PHASE 3.32 SECOND INTERVENTION RESULTS

PRIMARY
Average ending bankroll Textbook/Selective: 99.956 / 98.412
Maximum bankroll observed Textbook/Selective: 126.0 at hand 29 (session 1777) / 126.0 at hand 29 (session 3697)
Positive sessions Textbook/Selective: 48.14% / 39.32%
Affordability base stops: 0
Affordability split fallbacks: 0
Affordability double fallbacks: 0
Paired winner Textbook/Selective/tie: 56.34% / 40.12% / 3.54%
Doubles Textbook/Selective: 15716 / 25349; splits Textbook/Selective: 3808 / 21735
Mean cards consumed Textbook/Selective: 165.674 / 175.360
Ending bankroll >=2x (200) Textbook/Selective: 0.00% / 0.00%
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: 99.972 / 98.496
Maximum bankroll observed Textbook/Selective: 122.5 at hand 24 (session 1273) / 125.5 at hand 29 (session 3625)
Positive sessions Textbook/Selective: 47.42% / 40.30%
Affordability base stops: 0
Affordability split fallbacks: 0
Affordability double fallbacks: 0
Paired winner Textbook/Selective/tie: 57.00% / 39.70% / 3.30%
Doubles Textbook/Selective: 15412 / 25011; splits Textbook/Selective: 3747 / 21628
Mean cards consumed Textbook/Selective: 165.647 / 175.259
Ending bankroll >=2x (200) Textbook/Selective: 0.00% / 0.00%
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 3.32 BANKRUPTCY-STOP CALIBRATION — CONSTANT 5x

SCIENTIFIC BOUNDARY
Decision policy: frozen Phase 3.20 checkpoint, validated Phase 3.21.
Wager architecture: constant 1-unit observational 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: 98.412
Maximum bankroll observed anywhere: 126.0 at Hand 29 (session 3697)
Mean per-session peak bankroll: 104.304
Mean per-session maximum drawdown: 8.317 units
Sessions ever reaching 2x / 3x / 5x / 10x: 0.00% / 0.00% / 0.00% / 0.00%
Sessions ever reaching bankroll <=0: 0.00%
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: 98.496
Maximum bankroll observed anywhere: 125.5 at Hand 29 (session 3625)
Mean per-session peak bankroll: 104.317
Mean per-session maximum drawdown: 8.256 units
Sessions ever reaching 2x / 3x / 5x / 10x: 0.00% / 0.00% / 0.00% / 0.00%
Sessions ever reaching bankroll <=0: 0.00%
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 |   99.901 |   99.933
 2 |   99.839 |   99.881
 3 |   99.763 |   99.815
 4 |   99.690 |   99.765
 5 |   99.658 |   99.673
 6 |   99.610 |   99.636
 7 |   99.568 |   99.611
 8 |   99.523 |   99.568
 9 |   99.474 |   99.534
10 |   99.427 |   99.495
11 |   99.381 |   99.439
12 |   99.336 |   99.370
13 |   99.289 |   99.332
14 |   99.221 |   99.279
15 |   99.167 |   99.231
16 |   99.107 |   99.137
17 |   99.065 |   99.114
18 |   99.023 |   99.052
19 |   98.981 |   99.007
20 |   98.930 |   98.975
21 |   98.905 |   98.950
22 |   98.837 |   98.903
23 |   98.769 |   98.850
24 |   98.726 |   98.788
25 |   98.673 |   98.757
26 |   98.593 |   98.689
27 |   98.567 |   98.652
28 |   98.503 |   98.640
29 |   98.479 |   98.545
30 |   98.412 |   98.496

PHASE 3.32 — SELECTIVE-AGGRESSION INSTRUMENTATION SUMMARY

PRIMARY resolved selective-aggression hands: 171735; mean net/hand -0.0462; mean committed stake 1.1476; bust rate 16.24%; third-card bust rate when a third card was taken 21.24%.
Textbook would have chosen on those same visible first-decision states: HIT 70251, STAND 68048, DOUBLE 15895.

HOLDOUT resolved selective-aggression hands: 171628; mean net/hand -0.0438; mean committed stake 1.1457; bust rate 16.15%; third-card bust rate when a third card was taken 21.14%.
Textbook would have chosen on those same visible first-decision states: HIT 70001, STAND 68188, DOUBLE 15744.

INTERPRETATION
Phase 3.32 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 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 2 | HARD 4 vs 9 [split-child] | textbook=HIT      |     10 |  -1.600 |  90.00% |   0.00% |   0.00% | 2.000
 3 | HARD 4 vs 7 [split-child] | textbook=HIT      |      8 |  -1.500 |  87.50% |   0.00% |   0.00% | 2.000
 4 | HARD 4 vs 10 [split-child] | textbook=HIT     |     37 |  -1.135 |  78.38% |   0.00% |   0.00% | 2.000
 5 | HARD 4 vs 4 [split-child] | textbook=HIT      |     13 |  -1.077 |  76.92% |   0.00% |   0.00% | 2.000
 6 | HARD 4 vs 2 [split-child] | textbook=HIT      |      4 |  -1.000 |  75.00% |   0.00% |   0.00% | 2.000
 7 | SOFT 19 vs 4 [split-child] | textbook=STAND   |     24 |  -0.583 |  58.33% |   0.00% |   0.00% | 2.000
 8 | HARD 16 vs 11 [split-child] | textbook=HIT    |    148 |  -0.574 |  76.35% |  68.24% |  68.24% | 1.000
 9 | HARD 4 vs 6 [split-child] | textbook=HIT      |     14 |  -0.571 |  64.29% |   0.00% |   0.00% | 2.000
10 | HARD 16 vs 10 [split-child] | textbook=HIT    |    852 |  -0.569 |  75.35% |  63.38% |  63.38% | 1.000
11 | HARD 6 vs 8 [split-child] | textbook=HIT      |     32 |  -0.563 |  71.88% |  59.38% |   0.00% | 1.000
12 | HARD 15 vs 10 | textbook=HIT                  |   2941 |  -0.531 |  72.87% |  58.93% |  53.79% | 1.000
13 | SOFT 16 vs 4 [split-child] | textbook=DOUBLE  |     19 |  -0.526 |  57.89% |   0.00% |   0.00% | 2.000
14 | HARD 16 vs 9 | textbook=HIT                   |    705 |  -0.525 |  73.33% |  62.70% |  62.70% | 1.000
15 | HARD 5 vs 9 [split-child] | textbook=HIT      |     23 |  -0.522 |  73.91% |  60.87% |   0.00% | 1.000
16 | SOFT 14 vs 2 [split-child] | textbook=HIT     |     23 |  -0.522 |  60.87% |   0.00% |   0.00% | 2.000
17 | HARD 16 vs 10 | textbook=HIT                  |   2552 |  -0.515 |  72.88% |  60.93% |  60.93% | 1.000
18 | HARD 14 vs 11 [split-child] | textbook=HIT    |    189 |  -0.513 |  71.96% |  61.90% |  50.26% | 1.000
19 | HARD 15 vs 11 [split-child] | textbook=HIT    |    160 |  -0.513 |  71.25% |  64.38% |  59.38% | 1.000
20 | HARD 15 vs 9 | textbook=HIT                   |    809 |  -0.504 |  71.94% |  58.47% |  53.52% | 1.000
21 | HARD 15 vs 7 [split-child] | textbook=HIT     |    240 |  -0.500 |  72.50% |  62.50% |  57.92% | 1.000
22 | HARD 7 vs 11 [split-child] | textbook=HIT     |     30 |  -0.500 |  66.67% |  43.33% |   0.00% | 1.000
23 | SOFT 20 vs 11 [split-child] | textbook=STAND  |     12 |  -0.500 |  58.33% |   0.00% |   0.00% | 2.000
24 | HARD 14 vs 10 [split-child] | textbook=HIT    |    927 |  -0.493 |  71.20% |  57.17% |  47.36% | 1.000
25 | HARD 16 vs 11 | textbook=HIT                  |    496 |  -0.492 |  71.57% |  62.70% |  62.70% | 1.000

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 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 2 | HARD 4 vs 8 [split-child] | textbook=HIT      |      7 |  -1.429 |  85.71% |   0.00% |   0.00% | 2.000
 3 | HARD 4 vs 11 [split-child] | textbook=HIT     |     13 |  -1.385 |  84.62% |   0.00% |   0.00% | 2.000
 4 | HARD 4 vs 10 [split-child] | textbook=HIT     |     37 |  -1.351 |  83.78% |   0.00% |   0.00% | 2.000
 5 | HARD 4 vs 9 [split-child] | textbook=HIT      |     12 |  -1.333 |  83.33% |   0.00% |   0.00% | 2.000
 6 | HARD 4 vs 5 [split-child] | textbook=HIT      |      9 |  -1.111 |  77.78% |   0.00% |   0.00% | 2.000
 7 | HARD 4 vs 4 [split-child] | textbook=HIT      |     11 |  -0.909 |  72.73% |   0.00% |   0.00% | 2.000
 8 | SOFT 14 vs 6 [split-child] | textbook=DOUBLE  |     16 |  -0.875 |  68.75% |   0.00% |   0.00% | 2.000
 9 | SOFT 14 vs 11 [split-child] | textbook=HIT    |      8 |  -0.625 |  75.00% |  62.50% |   0.00% | 1.000
10 | HARD 16 vs 9 [split-child] | textbook=HIT     |    225 |  -0.587 |  77.33% |  64.89% |  64.89% | 1.000
11 | SOFT 18 vs 11 [split-child] | textbook=HIT    |     12 |  -0.583 |  75.00% |  25.00% |   0.00% | 1.000
12 | HARD 16 vs 11 | textbook=HIT                  |    503 |  -0.563 |  74.75% |  64.21% |  64.21% | 1.000
13 | SOFT 19 vs 8 [split-child] | textbook=STAND   |     25 |  -0.560 |  56.00% |   0.00% |   0.00% | 2.000
14 | HARD 16 vs 10 [split-child] | textbook=HIT    |    776 |  -0.557 |  75.00% |  63.14% |  63.14% | 1.000
15 | HARD 14 vs 9 [split-child] | textbook=HIT     |    273 |  -0.542 |  75.09% |  61.17% |  53.48% | 1.000
16 | HARD 14 vs 11 [split-child] | textbook=HIT    |    185 |  -0.519 |  72.97% |  61.08% |  47.57% | 1.000
17 | HARD 16 vs 11 [split-child] | textbook=HIT    |    160 |  -0.506 |  71.88% |  59.38% |  59.38% | 1.000
18 | HARD 16 vs 9 | textbook=HIT                   |    694 |  -0.506 |  72.33% |  59.65% |  59.65% | 1.000
19 | HARD 17 vs 11 | textbook=STAND                |    459 |  -0.503 |  66.67% |   0.00% |   0.00% | 1.000
20 | HARD 5 vs 3 [split-child] | textbook=HIT      |     20 |  -0.500 |  75.00% |  10.00% |   0.00% | 1.000
21 | SOFT 18 vs 7 [split-child] | textbook=STAND   |     16 |  -0.500 |  62.50% |   0.00% |   0.00% | 2.000
22 | HARD 16 vs 10 | textbook=HIT                  |   2426 |  -0.494 |  71.76% |  59.93% |  59.93% | 1.000
23 | HARD 15 vs 10 | textbook=HIT                  |   2989 |  -0.488 |  71.36% |  57.91% |  53.20% | 1.000
24 | HARD 14 vs 10 | textbook=HIT                  |   2992 |  -0.478 |  70.49% |  56.68% |  47.19% | 1.000
25 | HARD 12 vs 11 [split-child] | textbook=HIT    |    178 |  -0.478 |  70.22% |  57.30% |  33.15% | 1.000


PHASE 3.32 — 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 / -0.099 |   136 / -0.368 |   0.00% /   0.00% | HIT
 2 | SOFT 14 vs 3                       |   106 / -0.132 |   128 / -0.250 |   0.00% /   0.00% | HIT
 3 | HARD 10 vs 11                      |   284 / -0.155 |   294 / -0.116 |   0.00% /   0.00% | HIT
 4 | SOFT 15 vs 2                       |   139 / -0.101 |   153 / -0.157 |   0.00% /   0.00% | HIT
 5 | SOFT 13 vs 2                       |   124 / -0.048 |   134 / -0.164 |   0.00% /   0.00% | HIT
 6 | HARD 9 vs 8                        |   434 / -0.180 |   429 / -0.028 |   0.00% /   0.00% | HIT
 7 | HARD 10 vs 10 [split-child]        |   287 / -0.077 |   241 / -0.017 |   0.00% /   0.00% | HIT
 8 | HARD 10 vs 10                      |  1487 / -0.008 |  1542 / -0.014 |   0.00% /   0.00% | HIT

DESIGN USE
Phase 3.32 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 3.32 — 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 3.32 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 3.32 DECISION RULE
Carry forward split-child HARD 20 STAND, HARD 19 STAND and split-child HARD 18 STAND. ONE additional Phase 3.32 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 3.32 REPLAY FINGERPRINT: 6d213be4ba6e6823ceb90efc1e81ab697b3a137e123e397a373dceac0994241a
