devils-agent / reports /policy-browser-novel-v002.json
devildasdf's picture
Upload experimental BAIM code, research checkpoints and measured evaluations
795f737 verified
Raw History Blame Contribute Delete
52.7 kB
{
"checkpoint": "models/v002-gru",
"quantized": false,
"platform": "Windows-11-10.0.26200-SP0",
"torch_threads": 2,
"model_load_ms": 8.020800072699785,
"samples": 120,
"success_rate": 0.39166666666666666,
"abstention_rate": 0.4,
"median_observation_ms": 14.639450004324317,
"median_policy_ms": 5.642850010190159,
"median_execution_ms": 15.774849976878613,
"scope": "single-step generated browser fixtures, held-out layout templates; not arbitrary websites",
"target_vps_validated": false,
"results": [
{
"sample_id": 0,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9106427431106567,
"observation_ms": 44.24660000950098,
"policy_ms": 7.870400091633201,
"execution_ms": 3.6689999978989363,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 1,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9873443841934204,
"target_confidence": 0.9999971389770508,
"observation_ms": 14.778300072066486,
"policy_ms": 6.43149996176362,
"execution_ms": 43.75750001054257,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 2,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9888303875923157,
"target_confidence": 1.0,
"observation_ms": 36.495500011369586,
"policy_ms": 5.358200054615736,
"execution_ms": 22.587800049223006,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 3,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9998986721038818,
"observation_ms": 15.025699976831675,
"policy_ms": 4.462999990209937,
"execution_ms": 3.001399920322001,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 4,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9679258465766907,
"observation_ms": 16.171199968084693,
"policy_ms": 5.426099989563227,
"execution_ms": 2.8247000882402062,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 5,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9498040080070496,
"observation_ms": 15.62059996649623,
"policy_ms": 6.210600025951862,
"execution_ms": 18.92640010919422,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 6,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.999823272228241,
"observation_ms": 19.638199941255152,
"policy_ms": 6.917600054293871,
"execution_ms": 19.17179999873042,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 7,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9934561848640442,
"observation_ms": 14.618700020946562,
"policy_ms": 5.980800022371113,
"execution_ms": 17.47959991917014,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 8,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9882636070251465,
"observation_ms": 16.187299974262714,
"policy_ms": 7.8931000316515565,
"execution_ms": 18.755099968984723,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 9,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.6589809656143188,
"target_confidence": 0.999976634979248,
"observation_ms": 15.046400018036366,
"policy_ms": 6.1913999961689115,
"execution_ms": 2.5551000144332647,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 10,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9514384269714355,
"observation_ms": 15.801900066435337,
"policy_ms": 5.364800104871392,
"execution_ms": 19.60490003693849,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 11,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9992782473564148,
"observation_ms": 14.57150001078844,
"policy_ms": 5.289900000207126,
"execution_ms": 2.4638999020680785,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 12,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9710627198219299,
"observation_ms": 14.585500000976026,
"policy_ms": 5.454499972984195,
"execution_ms": 17.143300035968423,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 13,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.6948939561843872,
"observation_ms": 14.131800038740039,
"policy_ms": 5.039899959228933,
"execution_ms": 2.332399948500097,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 14,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.882300096563995,
"policy_ms": 4.618899896740913,
"execution_ms": 19.744499935768545,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 15,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.628600001335144,
"policy_ms": 5.319400108419359,
"execution_ms": 17.34090002719313,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 16,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9597891569137573,
"observation_ms": 15.164899989031255,
"policy_ms": 6.308699958026409,
"execution_ms": 16.590299899689853,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 17,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 20.442000008188188,
"policy_ms": 14.638499938882887,
"execution_ms": 25.483200093731284,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 18,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9969860911369324,
"observation_ms": 22.283100057393312,
"policy_ms": 8.245299919508398,
"execution_ms": 3.1480001052841544,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 19,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.50219995342195,
"policy_ms": 5.641499999910593,
"execution_ms": 20.024199970066547,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 20,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9956907629966736,
"observation_ms": 21.485199918970466,
"policy_ms": 10.731799993664026,
"execution_ms": 3.246000036597252,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 21,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9999998807907104,
"target_confidence": 0.9992986917495728,
"observation_ms": 21.41929999925196,
"policy_ms": 5.92360005248338,
"execution_ms": 3.3164999913424253,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 22,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.8012701869010925,
"observation_ms": 19.006700022146106,
"policy_ms": 6.379799917340279,
"execution_ms": 3.13510000705719,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 23,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.0764999454841,
"policy_ms": 5.175700061954558,
"execution_ms": 20.086499978788197,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 24,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.6497063636779785,
"observation_ms": 17.871599993668497,
"policy_ms": 5.860900040715933,
"execution_ms": 2.8192000463604927,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 25,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.6710407137870789,
"observation_ms": 15.921200043521821,
"policy_ms": 4.068300011567771,
"execution_ms": 3.2719000009819865,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 26,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9805163741111755,
"observation_ms": 15.411500004120171,
"policy_ms": 6.655100034549832,
"execution_ms": 16.829799977131188,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 27,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9994151592254639,
"observation_ms": 13.451500097289681,
"policy_ms": 3.9328999118879437,
"execution_ms": 17.0963000273332,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 28,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 13.573499978519976,
"policy_ms": 4.711700021289289,
"execution_ms": 16.50489994790405,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 29,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9940434098243713,
"observation_ms": 14.351799967698753,
"policy_ms": 4.563600057736039,
"execution_ms": 2.69210000988096,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 30,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999980926513672,
"observation_ms": 16.997999977320433,
"policy_ms": 8.311899960972369,
"execution_ms": 18.91580002848059,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 31,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.44539991300553,
"policy_ms": 5.644200020469725,
"execution_ms": 18.05759989656508,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 32,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999985694885254,
"observation_ms": 15.494500054046512,
"policy_ms": 4.54239989630878,
"execution_ms": 16.404900001361966,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 33,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.381199911236763,
"policy_ms": 4.269700031727552,
"execution_ms": 2.302700071595609,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 34,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9988446235656738,
"target_confidence": 0.999969482421875,
"observation_ms": 15.084499958902597,
"policy_ms": 6.35020004119724,
"execution_ms": 11.644899961538613,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 35,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.976399972103536,
"policy_ms": 6.781600066460669,
"execution_ms": 2.4924000026658177,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 36,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.151700026355684,
"policy_ms": 6.173499976284802,
"execution_ms": 18.531200010329485,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 37,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.123800072818995,
"policy_ms": 9.156499989330769,
"execution_ms": 19.456699956208467,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 38,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9331730604171753,
"target_confidence": 0.9992374181747437,
"observation_ms": 16.19349990505725,
"policy_ms": 5.165400099940598,
"execution_ms": 11.042700032703578,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 39,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.94921875,
"observation_ms": 13.69160006288439,
"policy_ms": 5.2671999437734485,
"execution_ms": 20.551699912175536,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 40,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.8621384501457214,
"observation_ms": 14.68430005479604,
"policy_ms": 5.860799923539162,
"execution_ms": 2.53950001206249,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 41,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.169800047762692,
"policy_ms": 5.166899994947016,
"execution_ms": 19.90090007893741,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 42,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999990463256836,
"observation_ms": 16.215500072576106,
"policy_ms": 5.8868000051006675,
"execution_ms": 15.761999995447695,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 43,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.84250000026077,
"policy_ms": 4.4160999823361635,
"execution_ms": 15.85169997997582,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 44,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9755481481552124,
"observation_ms": 18.474900047294796,
"policy_ms": 6.045799935236573,
"execution_ms": 2.5333999656140804,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 45,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.774900067597628,
"policy_ms": 4.94549993891269,
"execution_ms": 15.691899927332997,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 46,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999706745147705,
"observation_ms": 13.911699992604554,
"policy_ms": 5.272399983368814,
"execution_ms": 15.609099995344877,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 47,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9941600561141968,
"observation_ms": 13.88399989809841,
"policy_ms": 5.4524000734090805,
"execution_ms": 16.107400064356625,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 48,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999527931213379,
"observation_ms": 12.878799927420914,
"policy_ms": 4.389000008814037,
"execution_ms": 15.67819993942976,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 49,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999653100967407,
"observation_ms": 12.603000039234757,
"policy_ms": 4.5912000350654125,
"execution_ms": 15.382300014607608,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 50,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.26609996613115,
"policy_ms": 4.6440999722108245,
"execution_ms": 2.288100076839328,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 51,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.426000019535422,
"policy_ms": 5.947500001639128,
"execution_ms": 16.165500041097403,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 52,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999997615814209,
"observation_ms": 12.6547000836581,
"policy_ms": 4.678700002841651,
"execution_ms": 17.162400064989924,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 53,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9989532232284546,
"observation_ms": 14.350200071930885,
"policy_ms": 5.14120003208518,
"execution_ms": 2.3252000100910664,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 54,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9810065031051636,
"target_confidence": 0.998680055141449,
"observation_ms": 14.452700037509203,
"policy_ms": 6.582799949683249,
"execution_ms": 18.378900014795363,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 55,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999997615814209,
"observation_ms": 15.689300023950636,
"policy_ms": 5.696299951523542,
"execution_ms": 18.688600044697523,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 56,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999995231628418,
"observation_ms": 15.179599984548986,
"policy_ms": 7.325300015509129,
"execution_ms": 2.467700047418475,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 57,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.71820003259927,
"policy_ms": 6.719099939800799,
"execution_ms": 2.520799986086786,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 58,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.816499944776297,
"policy_ms": 5.723300040699542,
"execution_ms": 16.337000066414475,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 59,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.891999959014356,
"policy_ms": 5.145099945366383,
"execution_ms": 15.593699994497001,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 60,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999799728393555,
"observation_ms": 13.682099990546703,
"policy_ms": 4.811599967069924,
"execution_ms": 16.774000017903745,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 61,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.277099980972707,
"policy_ms": 8.364200009964406,
"execution_ms": 19.13380005862564,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 62,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.8035814762115479,
"observation_ms": 15.815299935638905,
"policy_ms": 5.672300001606345,
"execution_ms": 2.436299924738705,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 63,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9838116765022278,
"observation_ms": 14.660199987702072,
"policy_ms": 5.406700074672699,
"execution_ms": 2.404000028036535,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 64,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9968637228012085,
"observation_ms": 14.243200072087348,
"policy_ms": 5.423899972811341,
"execution_ms": 15.442600008100271,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 65,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 13.283299980685115,
"policy_ms": 4.714200040325522,
"execution_ms": 2.179000061005354,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 66,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.8451939821243286,
"observation_ms": 15.359399956651032,
"policy_ms": 5.572100053541362,
"execution_ms": 2.367699984461069,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 67,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.154100044630468,
"policy_ms": 5.556099931709468,
"execution_ms": 17.591699957847595,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 68,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.526800041086972,
"policy_ms": 4.182599950581789,
"execution_ms": 2.3926999419927597,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 69,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9994825124740601,
"observation_ms": 14.410000061616302,
"policy_ms": 5.191099946387112,
"execution_ms": 2.831999910995364,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 70,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9999996423721313,
"target_confidence": 0.9999701976776123,
"observation_ms": 14.026100048795342,
"policy_ms": 5.702499998733401,
"execution_ms": 2.484200056642294,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 71,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9580230712890625,
"observation_ms": 12.456300086341798,
"policy_ms": 4.1102000977844,
"execution_ms": 15.295200049877167,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 72,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.999990701675415,
"observation_ms": 14.332700055092573,
"policy_ms": 5.6705999886617064,
"execution_ms": 16.608400037512183,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 73,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.999998927116394,
"observation_ms": 11.805300018750131,
"policy_ms": 5.159699940122664,
"execution_ms": 15.969399944879115,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 74,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.9997367262840271,
"target_confidence": 0.5425891280174255,
"observation_ms": 15.75839996803552,
"policy_ms": 5.910899955779314,
"execution_ms": 2.4791999021545053,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 75,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999966621398926,
"observation_ms": 12.371599907055497,
"policy_ms": 4.641800071112812,
"execution_ms": 16.78669999819249,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 76,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.665900052525103,
"policy_ms": 4.241300048306584,
"execution_ms": 15.841100015677512,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 77,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.91079998575151,
"policy_ms": 7.136700092814863,
"execution_ms": 16.29639999009669,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 78,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.315700042061508,
"policy_ms": 5.353999906219542,
"execution_ms": 16.416999977082014,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 79,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 17.127800034359097,
"policy_ms": 8.579300018027425,
"execution_ms": 16.487499931827188,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 80,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.218700001947582,
"policy_ms": 5.369900027289987,
"execution_ms": 2.751899999566376,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 81,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999608993530273,
"observation_ms": 15.178900095634162,
"policy_ms": 5.437299958430231,
"execution_ms": 2.516100066713989,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 82,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9960330128669739,
"observation_ms": 15.121700009331107,
"policy_ms": 5.732999998144805,
"execution_ms": 2.6709999656304717,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 83,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.9999986886978149,
"target_confidence": 0.8480029702186584,
"observation_ms": 13.722400064580142,
"policy_ms": 6.257299915887415,
"execution_ms": 2.3250000085681677,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 84,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9913052916526794,
"observation_ms": 15.474800020456314,
"policy_ms": 5.90430002193898,
"execution_ms": 16.301500028930604,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 85,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9209082722663879,
"observation_ms": 14.292799984104931,
"policy_ms": 6.63459999486804,
"execution_ms": 16.415800084359944,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 86,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 12.9893000703305,
"policy_ms": 4.4371000258252025,
"execution_ms": 2.466200035996735,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 87,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.5589049458503723,
"observation_ms": 15.525400056503713,
"policy_ms": 7.321100099943578,
"execution_ms": 2.8237999649718404,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 88,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9998763799667358,
"observation_ms": 15.69139992352575,
"policy_ms": 5.579799995757639,
"execution_ms": 2.516699954867363,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 89,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9988917708396912,
"observation_ms": 17.7850000327453,
"policy_ms": 6.633299984969199,
"execution_ms": 16.517199925146997,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 90,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999994039535522,
"observation_ms": 15.42800001334399,
"policy_ms": 6.517100031487644,
"execution_ms": 2.6801000349223614,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 91,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999995231628418,
"target_confidence": 0.999991774559021,
"observation_ms": 18.885600031353533,
"policy_ms": 7.807799964211881,
"execution_ms": 21.415700088255107,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 92,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9968438148498535,
"observation_ms": 15.483899973332882,
"policy_ms": 6.061500054784119,
"execution_ms": 16.276399954222143,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 93,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.5529961585998535,
"observation_ms": 12.816700036637485,
"policy_ms": 4.880900029093027,
"execution_ms": 2.2583999671041965,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 94,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9746989607810974,
"observation_ms": 14.847400016151369,
"policy_ms": 8.308400050736964,
"execution_ms": 2.891700016334653,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 95,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.6894709467887878,
"observation_ms": 13.81010003387928,
"policy_ms": 7.412100094370544,
"execution_ms": 2.658099983818829,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 96,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9780493378639221,
"target_confidence": 1.0,
"observation_ms": 15.902300016023219,
"policy_ms": 5.481399944983423,
"execution_ms": 16.780099947936833,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 97,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.5665366649627686,
"target_confidence": 0.9999916553497314,
"observation_ms": 13.692499953322113,
"policy_ms": 5.062200012616813,
"execution_ms": 2.353199990466237,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 98,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.573700048960745,
"policy_ms": 6.14269997458905,
"execution_ms": 18.901500036008656,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 99,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999967813491821,
"observation_ms": 19.381299964152277,
"policy_ms": 5.829700035974383,
"execution_ms": 2.478900016285479,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 100,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9519977569580078,
"observation_ms": 14.208900043740869,
"policy_ms": 5.3721999283879995,
"execution_ms": 2.4892999790608883,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 101,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 11.710799997672439,
"policy_ms": 4.391100024804473,
"execution_ms": 2.3975000949576497,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 102,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999699592590332,
"target_confidence": 0.9877586960792542,
"observation_ms": 16.78659999743104,
"policy_ms": 6.5367999486625195,
"execution_ms": 16.190700000151992,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 103,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9960851669311523,
"target_confidence": 0.9997296929359436,
"observation_ms": 13.554899953305721,
"policy_ms": 3.9613000117242336,
"execution_ms": 17.097899923101068,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 104,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9994691014289856,
"observation_ms": 14.564899960532784,
"policy_ms": 5.859700031578541,
"execution_ms": 15.829900046810508,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 105,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 0.9999922513961792,
"observation_ms": 12.78019999153912,
"policy_ms": 3.944299998693168,
"execution_ms": 16.73899998422712,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 106,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999992847442627,
"observation_ms": 15.06660005543381,
"policy_ms": 5.027799983508885,
"execution_ms": 11.834000004455447,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 107,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 16.96310006082058,
"policy_ms": 6.54430000577122,
"execution_ms": 17.723500030115247,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 108,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 17.147900070995092,
"policy_ms": 6.6255999263376,
"execution_ms": 2.570000011473894,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 109,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9680730104446411,
"target_confidence": 0.9812092185020447,
"observation_ms": 13.616799958981574,
"policy_ms": 5.672800005413592,
"execution_ms": 16.66189997922629,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 110,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.796399998478591,
"policy_ms": 4.303400055505335,
"execution_ms": 16.243300051428378,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 111,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.10790006816387,
"policy_ms": 6.166999926790595,
"execution_ms": 15.69439994636923,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 112,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999850988388062,
"target_confidence": 0.9864395260810852,
"observation_ms": 15.109900035895407,
"policy_ms": 4.6709999442100525,
"execution_ms": 17.726799938827753,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 113,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9999536275863647,
"observation_ms": 14.065099996514618,
"policy_ms": 5.889200023375452,
"execution_ms": 2.464100020006299,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 114,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.09929991234094,
"policy_ms": 6.019800086505711,
"execution_ms": 15.787699958309531,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 115,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9998906850814819,
"target_confidence": 1.0,
"observation_ms": 12.961399974301457,
"policy_ms": 6.4616999588906765,
"execution_ms": 17.88450009189546,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 116,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.8286662697792053,
"target_confidence": 0.9999352693557739,
"observation_ms": 15.840500011108816,
"policy_ms": 5.301999975927174,
"execution_ms": 2.3964999709278345,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 117,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.605000054463744,
"policy_ms": 4.79289994109422,
"execution_ms": 2.412299974821508,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 118,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.805299997329712,
"policy_ms": 5.196699989028275,
"execution_ms": 16.23519998975098,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 119,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.033100033178926,
"policy_ms": 6.443300051614642,
"execution_ms": 15.90520003810525,
"status": "ok",
"code": "SELECT"
}
]
}