Ruling — London (Second Edition)

You asked

What needs to be placed on the table before the first round begins?

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 (A, B, and C) [1], shuffle each deck separately [1], then place the C deck face-down [1], the B deck face-down on top of C [1], and finally the A deck face-down on top of B to create the city deck [1]. 6. Deal each player 6 cards from the deck [1]. 7. Find the three starter boroughs with a different-coloured name (City, Westminster, and Southwark & Bermondsey) and place them face-up beside the board [1]. 8. Shuffle the rest of the borough cards and place them face-down to form the borough deck [1].

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

🔧 debug — where this ruling came from

outcome: ANSWERED — Answered
corpus profile: live
answerer pin (deploy-frozen, attribution only): gemma4:26b think:false 5571076f3d70
timings: search 278 ms · ask 4658 ms · total 45106 ms
single-flight (PR-5): queued 40156 ms · generation 4950 ms
retrieval refs (raw): [{"page": 6, "score": 0.032787, "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": 5, "score": 0.032258, "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": 7, "score": 0.031746, "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": 7, "score": 0.03125, "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": 3, "score": 0.030769, "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": 9, "score": 0.030303, "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": 12, "score": 0.029851, "snippet": "| Gain prestige immediately | Gain one poverty | | Gain prestige at the end of the game | Alleviate one poverty | | Spend money | Spend an additional card to activate | | Gain money | Flip this card after activation | | 1-2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 | 10 | each point over 10 | | -1 | -2 -3 | -5 | ", "headingPath": "Card Symbols · Prestige lost due to Poverty", "sharpsignalDocId": 531}, {"page": 4, "score": 0.029412, "snippet": "The larger cards represent an opportunity to purchase land in one of 20 boroughs in London. Land is expensive, but highly valuable. Every time you buy a piece of land it will immediately grant you prestige; alleviate poverty; and open up new opportunities, allowing you to draw cards. Some boroughs m", "headingPath": "BOROUGH CARDS", "sharpsignalDocId": 531}]
citations (raw): [{"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)
debug row retained until: Nov 7, 2026 08:03

retrieval — what the search arm returned

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	0.032787 (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 London (Second Edition) — Rulebook (corpus doc 531)	LOANS · THE DEVELOPMENT BOARD · DRAWING AND DISCARDING CARDS	p.5	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)	EXAMPLE OF DEVELOPMENT	p.7	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)	How to Play · DEVELOPING YOUR CITY	p.7	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)	CARD SYMBOLS · ACTION CARDS	p.3	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)	RUNNING YOUR CITY · DRAWING THREE CARDS	p.9	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 London (Second Edition) — Rulebook (corpus doc 531)	Card Symbols · Prestige lost due to Poverty	p.12	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 London (Second Edition) — Rulebook (corpus doc 531)	BOROUGH CARDS	p.4	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

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 278 ms · first delta 3202 ms · total 45106 ms (retrieval and first-delta both measured from the START of gateway work, so first-delta INCLUDES retrieval — do not subtract)
full breakdown: queued 40156 ms · retrieval 278 ms · ask 4658 ms · gateway work 4950 ms · total 45106 ms
tokens in (the prompt the answerer read): 3304
tokens out (what the answerer generated): 234
tok/sec: 137.8 tok/sec — 234 output tokens in 1.698 s of generation
live seat (read from the running child): answering — gemma4:26b think:false · num_ctx 32768 (live-verified 50s 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 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.