level deck, placing them in a row to the right of their respective decks. 3 Shuffle the Noble tiles and reveal 5", "headingPath": "4-Player game", "sharpsignalDocId": 99}, {"page": 2, "score": 0.029851, "snippet": "To reserve a card, you simply take a faceup Development card from the middle of the table or (if you're feeling lucky) draw the top card from one of the three decks without showing it to the other players. Then, take 1 Gold piece. If no Gold pieces remain in the supply, you may still reserve a card.", "headingPath": "· Reserve 1 Development card and take 1 Gold piece", "sharpsignalDocId": 99}, {"page": 2, "score": 0.029412, "snippet": "Each time a card from the middle of the table is reserved or purchased, draw the top card from the corresponding deck to replace it. There must always be 4 face-up cards of each level in the middle of the table, unless the deck becomes depleted; in this case, continue the game with fewer than 4 card", "headingPath": "Replace cards", "sharpsignalDocId": 99}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 2, "quote": null, "headingPath": "4-Player game", "sharpsignalDocId": 99}, {"page": 2, "quote": null, "headingPath": "Actions", "sharpsignalDocId": 99}, {"page": 2, "quote": null, "headingPath": "Replace cards", "sharpsignalDocId": 99}, {"page": 2, "quote": null, "headingPath": "NOBLE TILES", "sharpsignalDocId": 99}, {"page": 2, "quote": null, "headingPath": "Piece pool limit", "sharpsignalDocId": 99}, {"page": 2, "quote": null, "headingPath": "END OF THE GAME", "sharpsignalDocId": 99}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 99 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 99 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 0.89870 of 2004 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row retained until: Nov 15, 2026 04:56

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 Splendor — Rulebook (corpus doc 99)	Actions	p.2	0.047883 (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 Splendor — Rulebook (corpus doc 99)	Don't want to read the rules?	p.2	0.047712 (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))	37
#3	RULEBOOK Splendor — Rulebook (corpus doc 99)	DISCOVER THE BEST OF BOARD GAMING	p.1	0.047643 (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))	198
#4	RULEBOOK Splendor — Rulebook (corpus doc 99)	END OF THE GAME	p.2	0.045475 (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 Splendor — Rulebook (corpus doc 99)	NOBLE TILES	p.2	0.045455 (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 Splendor — Rulebook (corpus doc 99)	4-Player game	p.2	0.031746 (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 Splendor — Rulebook (corpus doc 99)	· Reserve 1 Development card and take 1 Gold piece	p.2	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 Splendor — Rulebook (corpus doc 99)	Replace cards	p.2	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 24 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 Splendor — Rulebook (corpus doc 99)	Actions	p.2	#1	0.047883 (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 Splendor — Rulebook (corpus doc 99)	2-Player game	p.2	#12	0.014493 (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
#3	RULEBOOK Splendor — Rulebook (corpus doc 99)	END OF THE GAME	p.2	#4	0.045475 (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 Splendor — Rulebook (corpus doc 99)	NOBLE TILES	p.2	#5	0.045455 (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 Splendor — Rulebook (corpus doc 99)	Piece pool limit	p.2	#17	0.013514 (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 Splendor — Rulebook (corpus doc 99)	3-Player game	p.2	#13	0.014286 (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
#7	RULEBOOK Splendor — Rulebook (corpus doc 99)	Replace cards	p.2	#8	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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK Splendor — Rulebook (corpus doc 99)	4-Player game	p.2	#6	0.031746 (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

chosen chunks — what the answer actually cited

#	document	heading	page	quote chars
[1]	RULEBOOK Splendor — Rulebook (corpus doc 99)	4-Player game	p.2	no quote on the wire
[2]	RULEBOOK Splendor — Rulebook (corpus doc 99)	Actions	p.2	no quote on the wire
[3]	RULEBOOK Splendor — Rulebook (corpus doc 99)	Replace cards	p.2	no quote on the wire
[4]	RULEBOOK Splendor — Rulebook (corpus doc 99)	NOBLE TILES	p.2	no quote on the wire
[5]	RULEBOOK Splendor — Rulebook (corpus doc 99)	Piece pool limit	p.2	no quote on the wire
[6]	RULEBOOK Splendor — Rulebook (corpus doc 99)	END OF THE GAME	p.2	no quote on the wire

generation — timing and the path taken

timing split: retrieval 91 ms · first delta 1166 ms · total 4295 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 91 ms · ask 4202 ms · gateway work 4295 ms · total 4295 ms
tokens in (the prompt the answerer read): 1155
tokens out (what the answerer generated): 642
tok/sec: 207.6 tok/sec — 642 output tokens in 3.093 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 14s 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 30), 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.