Ruling — London (Second Edition)

← London (Second Edition)

You asked

How do I setup the game?

Answered counted as answered

Asked with: London (Second Edition)bg-236191-en-1e

1. Place the board in the middle of the table.[1]

2. Each player chooses a score tracker and places it on the '0' space on the board.[1]

3. Place the coin, poverty and loan tokens next to the board as a supply.[1]

4. Each player takes £5 and places it in front of them as part of their building display.[1]

5. Separate the building cards into three decks, based on the letter printed above the title of the card - A, B or C.[1]

6. Shuffle each deck separately, then place the C deck face-down.[1]

7. Place the B deck face-down on top of C, and finally the A deck face-down on top of B, creating the city deck.[1]

8. Deal each player 6 cards from the deck.[1]

9. Find the three starter boroughs with a different-coloured name (City, Westminster, and Southwark & Bermondsey) and place them face-up beside the board.[1]

10. Shuffle the rest of the borough cards, and place them face-down to form the borough deck.[1]

11. The player who set the game up becomes the first player.[1]

[1] RULEBOOK London (Second Edition) — Rulebook · p.6 · Setup

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 203 ms · ask 2365 ms · total 2570 ms
single-flight (PR-5): queued 0 ms · generation 2570 ms
retrieval refs (raw) — what the PASSAGE SEARCH returned, not what the answerer read: [{"page": 6, "score": 0.04918, "snippet": "Place the board in the middle of the table. Each player chooses a score tracker and places it on the '0' space on the board. Place the coin, poverty and loan tokens next to the board as a supply. Each player takes £5 and places it in front of them as part of their building display. The items in your", "headingPath": "Setup", "sharpsignalDocId": 531}, {"page": 7, "score": 0.032258, "snippet": "The object of the game is to have the most prestige when the city cards run out. During the game players will take turns in clockwise order. During your turn you must first draw one city card , then you must take one of the following actions: Develop your city , 2) Buy land , 3) Run your city or Dra", "headingPath": "How to Play · DEVELOPING YOUR CITY", "sharpsignalDocId": 531}, {"page": 9, "score": 0.031746, "snippet": "When you run your city, you will activate city cards in your building display, one at a time, in any order. Once you have activated as many cards as you wish, you will accumulate poverty. Activating a face-up card in your display has three steps: Pay the activation cost , if there is one. The cost w", "headingPath": "RUNNING YOUR CITY · DRAWING THREE CARDS", "sharpsignalDocId": 531}, {"page": 5, "score": 0.03125, "snippet": "If you are ever required to pay a cost you cannot afford, you must take a loan , though you may choose to take one at any point. For each loan you take, you receive £10 from the supply and a loan token. Every £10 worth of loans you have taken will generate poverty every time you run your city. To ge", "headingPath": "LOANS · THE DEVELOPMENT BOARD · DRAWING AND DISCARDING CARDS", "sharpsignalDocId": 531}, {"page": 10, "score": 0.030769, "snippet": "This is your building display when you decide to run your city. You can activate the face-up city cards in any order you wish. Your hospital gives you some good flexibility here, allowing you to re-use another city card on a later turn. As you already have some money, perhaps prestige is more import", "headingPath": "EXAMPLE OF RUNNING YOUR CITY - PART 1 · If the city deck is empty at the end of any player's turn, each other player takes one final turn.", "sharpsignalDocId": 531}, {"page": 3, "score": 0.030415, "snippet": "The city and borough cards contain a number of symbols, which are detailed here. These either gain or lose resources, or are an effect of activating your city cards when you run your city. Card name The set to which this card belongs (A, B or C). Some cards have an additional cost , which must be pa", "headingPath": "CARD SYMBOLS · ACTION CARDS", "sharpsignalDocId": 531}, {"page": 7, "score": 0.030303, "snippet": "You have these four cards in hand when you choose to develop. With your blue cards you could discard Vauxhall Gardens to build a Hospital. As the Hospital has an additional cost of £2, you would have to pay that money to the supply. You could also discard the Hospital to build the Gardens, saving yo", "headingPath": "EXAMPLE OF DEVELOPMENT", "sharpsignalDocId": 531}, {"page": 8, "score": 0.029851, "snippet": "When you buy land you must choose a borough card from the three face-up cards in the middle of the table, pay its cost and add it to your building display. If you already own one or more borough cards you must place the new one on top of it so that only the title of the previous card is visible. Rep", "headingPath": "BUYING LAND · PAUPERS · EXAMPLE OF BUYING LAND", "sharpsignalDocId": 531}]
citations (raw) — what the answer cited, chosen from a retrieval this page cannot show: [{"page": 6, "quote": null, "headingPath": "Setup", "sharpsignalDocId": 531}]
boost provenance — errata + base rulebook (E2/E3): no registered errata card matched this query; base rulebook doc 531 boosted; rulesage.errata.boost-enabled=true, rulesage.errata.supersedence-enabled=true
base rulebook doc 531 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 0.88346 of 798 non-space chars (floor 0.45); 0 glyph-index tokens (max 2)
debug row recorded: Sep 12, 2026 04:55 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 London (Second Edition) — Rulebook (corpus doc 531)	Setup	p.6	0.04918 (at the 3-arm ceiling (0.04918) — every arm ranked it #1)	300
#2	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	How to Play · DEVELOPING YOUR CITY	p.7	0.032258 (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 London (Second Edition) — Rulebook (corpus doc 531)	RUNNING YOUR CITY · DRAWING THREE CARDS	p.9	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
#4	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	LOANS · THE DEVELOPMENT BOARD · DRAWING AND DISCARDING CARDS	p.5	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
#5	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	EXAMPLE OF RUNNING YOUR CITY - PART 1 · If the city deck is empty at the end of any player's turn, each other player takes one final turn.	p.10	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
#6	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	CARD SYMBOLS · ACTION CARDS	p.3	0.030415 (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 London (Second Edition) — Rulebook (corpus doc 531)	EXAMPLE OF DEVELOPMENT	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
#8	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	BUYING LAND · PAUPERS · EXAMPLE OF BUYING LAND	p.8	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

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 12 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 London (Second Edition) — Rulebook (corpus doc 531)	Setup	p.6	#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 London (Second Edition) — Rulebook (corpus doc 531)	EXAMPLE OF RUNNING YOUR CITY - PART 1 · If the city deck is empty at the end of any player's turn, each other player takes one final turn.	p.10	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#3	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	CARD SYMBOLS · ACTION CARDS	p.3	#6	0.030415 (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 London (Second Edition) — Rulebook (corpus doc 531)	RUNNING YOUR CITY · DRAWING THREE CARDS	p.9	#3	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
#5	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	EXAMPLE OF DEVELOPMENT	p.7	#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))	vector + the doc-priority boost arm	the re-ranker chose it
#6	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	EXAMPLE OF RUNNING YOUR CITY - PART 2	p.11	#9	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
#7	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	LOANS · THE DEVELOPMENT BOARD · DRAWING AND DISCARDING CARDS	p.5	#4	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))	vector + the doc-priority boost arm	the re-ranker chose it
#8	RULEBOOK London (Second Edition) — Rulebook (corpus doc 531)	How to Play · DEVELOPING YOUR CITY	p.7	#2	0.032258 (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 London (Second Edition) — Rulebook (corpus doc 531)	Setup	p.6	no quote on the wire

generation — timing and the path taken

timing split: retrieval 203 ms · first delta 1196 ms · total 2570 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 203 ms · ask 2365 ms · gateway work 2570 ms · total 2570 ms
tokens in (the prompt the answerer read): 2934
tokens out (what the answerer generated): 267
tok/sec: 201.4 tok/sec — 267 output tokens in 1.326 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 22h, checked 1s 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: NO_APPROVED_CHECKLIST — setup-shaped, but no approved setup checklist exists for this game
pattern that matched: SETUP — "setup" / "set up"
matched words (in the normalized question): setup

errata registry — what the gate above had to match against

this game registers NO errata cards (edition 462), 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.