Ruling — A Game of Thrones

You asked

When does the game end?

Answered counted as answered

Asked with: A Game of Thronesbg-6472-en-1e

The game ends in one of the following ways:

1. If a House controls seven areas containing Cities and Strongholds at any time, the game is immediately over and that player is declared the winner.[1]

2. After the Action Phase on game turn 10, the game is over.[2] Specifically, if it is the last turn (turn 10), the game is over and a winner is determined.[3]

At the end of turn 10, the winner is the player who controls the most areas containing Cities and Strongholds.[1][4][2] If there is a tie for the greatest number of areas containing Cities and Strongholds, the player with the highest placement on the Supply track wins.[1] If there is also a tie for highest supply, the player with the most available power wins.[1] If there is still a tie, the game ends in a draw.[1]

[1] RULEBOOK A Game of Thrones — Rulebook · p.14 · Winning the Game · Other Rules Neutral Forces (Kings Landing, The · Three and Four Player Games

[2] RULEBOOK A Game of Thrones — Rulebook · p.3 · Game Setup · The Turn Sequence · The Westeros Phase · The Westeros Cards

[3] RULEBOOK A Game of Thrones — Rulebook · p.14 · Retreats · Existing orders in a conquered area. · Used House Card · The game continues · C) Resolve Consolidate Power Orders

[4] RULEBOOK A Game of Thrones — Rulebook · p.1 · A Game of Thrones: The Board Game · Welcome to Westeros · Introduction · Game Objective · Number of Players

That settles it — whose turn was it?

🔧 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 82 ms · ask 10760 ms · total 10845 ms
single-flight (PR-5): queued 0 ms · generation 10845 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 14, "score": 0.04918, "snippet": "The A GAME OF THRONES board game is won in either of the two following ways: a) At the end of turn 10, the player who controls the most areas containing Cities and Strongholds wins the game. If two players are tied for the greatest number of areas containing Cities and Strongholds, the player with t", "headingPath": "Winning the Game · Other Rules Neutral Forces (Kings Landing, The · Three and Four Player Games", "sharpsignalDocId": 661}, {"page": 13, "score": 0.047883, "snippet": "After taking casualties, the losing army must retreat from the embattled area. If the loser was the attacking army, all surviving units must retreat back into the area from which they came. If the defender lost, the surviving defending units must retreat using the following rules: All retreating uni", "headingPath": "Retreats", "sharpsignalDocId": 661}, {"page": 1, "score": 0.047379, "snippet": "Agame for 3-5 players designed by Christian T. Petersen, based on the bestselling A Song of Ice & Fire novels by George R.R. Martin. Playing time: 2-4 hours. King Robert Baratheon is dead, and the lands of Westeros brace for war. House Lannister, whose daughter Cersei was Robert's queen, claims the ", "headingPath": "A Game of Thrones: The Board Game · Welcome to Westeros · Introduction · Game Objective · Number of Players", "sharpsignalDocId": 661}, {"page": 14, "score": 0.047131, "snippet": "The Tyrell player has a defending combat strenght of 1 for the Footman since the routed Knight unit provides no combat strength. If House Tyrell loses the battle, the Knight -- since a routed unit may not retreat -- will be automatically destroyed. If an area is successfully taken by the attacker, r", "headingPath": "Retreats · Existing orders in a conquered area. · Used House Card · The game continues · C) Resolve Consolidate Power Orders", "sharpsignalDocId": 661}, {"page": 7, "score": 0.045921, "snippet": "If the wildlings are victorious, marauding bands will wreak havoc throughout Westeros. Each player must immediately remove 2 mustering points worth of units (Knights, Footmen, or Ships) from the board to deal with this threat (Removing one Knight, which is worth 2 mustering points, will satisfy this", "headingPath": "Wildling Victory · End of the Westeros Phase. · The Planning Phase · The Order Counters · Why give orders?", "sharpsignalDocId": 661}, {"page": 14, "score": 0.030303, "snippet": "House Greyjoy and House Tyrell are not available to players. The starting units (Ships, Knights, and Footmen) for Greyjoy and Tyrell are set up as normal on the board, and now represent neutral forces (like those of King's Landing, Sunspear, and The Eyrie) with a Footman representing 1 neutral stren", "headingPath": "Three Player Game · Four Player Game · Token Limits", "sharpsignalDocId": 661}, {"page": 11, "score": 0.029851, "snippet": "Aretreating army may not retreat into an area that contains an opponents Power token. You can never establish control over a Sea area. Since you may need your Footmen and Knight units elsewhere, establishing control ensures that you control any Supply, Power, Cities, or Strongholds in that area. Sin", "headingPath": "Establishing Control · Why establish control? · Battle", "sharpsignalDocId": 661}, {"page": 3, "score": 0.029412, "snippet": "c) Each player now places his starting units (Footmen, Knights, and Ships) in the areas indicated by his House Start Card. The game setup is now complete and the game is ready to commence. The A GAME OF THRONES board game is played over 10 whole game turns, with each game turn separated into three p", "headingPath": "Game Setup · The Turn Sequence · The Westeros Phase · The Westeros Cards", "sharpsignalDocId": 661}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 14, "quote": null, "headingPath": "Winning the Game · Other Rules Neutral Forces (Kings Landing, The · Three and Four Player Games", "sharpsignalDocId": 661}, {"page": 3, "quote": null, "headingPath": "Game Setup · The Turn Sequence · The Westeros Phase · The Westeros Cards", "sharpsignalDocId": 661}, {"page": 14, "quote": null, "headingPath": "Retreats · Existing orders in a conquered area. · Used House Card · The game continues · C) Resolve Consolidate Power Orders", "sharpsignalDocId": 661}, {"page": 1, "quote": null, "headingPath": "A Game of Thrones: The Board Game · Welcome to Westeros · Introduction · Game Objective · Number of Players", "sharpsignalDocId": 661}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 661 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 661 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 0.91352 of 636 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Aug 20, 2026 13:14 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 A Game of Thrones — Rulebook (corpus doc 661)	Winning the Game · Other Rules Neutral Forces (Kings Landing, The · Three and Four Player Games	p.14	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Retreats	p.13	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
#3	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	A Game of Thrones: The Board Game · Welcome to Westeros · Introduction · Game Objective · Number of Players	p.1	0.047379 (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 A Game of Thrones — Rulebook (corpus doc 661)	Retreats · Existing orders in a conquered area. · Used House Card · The game continues · C) Resolve Consolidate Power Orders	p.14	0.047131 (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 A Game of Thrones — Rulebook (corpus doc 661)	Wildling Victory · End of the Westeros Phase. · The Planning Phase · The Order Counters · Why give orders?	p.7	0.045921 (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 A Game of Thrones — Rulebook (corpus doc 661)	Three Player Game · Four Player Game · Token Limits	p.14	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 A Game of Thrones — Rulebook (corpus doc 661)	Establishing Control · Why establish control? · Battle	p.11	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 A Game of Thrones — Rulebook (corpus doc 661)	Game Setup · The Turn Sequence · The Westeros Phase · The Westeros Cards	p.3	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 38 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 A Game of Thrones — Rulebook (corpus doc 661)	Winning the Game · Other Rules Neutral Forces (Kings Landing, The · Three and Four Player Games	p.14	#1	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	vector + full-text + the doc-priority boost arm	the re-ranker chose it
#2	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	A Game of Thrones: The Board Game · Welcome to Westeros · Introduction · Game Objective · Number of Players	p.1	#3	0.047379 (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 A Game of Thrones — Rulebook (corpus doc 661)	Game Setup · The Turn Sequence · The Westeros Phase · The Westeros Cards	p.3	#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
#4	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Third Bid: The King's Court	p.6	#28	0.011364 (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
#5	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Resolving Raid Orders	p.10	#14	0.013699 (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 A Game of Thrones — Rulebook (corpus doc 661)	Retreats · Existing orders in a conquered area. · Used House Card · The game continues · C) Resolve Consolidate Power Orders	p.14	#4	0.047131 (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 A Game of Thrones — Rulebook (corpus doc 661)	Winter is Coming · Sea of Storms · Storm of Swords · Stronghold · Supply · Clash of Kings · …	p.16	#11	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
#8	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Wildling Victory · End of the Westeros Phase. · The Planning Phase · The Order Counters · Why give orders?	p.7	#5	0.045921 (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

#	document	heading	page	quote chars
[1]	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Winning the Game · Other Rules Neutral Forces (Kings Landing, The · Three and Four Player Games	p.14	no quote on the wire
[2]	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Game Setup · The Turn Sequence · The Westeros Phase · The Westeros Cards	p.3	no quote on the wire
[3]	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	Retreats · Existing orders in a conquered area. · Used House Card · The game continues · C) Resolve Consolidate Power Orders	p.14	no quote on the wire
[4]	RULEBOOK A Game of Thrones — Rulebook (corpus doc 661)	A Game of Thrones: The Board Game · Welcome to Westeros · Introduction · Game Objective · Number of Players	p.1	no quote on the wire

generation — timing and the path taken

timing split: retrieval 82 ms · first delta 4280 ms · total 10845 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 82 ms · ask 10760 ms · gateway work 10845 ms · total 10845 ms
tokens in (the prompt the answerer read): 3511
tokens out (what the answerer generated): 193
tok/sec: 35.6 tok/sec — 193 output tokens in 5.415 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 22s ago)
answerer host (measured by rulesage): reachable (for 23h, 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 594), 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.