PHASE 3.16 SECOND INTERVENTION RESULTS

PRIMARY
Average ending bankroll Textbook/Selective: 99.956 / 97.632
Maximum bankroll observed Textbook/Selective: 126.0 at hand 29 (session 1777) / 126.5 at hand 26 (session 2440)
Positive sessions Textbook/Selective: 48.14% / 36.38%
Paired winner Textbook/Selective/tie: 59.48% / 37.74% / 2.78%
Doubles Textbook/Selective: 15716 / 40600; splits Textbook/Selective: 3808 / 21723
Mean cards consumed Textbook/Selective: 165.674 / 175.471
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 / 97.683
Maximum bankroll observed Textbook/Selective: 122.5 at hand 24 (session 1273) / 124.5 at hand 15 (session 3044)
Positive sessions Textbook/Selective: 47.42% / 36.28%
Paired winner Textbook/Selective/tie: 60.12% / 37.22% / 2.66%
Doubles Textbook/Selective: 15412 / 40314; splits Textbook/Selective: 3747 / 21459
Mean cards consumed Textbook/Selective: 165.647 / 175.231
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 3.16 — SELECTIVE-AGGRESSION INSTRUMENTATION SUMMARY

PRIMARY resolved selective-aggression hands: 171723; mean net/hand -0.0689; mean committed stake 1.2364; bust rate 16.36%; third-card bust rate when a third card was taken 21.28%.
Textbook would have chosen on those same visible first-decision states: HIT 70237, STAND 68142, DOUBLE 15797.

HOLDOUT resolved selective-aggression hands: 171459; mean net/hand -0.0676; mean committed stake 1.2351; bust rate 16.35%; third-card bust rate when a third card was taken 21.34%.
Textbook would have chosen on those same visible first-decision states: HIT 69974, STAND 67918, DOUBLE 15831.

INTERPRETATION
Phase 3.16 carries forward split-child HARD 20 STAND, HARD 19 STAND, and split-child HARD 18 STAND. It adds one new family only: SOFT 13-17 vs dealer 7-Ace now HIT 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 4 vs 9 [split-child] | textbook=HIT      |     10 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 2 | HARD 4 vs 11 [split-child] | textbook=HIT     |     10 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 3 | HARD 4 vs 7 [split-child] | textbook=HIT      |     10 |  -1.600 |  90.00% |   0.00% |   0.00% | 2.000
 4 | HARD 4 vs 4 [split-child] | textbook=HIT      |     12 |  -1.333 |  83.33% |   0.00% |   0.00% | 2.000
 5 | HARD 4 vs 10 [split-child] | textbook=HIT     |     37 |  -1.135 |  78.38% |   0.00% |   0.00% | 2.000
 6 | HARD 6 vs 4 [split-child] | textbook=HIT      |     34 |  -1.059 |  76.47% |   0.00% |   0.00% | 2.000
 7 | HARD 4 vs 2 [split-child] | textbook=HIT      |      4 |  -1.000 |  75.00% |   0.00% |   0.00% | 2.000
 8 | HARD 5 vs 2 [split-child] | textbook=HIT      |     25 |  -0.880 |  72.00% |   0.00% |   0.00% | 2.000
 9 | HARD 6 vs 3 [split-child] | textbook=HIT      |     28 |  -0.857 |  71.43% |   0.00% |   0.00% | 2.000
10 | HARD 5 vs 3 | textbook=HIT                    |    127 |  -0.772 |  69.29% |   0.00% |   0.00% | 2.000
11 | SOFT 18 vs 11 [split-child] | textbook=HIT    |     14 |  -0.714 |  57.14% |   0.00% |   0.00% | 2.000
12 | SOFT 18 vs 2 [split-child] | textbook=STAND   |      9 |  -0.667 |  66.67% |   0.00% |   0.00% | 2.000
13 | HARD 4 vs 5 [split-child] | textbook=HIT      |      3 |  -0.667 |  66.67% |   0.00% |   0.00% | 2.000
14 | HARD 6 vs 5 | textbook=HIT                    |    136 |  -0.662 |  66.18% |   0.00% |   0.00% | 2.000
15 | HARD 5 vs 2 | textbook=HIT                    |    122 |  -0.656 |  66.39% |   0.00% |   0.00% | 2.000
16 | HARD 12 vs 2 [split-child] | textbook=HIT     |    284 |  -0.648 |  63.38% |  29.23% |  29.23% | 2.000
17 | SOFT 14 vs 2 [split-child] | textbook=HIT     |     22 |  -0.636 |  63.64% |   0.00% |   0.00% | 2.000
18 | HARD 7 vs 11 [split-child] | textbook=HIT     |     29 |  -0.621 |  72.41% |  44.83% |   0.00% | 1.000
19 | HARD 9 vs 9 [split-child] | textbook=HIT      |     46 |  -0.609 |  60.87% |   0.00% |   0.00% | 2.000
20 | HARD 5 vs 9 [split-child] | textbook=HIT      |     23 |  -0.609 |  78.26% |  65.22% |   0.00% | 1.000
21 | SOFT 19 vs 11 [split-child] | textbook=STAND  |     10 |  -0.600 |  60.00% |   0.00% |   0.00% | 2.000
22 | HARD 6 vs 8 [split-child] | textbook=HIT      |     27 |  -0.593 |  74.07% |  62.96% |   0.00% | 1.000
23 | HARD 8 vs 2 [split-child] | textbook=HIT      |     48 |  -0.583 |  60.42% |   0.00% |   0.00% | 2.000
24 | HARD 16 vs 10 [split-child] | textbook=HIT    |    872 |  -0.575 |  75.92% |  62.73% |  62.73% | 1.000
25 | HARD 14 vs 11 [split-child] | textbook=HIT    |    190 |  -0.574 |  74.74% |  64.21% |  52.11% | 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      |      4 |  -2.000 | 100.00% |   0.00% |   0.00% | 2.000
 2 | HARD 4 vs 8 [split-child] | textbook=HIT      |      8 |  -1.500 |  87.50% |   0.00% |   0.00% | 2.000
 3 | HARD 4 vs 11 [split-child] | textbook=HIT     |     15 |  -1.467 |  86.67% |   0.00% |   0.00% | 2.000
 4 | HARD 6 vs 2 [split-child] | textbook=HIT      |     34 |  -1.412 |  85.29% |   0.00% |   0.00% | 2.000
 5 | HARD 4 vs 9 [split-child] | textbook=HIT      |     11 |  -1.273 |  81.82% |   0.00% |   0.00% | 2.000
 6 | HARD 4 vs 10 [split-child] | textbook=HIT     |     31 |  -1.226 |  80.65% |   0.00% |   0.00% | 2.000
 7 | HARD 4 vs 5 [split-child] | textbook=HIT      |      8 |  -1.000 |  75.00% |   0.00% |   0.00% | 2.000
 8 | HARD 5 vs 3 [split-child] | textbook=HIT      |     20 |  -0.800 |  70.00% |   0.00% |   0.00% | 2.000
 9 | HARD 4 vs 6 [split-child] | textbook=HIT      |     10 |  -0.800 |  70.00% |   0.00% |   0.00% | 2.000
10 | SOFT 13 vs 2 [split-child] | textbook=HIT     |     18 |  -0.778 |  61.11% |   0.00% |   0.00% | 2.000
11 | HARD 5 vs 11 [split-child] | textbook=HIT     |      7 |  -0.714 |  85.71% |  57.14% |   0.00% | 1.000
12 | HARD 5 vs 2 | textbook=HIT                    |    129 |  -0.667 |  66.67% |   0.00% |   0.00% | 2.000
13 | HARD 7 vs 6 [split-child] | textbook=HIT      |     33 |  -0.667 |  63.64% |   0.00% |   0.00% | 2.000
14 | SOFT 16 vs 2 [split-child] | textbook=HIT     |     24 |  -0.667 |  66.67% |   0.00% |   0.00% | 2.000
15 | HARD 7 vs 4 [split-child] | textbook=HIT      |     46 |  -0.652 |  65.22% |   0.00% |   0.00% | 2.000
16 | HARD 6 vs 2 | textbook=HIT                    |    120 |  -0.650 |  65.83% |   0.00% |   0.00% | 2.000
17 | HARD 9 vs 10 [split-child] | textbook=HIT     |    243 |  -0.642 |  60.91% |   0.00% |   0.00% | 2.000
18 | HARD 5 vs 5 | textbook=HIT                    |    126 |  -0.635 |  65.87% |   0.00% |   0.00% | 2.000
19 | HARD 6 vs 3 | textbook=HIT                    |    132 |  -0.621 |  63.64% |   0.00% |   0.00% | 2.000
20 | HARD 6 vs 6 [split-child] | textbook=HIT      |     33 |  -0.606 |  63.64% |   0.00% |   0.00% | 2.000
21 | HARD 5 vs 6 [split-child] | textbook=HIT      |     20 |  -0.600 |  65.00% |   0.00% |   0.00% | 2.000
22 | HARD 16 vs 9 [split-child] | textbook=HIT     |    223 |  -0.596 |  77.58% |  65.47% |  65.47% | 1.000
23 | HARD 5 vs 3 | textbook=HIT                    |    128 |  -0.594 |  64.84% |   0.00% |   0.00% | 2.000
24 | SOFT 17 vs 11 [split-child] | textbook=HIT    |     14 |  -0.571 |  71.43% |  28.57% |   0.00% | 1.000
25 | HARD 16 vs 10 [split-child] | textbook=HIT    |    784 |  -0.563 |  75.00% |  63.01% |  63.01% | 1.000


PHASE 3.16 — REMAINING REPLICATED DAMAGE STATES AFTER SOFT 13-17 vs 7-ACE HIT 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 5 vs 3                        |   127 / -0.772 |   128 / -0.594 |   0.00% /   0.00% | HIT
 2 | HARD 5 vs 2                        |   122 / -0.656 |   129 / -0.667 |   0.00% /   0.00% | HIT
 3 | HARD 12 vs 2 [split-child]         |   284 / -0.648 |   282 / -0.496 |  29.23% /  26.95% | HIT
 4 | HARD 16 vs 10 [split-child]        |   872 / -0.575 |   784 / -0.563 |  62.73% /  63.01% | HIT
 5 | HARD 16 vs 9 [split-child]         |   240 / -0.513 |   223 / -0.596 |  61.25% /  65.47% | HIT
 6 | HARD 12 vs 3 [split-child]         |   326 / -0.552 |   310 / -0.523 |  28.83% /  30.97% | HIT
 7 | HARD 6 vs 3                        |   142 / -0.451 |   132 / -0.621 |   0.00% /   0.00% | HIT
 8 | HARD 9 vs 10 [split-child]         |   261 / -0.429 |   243 / -0.642 |   0.00% /   0.00% | HIT
 9 | HARD 16 vs 11                      |   510 / -0.508 |   514 / -0.551 |  62.16% /  64.79% | HIT
10 | HARD 16 vs 11 [split-child]        |   141 / -0.511 |   156 / -0.532 |  63.12% /  59.62% | HIT
11 | HARD 16 vs 9                       |   717 / -0.526 |   683 / -0.512 |  64.02% /  60.91% | HIT
12 | HARD 14 vs 11 [split-child]        |   190 / -0.574 |   177 / -0.446 |  64.21% /  57.06% | HIT
13 | HARD 16 vs 10                      |  2580 / -0.510 |  2415 / -0.506 |  60.04% /  61.12% | HIT
14 | HARD 15 vs 10                      |  2928 / -0.524 |  2962 / -0.491 |  58.95% /  57.53% | HIT
15 | HARD 12 vs 3                       |   910 / -0.475 |   980 / -0.516 |  29.89% /  30.92% | HIT
16 | HARD 14 vs 9 [split-child]         |   264 / -0.443 |   260 / -0.515 |  54.17% /  60.00% | HIT
17 | HARD 12 vs 2                       |   936 / -0.483 |   946 / -0.471 |  33.23% /  30.76% | HIT
18 | HARD 14 vs 10 [split-child]        |   953 / -0.488 |   913 / -0.464 |  55.82% /  54.11% | HIT
19 | HARD 17 vs 11                      |   460 / -0.450 |   476 / -0.494 |   0.00% /   0.00% | STAND
20 | HARD 14 vs 10                      |  3117 / -0.476 |  2977 / -0.467 |  57.39% /  56.26% | HIT

DESIGN USE
Phase 3.16 carries forward the validated split-child HARD 20, HARD 19 and split-child HARD 18 protections and replaces automatic DOUBLE in one soft-hand family: SOFT 13-17 vs dealer 7-Ace -> HIT. Remaining replicated damage states are retained for later one-rule-at-a-time interventions.

PHASE 3.16 — 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 3.16 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 3.16 DECISION RULE
Carry forward split-child HARD 20 STAND, HARD 19 STAND and split-child HARD 18 STAND. ONE additional Phase 3.16 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 3.16 REPLAY FINGERPRINT: a20de4cc0862e19bdb6b40a7d5e04cab3d93e35e1175a9d99e42a40481c0bded
