PHASE 3.09 SECOND INTERVENTION RESULTS

PRIMARY
Average ending bankroll Textbook/Selective: 99.956 / 91.986
Maximum bankroll observed Textbook/Selective: 126.0 at hand 29 (session 1777) / 130.0 at hand 30 (session 1543)
Positive sessions Textbook/Selective: 48.14% / 19.56%
Paired winner Textbook/Selective/tie: 77.12% / 21.40% / 1.48%
Doubles Textbook/Selective: 15716 / 104297; splits Textbook/Selective: 3808 / 21727
Mean cards consumed Textbook/Selective: 165.674 / 174.145
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 / 91.741
Maximum bankroll observed Textbook/Selective: 122.5 at hand 24 (session 1273) / 130.0 at hand 18 (session 3473)
Positive sessions Textbook/Selective: 47.42% / 18.66%
Paired winner Textbook/Selective/tie: 77.54% / 20.92% / 1.54%
Doubles Textbook/Selective: 15412 / 104294; splits Textbook/Selective: 3747 / 21770
Mean cards consumed Textbook/Selective: 165.647 / 173.973
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 3.09 — SELECTIVE-AGGRESSION INSTRUMENTATION SUMMARY

PRIMARY resolved selective-aggression hands: 171727; mean net/hand -0.2333; mean committed stake 1.6073; bust rate 16.22%; third-card bust rate when a third card was taken 25.07%.
Textbook would have chosen on those same visible first-decision states: HIT 69972, STAND 68185, DOUBLE 15827.

HOLDOUT resolved selective-aggression hands: 171770; mean net/hand -0.2404; mean committed stake 1.6072; bust rate 16.37%; third-card bust rate when a third card was taken 25.33%.
Textbook would have chosen on those same visible first-decision states: HIT 70290, STAND 67897, DOUBLE 15722.

INTERPRETATION
Phase 3.09 carries forward split-child HARD 20 STAND, HARD 19 STAND, and split-child HARD 18 STAND. It adds one new family only: HARD 16 now follows its dealer-dependent Textbook action instead of automatically DOUBLING. 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 5 vs 11 [split-child] | textbook=HIT     |     14 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 2 | HARD 4 vs 11 [split-child] | textbook=HIT     |      9 |  -1.556 |  88.89% |   0.00% |   0.00% | 2.000
 3 | HARD 4 vs 8 [split-child] | textbook=HIT      |      8 |  -1.500 |  87.50% |   0.00% |   0.00% | 2.000
 4 | HARD 5 vs 11 | textbook=HIT                   |     88 |  -1.455 |  86.36% |   0.00% |   0.00% | 2.000
 5 | HARD 7 vs 11 [split-child] | textbook=HIT     |     30 |  -1.400 |  83.33% |   0.00% |   0.00% | 2.000
 6 | HARD 6 vs 11 | textbook=HIT                   |     99 |  -1.394 |  84.85% |   0.00% |   0.00% | 2.000
 7 | HARD 4 vs 9 [split-child] | textbook=HIT      |     13 |  -1.385 |  84.62% |   0.00% |   0.00% | 2.000
 8 | HARD 6 vs 11 [split-child] | textbook=HIT     |     29 |  -1.310 |  82.76% |   0.00% |   0.00% | 2.000
 9 | HARD 5 vs 9 | textbook=HIT                    |    124 |  -1.290 |  82.26% |   0.00% |   0.00% | 2.000
10 | HARD 5 vs 9 [split-child] | textbook=HIT      |     22 |  -1.273 |  81.82% |   0.00% |   0.00% | 2.000
11 | SOFT 16 vs 3 [split-child] | textbook=HIT     |     21 |  -1.238 |  76.19% |   0.00% |   0.00% | 2.000
12 | HARD 7 vs 8 [split-child] | textbook=HIT      |     38 |  -1.211 |  76.32% |   0.00% |   0.00% | 2.000
13 | HARD 4 vs 7 [split-child] | textbook=HIT      |     10 |  -1.200 |  80.00% |   0.00% |   0.00% | 2.000
14 | HARD 5 vs 10 | textbook=HIT                   |    472 |  -1.161 |  79.03% |   0.00% |   0.00% | 2.000
15 | HARD 7 vs 11 | textbook=HIT                   |    200 |  -1.150 |  75.00% |   0.00% |   0.00% | 2.000
16 | HARD 5 vs 10 [split-child] | textbook=HIT     |     88 |  -1.136 |  78.41% |   0.00% |   0.00% | 2.000
17 | HARD 6 vs 10 [split-child] | textbook=HIT     |    113 |  -1.133 |  77.88% |   0.00% |   0.00% | 2.000
18 | SOFT 15 vs 11 [split-child] | textbook=HIT    |     11 |  -1.091 |  72.73% |   0.00% |   0.00% | 2.000
19 | HARD 6 vs 9 [split-child] | textbook=HIT      |     26 |  -1.077 |  76.92% |   0.00% |   0.00% | 2.000
20 | HARD 13 vs 11 [split-child] | textbook=HIT    |    177 |  -1.073 |  74.58% |  42.37% |  42.37% | 2.000
21 | HARD 6 vs 10 | textbook=HIT                   |    478 |  -1.071 |  76.36% |   0.00% |   0.00% | 2.000
22 | HARD 15 vs 9 [split-child] | textbook=HIT     |    273 |  -1.070 |  73.63% |  55.68% |  55.68% | 2.000
23 | HARD 14 vs 11 [split-child] | textbook=HIT    |    180 |  -1.067 |  74.44% |  48.33% |  48.33% | 2.000
24 | HARD 15 vs 10 | textbook=HIT                  |   3025 |  -1.055 |  73.06% |  53.55% |  53.55% | 2.000
25 | HARD 15 vs 11 [split-child] | textbook=HIT    |    172 |  -1.047 |  71.51% |  59.30% |  59.30% | 2.000

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 2 [split-child] | textbook=HIT      |      7 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 2 | HARD 4 vs 5 [split-child] | textbook=HIT      |      2 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 3 | SOFT 13 vs 2 [split-child] | textbook=HIT     |     12 |  -1.833 |  91.67% |   0.00% |   0.00% | 2.000
 4 | HARD 4 vs 9 [split-child] | textbook=HIT      |     11 |  -1.636 |  90.91% |   0.00% |   0.00% | 2.000
 5 | HARD 4 vs 10 [split-child] | textbook=HIT     |     36 |  -1.444 |  86.11% |   0.00% |   0.00% | 2.000
 6 | HARD 5 vs 11 [split-child] | textbook=HIT     |      7 |  -1.429 |  85.71% |   0.00% |   0.00% | 2.000
 7 | SOFT 15 vs 11 [split-child] | textbook=HIT    |     17 |  -1.412 |  82.35% |   0.00% |   0.00% | 2.000
 8 | SOFT 17 vs 11 [split-child] | textbook=HIT    |     17 |  -1.412 |  82.35% |   0.00% |   0.00% | 2.000
 9 | HARD 7 vs 11 [split-child] | textbook=HIT     |     26 |  -1.385 |  84.62% |   0.00% |   0.00% | 2.000
10 | HARD 6 vs 9 [split-child] | textbook=HIT      |     40 |  -1.350 |  82.50% |   0.00% |   0.00% | 2.000
11 | HARD 7 vs 11 | textbook=HIT                   |    200 |  -1.320 |  81.00% |   0.00% |   0.00% | 2.000
12 | HARD 6 vs 11 | textbook=HIT                   |    101 |  -1.267 |  81.19% |   0.00% |   0.00% | 2.000
13 | HARD 6 vs 8 [split-child] | textbook=HIT      |     38 |  -1.263 |  81.58% |   0.00% |   0.00% | 2.000
14 | HARD 5 vs 10 | textbook=HIT                   |    487 |  -1.195 |  79.88% |   0.00% |   0.00% | 2.000
15 | HARD 5 vs 6 [split-child] | textbook=HIT      |     19 |  -1.158 |  78.95% |   0.00% |   0.00% | 2.000
16 | HARD 7 vs 8 [split-child] | textbook=HIT      |     35 |  -1.143 |  77.14% |   0.00% |   0.00% | 2.000
17 | HARD 6 vs 9 | textbook=HIT                    |    140 |  -1.129 |  77.14% |   0.00% |   0.00% | 2.000
18 | SOFT 16 vs 2 [split-child] | textbook=HIT     |     22 |  -1.091 |  77.27% |   0.00% |   0.00% | 2.000
19 | HARD 8 vs 11 [split-child] | textbook=HIT     |     48 |  -1.083 |  75.00% |   0.00% |   0.00% | 2.000
20 | HARD 6 vs 8 | textbook=HIT                    |    134 |  -1.075 |  76.87% |   0.00% |   0.00% | 2.000
21 | HARD 7 vs 9 [split-child] | textbook=HIT      |     45 |  -1.067 |  73.33% |   0.00% |   0.00% | 2.000
22 | HARD 5 vs 8 [split-child] | textbook=HIT      |     21 |  -1.048 |  76.19% |   0.00% |   0.00% | 2.000
23 | HARD 14 vs 11 [split-child] | textbook=HIT    |    169 |  -1.041 |  73.37% |  43.20% |  43.20% | 2.000
24 | HARD 13 vs 9 [split-child] | textbook=HIT     |    251 |  -1.036 |  73.71% |  45.02% |  45.02% | 2.000
25 | HARD 5 vs 11 | textbook=HIT                   |     90 |  -1.022 |  75.56% |   0.00% |   0.00% | 2.000


PHASE 3.09 — REMAINING REPLICATED DAMAGE STATES AFTER HARD 16 TEXTBOOK-MAPPED FAMILY

Filter: same visible state appears >=100 times in BOTH primary and holdout, and Selective Aggression has negative mean net/hand in BOTH cohorts. This avoids choosing later interventions from tiny-sample extremes.

Rank | State | Primary n / net | Holdout n / net | P bust% / H bust% | Textbook first action
 1 | HARD 7 vs 11                       |   200 / -1.150 |   200 / -1.320 |   0.00% /   0.00% | HIT
 2 | HARD 5 vs 10                       |   472 / -1.161 |   487 / -1.195 |   0.00% /   0.00% | HIT
 3 | HARD 5 vs 9                        |   124 / -1.290 |   154 / -0.987 |   0.00% /   0.00% | HIT
 4 | HARD 14 vs 11 [split-child]        |   180 / -1.067 |   169 / -1.041 |  48.33% /  43.20% | HIT
 5 | HARD 6 vs 9                        |   153 / -0.967 |   140 / -1.129 |   0.00% /   0.00% | HIT
 6 | HARD 6 vs 10                       |   478 / -1.071 |   476 / -1.017 |   0.00% /   0.00% | HIT
 7 | HARD 14 vs 10 [split-child]        |   950 / -1.004 |   977 / -1.019 |  45.79% /  46.57% | HIT
 8 | HARD 15 vs 10                      |  3025 / -1.055 |  3033 / -0.948 |  53.55% /  52.92% | HIT
 9 | HARD 13 vs 9 [split-child]         |   240 / -0.950 |   251 / -1.036 |  40.83% /  45.02% | HIT
10 | HARD 15 vs 9                       |   854 / -0.986 |   847 / -0.999 |  52.11% /  57.02% | HIT
11 | HARD 6 vs 8                        |   148 / -0.905 |   134 / -1.075 |   0.00% /   0.00% | HIT
12 | HARD 15 vs 9 [split-child]         |   273 / -1.070 |   232 / -0.879 |  55.68% /  54.74% | HIT
13 | HARD 15 vs 11                      |   603 / -0.955 |   545 / -0.980 |  56.22% /  54.68% | HIT
14 | HARD 13 vs 11                      |   633 / -0.929 |   676 / -0.967 |  36.49% /  39.05% | HIT
15 | HARD 12 vs 11 [split-child]        |   165 / -0.909 |   198 / -0.970 |  32.73% /  28.79% | HIT
16 | HARD 15 vs 3 [split-child]         |   256 / -0.945 |   264 / -0.924 |  56.64% /  57.20% | STAND
17 | HARD 14 vs 10                      |  2988 / -0.902 |  3045 / -0.960 |  47.02% /  47.00% | HIT
18 | HARD 15 vs 4 [split-child]         |   247 / -0.972 |   230 / -0.887 |  57.89% /  53.48% | STAND
19 | HARD 7 vs 10                       |  1041 / -0.918 |   992 / -0.935 |   0.00% /   0.00% | HIT
20 | HARD 14 vs 9                       |   833 / -0.898 |   830 / -0.940 |  48.98% /  44.94% | HIT

DESIGN USE
Phase 3.09 carries forward the validated split-child HARD 20, HARD 19 and split-child HARD 18 protections and replaces automatic DOUBLE in one structured family: HARD 16 -> corresponding Textbook action. Remaining replicated damage states are retained for later one-rule-at-a-time interventions.

PHASE 3.09 — 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 3.09 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 3.09 DECISION RULE
Carry forward split-child HARD 20 STAND, HARD 19 STAND and split-child HARD 18 STAND. ONE additional Phase 3.09 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 3.09 REPLAY FINGERPRINT: 1eb269f8f31888f8bb4b8be62aee85e7f87772b65ed8e56ff5a11034694c6193
