PHASE 3.30 SECOND INTERVENTION RESULTS

PRIMARY
Average ending bankroll Textbook/Selective: 99.781 / 92.061
Maximum bankroll observed Textbook/Selective: 230.0 at hand 29 (session 1777) / 230.0 at hand 29 (session 3697)
Positive sessions Textbook/Selective: 48.14% / 39.32%
Affordability base stops: 12
Affordability split fallbacks: 7
Affordability double fallbacks: 22
Paired winner Textbook/Selective/tie: 56.34% / 40.12% / 3.54%
Doubles Textbook/Selective: 15716 / 25294; splits Textbook/Selective: 3808 / 21702
Mean cards consumed Textbook/Selective: 165.674 / 175.122
Ending bankroll >=2x (200) Textbook/Selective: 0.20% / 0.06%
Ending bankroll >=3x (300) Textbook/Selective: 0.00% / 0.00%
Ending bankroll >=5x (500) Textbook/Selective: 0.00% / 0.00%
Ending bankroll >=10x (1000) Textbook/Selective: 0.00% / 0.00%

HOLDOUT
Average ending bankroll Textbook/Selective: 99.862 / 92.481
Maximum bankroll observed Textbook/Selective: 212.5 at hand 24 (session 1273) / 227.5 at hand 29 (session 3625)
Positive sessions Textbook/Selective: 47.42% / 40.30%
Affordability base stops: 12
Affordability split fallbacks: 5
Affordability double fallbacks: 23
Paired winner Textbook/Selective/tie: 57.00% / 39.70% / 3.30%
Doubles Textbook/Selective: 15412 / 24961; splits Textbook/Selective: 3747 / 21604
Mean cards consumed Textbook/Selective: 165.647 / 175.086
Ending bankroll >=2x (200) Textbook/Selective: 0.08% / 0.22%
Ending bankroll >=3x (300) Textbook/Selective: 0.00% / 0.00%
Ending bankroll >=5x (500) Textbook/Selective: 0.00% / 0.00%
Ending bankroll >=10x (1000) Textbook/Selective: 0.00% / 0.00%


PHASE 3.30 BANKRUPTCY-STOP CALIBRATION — CONSTANT 5x

SCIENTIFIC BOUNDARY
Decision policy: frozen Phase 3.20 checkpoint, validated Phase 3.21.
Wager architecture: constant 5-unit base wager (5x the Phase 3.22 baseline).
One multiplier intervention is active: the base wager is five times the Phase 3.22 baseline (5 units).

PRIMARY
Mean ending bankroll: 92.061
Maximum bankroll observed anywhere: 230.0 at Hand 29 (session 3697)
Mean per-session peak bankroll: 121.520
Mean per-session maximum drawdown: 41.525 units
Sessions ever reaching 2x / 3x / 5x / 10x: 0.14% / 0.00% / 0.00% / 0.00%
Sessions ever reaching bankroll <=0: 0.72%
Sessions whose highest bankroll never exceeded the 100-unit start: 833
Most common positive hand-of-peak among sessions that exceeded start: Hand 1 [328 sessions]

HOLDOUT
Mean ending bankroll: 92.481
Maximum bankroll observed anywhere: 227.5 at Hand 29 (session 3625)
Mean per-session peak bankroll: 121.583
Mean per-session maximum drawdown: 41.229 units
Sessions ever reaching 2x / 3x / 5x / 10x: 0.26% / 0.00% / 0.00% / 0.00%
Sessions ever reaching bankroll <=0: 0.38%
Sessions whose highest bankroll never exceeded the 100-unit start: 889
Most common positive hand-of-peak among sessions that exceeded start: Hand 1 [342 sessions]

MEAN SELECTIVE BANKROLL TRAJECTORY AFTER EACH HAND
Hand | Primary | Holdout
 1 |   99.504 |   99.666
 2 |   99.197 |   99.407
 3 |   98.813 |   99.073
 4 |   98.452 |   98.826
 5 |   98.289 |   98.365
 6 |   98.049 |   98.178
 7 |   97.838 |   98.053
 8 |   97.617 |   97.839
 9 |   97.371 |   97.671
10 |   97.133 |   97.473
11 |   96.906 |   97.194
12 |   96.680 |   96.852
13 |   96.444 |   96.660
14 |   96.106 |   96.397
15 |   95.836 |   96.152
16 |   95.537 |   95.686
17 |   95.326 |   95.570
18 |   95.111 |   95.262
19 |   94.899 |   95.035
20 |   94.649 |   94.870
21 |   94.521 |   94.744
22 |   94.179 |   94.514
23 |   93.836 |   94.253
24 |   93.629 |   93.939
25 |   93.361 |   93.787
26 |   92.959 |   93.446
27 |   92.825 |   93.252
28 |   92.509 |   93.183
29 |   92.398 |   92.718
30 |   92.061 |   92.481

PHASE 3.30 — SELECTIVE-AGGRESSION INSTRUMENTATION SUMMARY

PRIMARY resolved selective-aggression hands: 171500; mean net/hand -0.2315; mean committed stake 5.7374; bust rate 16.24%; third-card bust rate when a third card was taken 21.23%.
Textbook would have chosen on those same visible first-decision states: HIT 70153, STAND 67953, DOUBLE 15874.

HOLDOUT resolved selective-aggression hands: 171456; mean net/hand -0.2193; mean committed stake 5.7279; bust rate 16.16%; third-card bust rate when a third card was taken 21.15%.
Textbook would have chosen on those same visible first-decision states: HIT 69928, STAND 68115, DOUBLE 15728.

INTERPRETATION
Phase 3.30 carries forward split-child HARD 20 STAND, HARD 19 STAND, and split-child HARD 18 STAND. It adds one new family only: NO POLICY OR WAGER INTERVENTION; frozen policy carried forward at 1x. All other Maximum Aggression behaviour remains frozen.

PRIMARY — WORST SELECTIVE-AGGRESSION VISIBLE STATES BY MEAN NET/HAND
Rank | Visible state | Hands | Mean net | Loss% | Bust% | 3rd-card bust% of 3rd-card draws | Mean stake
 1 | HARD 4 vs 11 [split-child] | textbook=HIT     |     11 | -10.000 | 100.00% |   0.00% |   0.00% | 10.000
 2 | HARD 4 vs 9 [split-child] | textbook=HIT      |     10 |  -8.000 |  90.00% |   0.00% |   0.00% | 10.000
 3 | HARD 4 vs 7 [split-child] | textbook=HIT      |      8 |  -7.500 |  87.50% |   0.00% |   0.00% | 10.000
 4 | HARD 4 vs 2 [split-child] | textbook=HIT      |      4 |  -6.250 |  75.00% |   0.00% |   0.00% | 8.750
 5 | HARD 4 vs 10 [split-child] | textbook=HIT     |     37 |  -5.676 |  78.38% |   0.00% |   0.00% | 10.000
 6 | HARD 4 vs 4 [split-child] | textbook=HIT      |     13 |  -5.385 |  76.92% |   0.00% |   0.00% | 10.000
 7 | HARD 4 vs 5 | textbook=HIT                    |      1 |  -5.000 | 100.00% |   0.00% |   0.00% | 5.000
 8 | SOFT 19 vs 4 [split-child] | textbook=STAND   |     24 |  -2.917 |  58.33% |   0.00% |   0.00% | 10.000
 9 | HARD 16 vs 11 [split-child] | textbook=HIT    |    148 |  -2.872 |  76.35% |  68.24% |  68.24% | 5.000
10 | HARD 4 vs 6 [split-child] | textbook=HIT      |     14 |  -2.857 |  64.29% |   0.00% |   0.00% | 10.000
11 | HARD 16 vs 10 [split-child] | textbook=HIT    |    849 |  -2.845 |  75.38% |  63.37% |  63.37% | 5.000
12 | HARD 6 vs 8 [split-child] | textbook=HIT      |     32 |  -2.813 |  71.88% |  59.38% |   0.00% | 5.000
13 | HARD 15 vs 10 | textbook=HIT                  |   2939 |  -2.656 |  72.85% |  58.90% |  53.76% | 5.000
14 | SOFT 16 vs 4 [split-child] | textbook=DOUBLE  |     19 |  -2.632 |  57.89% |   0.00% |   0.00% | 10.000
15 | HARD 16 vs 9 | textbook=HIT                   |    705 |  -2.624 |  73.33% |  62.70% |  62.70% | 5.000
16 | HARD 5 vs 9 [split-child] | textbook=HIT      |     23 |  -2.609 |  73.91% |  60.87% |   0.00% | 5.000
17 | SOFT 14 vs 2 [split-child] | textbook=HIT     |     23 |  -2.609 |  60.87% |   0.00% |   0.00% | 10.000
18 | HARD 16 vs 10 | textbook=HIT                  |   2549 |  -2.577 |  72.89% |  60.93% |  60.93% | 5.000
19 | HARD 14 vs 11 [split-child] | textbook=HIT    |    189 |  -2.566 |  71.96% |  61.90% |  50.26% | 5.000
20 | HARD 15 vs 11 [split-child] | textbook=HIT    |    159 |  -2.547 |  71.07% |  64.15% |  59.12% | 5.000
21 | HARD 15 vs 9 | textbook=HIT                   |    808 |  -2.519 |  71.91% |  58.42% |  53.47% | 5.000
22 | HARD 7 vs 11 [split-child] | textbook=HIT     |     30 |  -2.500 |  66.67% |  43.33% |   0.00% | 5.000
23 | SOFT 20 vs 11 [split-child] | textbook=STAND  |     12 |  -2.500 |  58.33% |   0.00% |   0.00% | 10.000
24 | HARD 15 vs 7 [split-child] | textbook=HIT     |    239 |  -2.490 |  72.38% |  62.34% |  57.74% | 5.000
25 | HARD 16 vs 11 | textbook=HIT                  |    496 |  -2.460 |  71.57% |  62.70% |  62.70% | 5.000

HOLDOUT — WORST SELECTIVE-AGGRESSION VISIBLE STATES BY MEAN NET/HAND
Rank | Visible state | Hands | Mean net | Loss% | Bust% | 3rd-card bust% of 3rd-card draws | Mean stake
 1 | HARD 4 vs 7 [split-child] | textbook=HIT      |      6 | -10.000 | 100.00% |   0.00% |   0.00% | 10.000
 2 | HARD 4 vs 8 [split-child] | textbook=HIT      |      7 |  -7.143 |  85.71% |   0.00% |   0.00% | 10.000
 3 | HARD 4 vs 11 [split-child] | textbook=HIT     |     13 |  -6.923 |  84.62% |   0.00% |   0.00% | 10.000
 4 | HARD 4 vs 10 [split-child] | textbook=HIT     |     36 |  -6.667 |  83.33% |   0.00% |   0.00% | 10.000
 5 | HARD 4 vs 9 [split-child] | textbook=HIT      |     12 |  -6.667 |  83.33% |   0.00% |   0.00% | 10.000
 6 | HARD 4 vs 5 [split-child] | textbook=HIT      |      9 |  -5.556 |  77.78% |   0.00% |   0.00% | 10.000
 7 | HARD 4 vs 10 | textbook=HIT                   |      1 |  -5.000 | 100.00% | 100.00% |   0.00% | 5.000
 8 | HARD 4 vs 4 [split-child] | textbook=HIT      |     11 |  -4.545 |  72.73% |   0.00% |   0.00% | 10.000
 9 | SOFT 14 vs 6 [split-child] | textbook=DOUBLE  |     16 |  -4.375 |  68.75% |   0.00% |   0.00% | 10.000
10 | SOFT 14 vs 11 [split-child] | textbook=HIT    |      8 |  -3.125 |  75.00% |  62.50% |   0.00% | 5.000
11 | HARD 16 vs 9 [split-child] | textbook=HIT     |    224 |  -2.924 |  77.23% |  64.73% |  64.73% | 5.000
12 | SOFT 18 vs 11 [split-child] | textbook=HIT    |     12 |  -2.917 |  75.00% |  25.00% |   0.00% | 5.000
13 | HARD 16 vs 11 | textbook=HIT                  |    503 |  -2.813 |  74.75% |  64.21% |  64.21% | 5.000
14 | SOFT 19 vs 8 [split-child] | textbook=STAND   |     25 |  -2.800 |  56.00% |   0.00% |   0.00% | 10.000
15 | HARD 16 vs 10 [split-child] | textbook=HIT    |    773 |  -2.788 |  75.03% |  63.13% |  63.13% | 5.000
16 | HARD 14 vs 9 [split-child] | textbook=HIT     |    273 |  -2.711 |  75.09% |  61.17% |  53.48% | 5.000
17 | HARD 14 vs 11 [split-child] | textbook=HIT    |    185 |  -2.595 |  72.97% |  61.08% |  47.57% | 5.000
18 | HARD 16 vs 11 [split-child] | textbook=HIT    |    160 |  -2.531 |  71.88% |  59.38% |  59.38% | 5.000
19 | HARD 16 vs 9 | textbook=HIT                   |    694 |  -2.529 |  72.33% |  59.65% |  59.65% | 5.000
20 | HARD 17 vs 11 | textbook=STAND                |    459 |  -2.516 |  66.67% |   0.00% |   0.00% | 5.000
21 | HARD 5 vs 3 [split-child] | textbook=HIT      |     20 |  -2.500 |  75.00% |  10.00% |   0.00% | 5.000
22 | SOFT 18 vs 7 [split-child] | textbook=STAND   |     16 |  -2.500 |  62.50% |   0.00% |   0.00% | 10.000
23 | HARD 16 vs 10 | textbook=HIT                  |   2424 |  -2.467 |  71.74% |  59.94% |  59.94% | 5.000
24 | HARD 15 vs 10 | textbook=HIT                  |   2987 |  -2.446 |  71.41% |  57.95% |  53.23% | 5.000
25 | HARD 14 vs 10 | textbook=HIT                  |   2992 |  -2.391 |  70.49% |  56.68% |  47.23% | 5.000


PHASE 3.30 — REMAINING TRUE POLICY-DIVERGENCE STATES UNDER FROZEN 3.20 POLICY

Filter: aggregate ONLY hands where Selective Aggression's recorded first action differs from the frozen Textbook first action; then require the same visible state >=100 times in BOTH cohorts and negative mean net/hand in BOTH cohorts. This prevents already-protected states with negative realised outcomes from being mislabelled as remaining policy damage.

Rank | State | Primary n / net | Holdout n / net | P bust% / H bust% | Textbook first action
 1 | SOFT 16 vs 3                       |   141 / -0.496 |   136 / -1.838 |   0.00% /   0.00% | HIT
 2 | SOFT 14 vs 3                       |   106 / -0.660 |   128 / -1.250 |   0.00% /   0.00% | HIT
 3 | HARD 10 vs 11                      |   284 / -0.775 |   292 / -0.565 |   0.00% /   0.00% | HIT
 4 | SOFT 15 vs 2                       |   138 / -0.435 |   153 / -0.784 |   0.00% /   0.00% | HIT
 5 | HARD 9 vs 8                        |   433 / -0.924 |   428 / -0.164 |   0.00% /   0.00% | HIT
 6 | SOFT 13 vs 2                       |   124 / -0.242 |   134 / -0.821 |   0.00% /   0.00% | HIT
 7 | HARD 10 vs 10 [split-child]        |   286 / -0.420 |   241 / -0.104 |   0.00% /   0.00% | HIT
 8 | HARD 10 vs 10                      |  1483 / -0.027 |  1540 / -0.088 |   0.00% /   0.06% | HIT

DESIGN USE
Phase 3.30 carries forward the validated split-child HARD 20, HARD 19 and split-child HARD 18 protections and adds no intervention; frozen decision policy is measured at the unchanged 1x wager. Remaining replicated damage states are retained for later one-rule-at-a-time interventions.

PHASE 3.30 — RUNNING TXT AUDIT RECORD

OBJECTIVE
Make the fourth controlled stabilisation intervention while preserving the frozen architecture. Carry forward the three validated protections, then add one new policy family: HARD 16 follows its corresponding Textbook action rather than taking Maximum Aggression's automatic DOUBLE.

EVIDENCE HIERARCHY
1. Primary design authority: finite six-deck Phase 2.xx evidence and new Phase 3.xx data.
2. Earlier non-depleting/infinite-generator behaviour-profile data: historical corroboration and hypothesis generation only.
3. Old behaviour-profile evidence must not directly define a new policy unless finite-shoe evidence independently supports the same conclusion.

FROZEN VARIABLES
Six decks, deterministic session shuffle, 30 hands, 100-unit start, 1-unit base wager, dealer rules, blackjack payout, split limit, no in-session reshuffle, textbook control and Maximum Aggression policy are unchanged from Phase 2.02.

POLICY INFORMATION BOUNDARY
The future optimiser may use player hand composition/total, pair status, dealer upcard and legal actions. Phase 3.30 deliberately uses no previous-card-history, running count, remaining-rank inventory, hidden card or future-card feature. The accumulated policy uses only current visible states: split-child HARD 20, HARD 19, HARD 18, split-child HARD 16 vs Ace, and HARD 17. No card-history or composition feature is introduced.

PHASE 3.30 DECISION RULE
Carry forward split-child HARD 20 STAND, HARD 19 STAND and split-child HARD 18 STAND. ONE additional Phase 3.30 intervention: if an ordinary first-decision hand is hard (not soft) and totals 18, Selective Aggression STANDS. Otherwise the frozen Maximum Aggression policy is unchanged. Textbook remains the control.

PHASE 3.30 REPLAY FINGERPRINT: 084c9006fab17061cb7bfa3c5487fc29436a0f9894615d1681a7ba6f195bd3d3
