Prioritize capital-efficient independent bundles

README.md

@@ -20,7 +20,7 @@ market snapshots. During an outage, cycles continue locally; cached entries are
 allowed for 90 minutes, older snapshots become mark-only, and all cached data
 expires after 24 hours.
 
-Build 120 targets five-minute slots with a serialized, self-chained GitHub Actions runtime.
+Build 121 targets five-minute slots with a serialized, self-chained GitHub Actions runtime.
 It continues from the previous agent snapshot and runs the next due paper cycle
 even when no browser is open. After each successful cycle, one repo-scoped
 workflow dispatch waits for the next five-minute boundary; one concurrency group
@@ -60,7 +60,7 @@ Polymarket event key. Related Ethereum or Bitcoin contracts cannot create
 several simultaneous copies of one move, and outcomes from the same underlying
 three-hour shock window count as one learner event.
 
-Each Build 120 cycle also scans the 1,000 most-active Polymarket events for
+Each Build 121 cycle also scans the 1,000 most-active Polymarket events for
 complete negative-risk bundles and logically nested threshold or deadline
 pairs. Gamma's market-specific fee flag replaces the old blanket 0.5-cent fee
 reserve for markets declared fee-free. The closest 60 structures are then
@@ -69,7 +69,11 @@ paper order up to a $400 verified-notional ceiling. The scanner applies each mar
 consumed ask level and checks the CLOB fee-rate endpoint for a matching enabled
 or fee-free state. Any opened position is capped to the exact equal-unit size
 of the largest fill that stays profitable and passes this depth test; portfolio
-cash, reserve, and 4% limits can reduce it further. Existing paper bundles are
+cash, reserve, and 4% limits can reduce it further. Strategy 64 ranks verified
+structures by net return per expected locked day before raw edge, and caps active
+cost from one underlying event at 12% of Value Hunter equity. This prevents
+several related threshold pairs from monopolizing the non-directional book while
+preserving every already-open complete bundle until settlement. Existing paper bundles are
 never retroactively enlarged against depth their original simulated fill would
 already have consumed. A bundle can enter Value Discipline only when that fee check
 passes and the resulting worst-case payout clears both the three-tenths-cent
@@ -79,7 +83,7 @@ The Suggestions view stores scan, depth, fee, actionable, and closest
 executable-margin counts so an empty lane is evidence rather than an ambiguous
 failure.
 
-Build 120 retains the directional learner's exact-fee policy, which replaced the blanket half-cent cost with
+Build 121 retains the directional learner's exact-fee policy, which replaced the blanket half-cent cost with
 the market's Gamma fee schedule at both the entry and future checkpoint, plus a
 separate half-cent round-trip slippage allowance. Fee-free markets pay only the
 slippage allowance; an unavailable fee schedule gets a conservative four-cent
@@ -90,7 +94,7 @@ available at reduced weight. The exact-fee replay covered the top 1,000
 active markets and 208 independent events: broad trends, reversals, and
 favorite trends all had 90% upper bounds below zero at 12 hours. A separate
 3,000-recently-closed-market study tested 297 one-decision-per-event settlement
-rules and found zero robust positive rule. Strategy 63 retains online
+rules and found zero robust positive rule. Strategy 64 retains online
 directional evidence under fee policy 2. A separate probation gate can now use
 capital after at least 12 current-policy independent events produce a net-of-cost
 six-hour lower confidence bound above 1% for every required cohort feature. It
@@ -100,7 +104,7 @@ Every probation position exits at the matching six-hour executable bid and keeps
 the 18% stop policy active. Normal directional sizing remains locked until the
 same cohort independently passes both the 24-hour and 72-hour promotion gates.
 
-Build 120 retains Build 100's retirement of the old 3-6 day resolution-window
+Build 121 retains Build 100's retirement of the old 3-6 day resolution-window
 capital permission. That audit clustered confidence by event but still averaged
 several correlated contracts inside each event, while production could choose
 only one. The corrected replay chooses the highest-volume eligible contract per event and
@@ -220,9 +224,9 @@ evidence proves an edge.
 
 Run `npm run evaluate:sports-favorites` for the retired pregame favorite audit.
 Its 12-hour, 60%-75% cohort had positive point estimates but did not establish a
-reliable confidence bound, so Build 120 no longer allocates capital to that rule.
+reliable confidence bound, so Build 121 no longer allocates capital to that rule.
 
-Strategy 63 also uses the exact-fee settlement calibration's three-day Sports
+Strategy 64 also uses the exact-fee settlement calibration's three-day Sports
 NO cohort as a bounded paper exploration lane. The corrected 5,000-market run
 groups every prop with the same dated contest slug, anchors the decision to the
 published game start, and keeps only the highest-priced eligible NO contract per
@@ -348,7 +352,7 @@ Strategy 54 gives previously opened Politics trend positions that 72-hour observ
 ordinary signal exits. Stops, profit locks, settlement handling, and risk-budget
 reductions remain immediate.
 
-Strategy 63 retains exact Gamma entry and exit taker fees plus a half-cent
+Strategy 64 retains exact Gamma entry and exit taker fees plus a half-cent
 slippage allowance when grading each live walk-forward signal. Confidence uses the largest independent matching bucket,
 not the sum of five overlapping feature buckets, and evidence from older engine
 versions is down-weighted. This prevents a handful of duplicated observations