devils-agent / reports /browser-v004-novel.json
devildasdf's picture
Add trained contextual action candidate with browser evaluation and explicit real-web limits
c8e5620 verified
Raw History Blame Contribute Delete
52 kB
{
"checkpoint": "models/v004-contextual",
"quantized": false,
"platform": "Windows-11-10.0.26200-SP0",
"torch_threads": 2,
"model_load_ms": 94.63169996161014,
"samples": 120,
"success_rate": 0.8166666666666667,
"abstention_rate": 0.10833333333333334,
"median_observation_ms": 19.925549917388707,
"median_policy_ms": 2.0463999826461077,
"median_execution_ms": 23.863700043875724,
"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": 0.997082531452179,
"target_confidence": 0.9630829095840454,
"observation_ms": 52.04129999037832,
"policy_ms": 3.6001999396830797,
"execution_ms": 24.167499970644712,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 1,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 17.381199984811246,
"policy_ms": 1.756099984049797,
"execution_ms": 64.2642000457272,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 2,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 41.61069996189326,
"policy_ms": 2.2362000308930874,
"execution_ms": 25.761299999430776,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 3,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.043700023554265,
"policy_ms": 1.3657000381499529,
"execution_ms": 80.96819999627769,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 4,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 23.297299980185926,
"policy_ms": 1.9205999560654163,
"execution_ms": 62.41819995921105,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 5,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 0.8784183263778687,
"observation_ms": 21.74580004066229,
"policy_ms": 2.3895999183878303,
"execution_ms": 20.609600003808737,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 6,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999873638153076,
"observation_ms": 27.131599956192076,
"policy_ms": 2.516700071282685,
"execution_ms": 28.519999934360385,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 7,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9832378625869751,
"observation_ms": 18.569599953480065,
"policy_ms": 1.7714999848976731,
"execution_ms": 20.5024000024423,
"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": 1.0,
"observation_ms": 18.716900027357042,
"policy_ms": 2.2554000606760383,
"execution_ms": 20.574199967086315,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 9,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.976699931547046,
"policy_ms": 1.9339000573381782,
"execution_ms": 27.41740003693849,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 10,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.524899962358177,
"policy_ms": 1.7152000218629837,
"execution_ms": 22.37550006248057,
"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": 0.5470258593559265,
"observation_ms": 18.770999973639846,
"policy_ms": 1.7818000633269548,
"execution_ms": 3.050200059078634,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 12,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9996076226234436,
"target_confidence": 0.9999998807907104,
"observation_ms": 18.240800010971725,
"policy_ms": 1.6741000581532717,
"execution_ms": 14.110499992966652,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 13,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.17189999949187,
"policy_ms": 2.1422000136226416,
"execution_ms": 50.70220003835857,
"status": "ok",
"code": "CLICK"
},
{
"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": 18.85320001747459,
"policy_ms": 2.1046000765636563,
"execution_ms": 25.676199933514,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 15,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9997895359992981,
"target_confidence": 1.0,
"observation_ms": 15.526799950748682,
"policy_ms": 1.6744000604376197,
"execution_ms": 19.506199983879924,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 16,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9971709847450256,
"observation_ms": 19.791599945165217,
"policy_ms": 2.011900069192052,
"execution_ms": 21.349199931137264,
"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": 1.0,
"observation_ms": 19.411099958233535,
"policy_ms": 1.8891999498009682,
"execution_ms": 21.164899924769998,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 18,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.839700031094253,
"policy_ms": 1.5915000112727284,
"execution_ms": 70.20590000320226,
"status": "ok",
"code": "CLICK"
},
{
"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": 22.31109992135316,
"policy_ms": 1.941800001077354,
"execution_ms": 21.803799900226295,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 20,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.659999943338335,
"policy_ms": 2.439300063997507,
"execution_ms": 51.54939997009933,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 21,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.627000062726438,
"policy_ms": 2.043199958279729,
"execution_ms": 54.44460001308471,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 22,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.43720004055649,
"policy_ms": 2.0836000330746174,
"execution_ms": 52.542699966579676,
"status": "ok",
"code": "CLICK"
},
{
"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": 17.43700006045401,
"policy_ms": 1.8903999589383602,
"execution_ms": 22.533199982717633,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 24,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.37820005696267,
"policy_ms": 1.7327999230474234,
"execution_ms": 48.637299914844334,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 25,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.0386000322178,
"policy_ms": 1.8211998976767063,
"execution_ms": 32.63259993400425,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 26,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 31.693299999460578,
"policy_ms": 4.196699941530824,
"execution_ms": 34.208000055514276,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 27,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.203899941407144,
"policy_ms": 1.6080000204965472,
"execution_ms": 23.110900074243546,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 28,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.319100072607398,
"policy_ms": 1.617099973373115,
"execution_ms": 27.02000003773719,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 29,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.1315999943763,
"policy_ms": 1.984399976208806,
"execution_ms": 61.0787000041455,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 30,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999998807907104,
"target_confidence": 0.9999998807907104,
"observation_ms": 24.716699961572886,
"policy_ms": 2.7118000434711576,
"execution_ms": 20.71119996253401,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 19.431499997153878,
"policy_ms": 1.9639000529423356,
"execution_ms": 21.217299974523485,
"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": 0.999996542930603,
"observation_ms": 17.129699932411313,
"policy_ms": 1.640500035136938,
"execution_ms": 20.674900035373867,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 33,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9980350136756897,
"target_confidence": 0.99998939037323,
"observation_ms": 15.770700061693788,
"policy_ms": 1.789200003258884,
"execution_ms": 3.0932999216020107,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 34,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.88559991493821,
"policy_ms": 2.4881999706849456,
"execution_ms": 21.22969995252788,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 35,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 17.057199962437153,
"policy_ms": 2.530900062993169,
"execution_ms": 35.879299975931644,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 36,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9625697731971741,
"target_confidence": 1.0,
"observation_ms": 19.18990002013743,
"policy_ms": 2.424499951303005,
"execution_ms": 25.121700018644333,
"status": "ok",
"code": "TYPE"
},
{
"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": 23.415900068357587,
"policy_ms": 2.4779000086709857,
"execution_ms": 23.03289994597435,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 38,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.38509999308735,
"policy_ms": 1.792999915778637,
"execution_ms": 21.66259998921305,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 39,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9615044593811035,
"observation_ms": 17.784499912522733,
"policy_ms": 1.5483000315725803,
"execution_ms": 13.7020000256598,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 40,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9991171956062317,
"target_confidence": 0.8294482827186584,
"observation_ms": 18.787800101563334,
"policy_ms": 2.069000038318336,
"execution_ms": 3.284999984316528,
"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": 18.18359992466867,
"policy_ms": 1.8230000277981162,
"execution_ms": 23.239500005729496,
"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": 1.0,
"observation_ms": 21.46099996753037,
"policy_ms": 2.3865000111982226,
"execution_ms": 26.55770001001656,
"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": 20.84760006982833,
"policy_ms": 1.6396999126300216,
"execution_ms": 27.551600011065602,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 44,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 59.78959996718913,
"policy_ms": 2.021700027398765,
"execution_ms": 45.08690000511706,
"status": "ok",
"code": "CLICK"
},
{
"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": 18.197900033555925,
"policy_ms": 1.7804999370127916,
"execution_ms": 23.228899925015867,
"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": 1.0,
"observation_ms": 20.208099973388016,
"policy_ms": 1.6938999760895967,
"execution_ms": 22.70880003925413,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 47,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9346925020217896,
"target_confidence": 0.9996263980865479,
"observation_ms": 19.146199920214713,
"policy_ms": 1.9916000310331583,
"execution_ms": 14.529700041748583,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 48,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9997907280921936,
"target_confidence": 1.0,
"observation_ms": 18.851600005291402,
"policy_ms": 1.7500000540167093,
"execution_ms": 22.093100007623434,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 49,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 16.993399942293763,
"policy_ms": 1.2751000467687845,
"execution_ms": 22.90139999240637,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 50,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.416999934241176,
"policy_ms": 1.7480000387877226,
"execution_ms": 55.009900010190904,
"status": "ok",
"code": "CLICK"
},
{
"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": 19.035200006328523,
"policy_ms": 1.66229996830225,
"execution_ms": 22.664399934001267,
"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": 1.0,
"observation_ms": 20.522900042124093,
"policy_ms": 1.9642000552266836,
"execution_ms": 22.66699995379895,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 53,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.8216633796691895,
"target_confidence": 0.999998927116394,
"observation_ms": 18.218699959106743,
"policy_ms": 1.763500040397048,
"execution_ms": 2.8200000524520874,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 54,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.149499992839992,
"policy_ms": 2.4216000456362963,
"execution_ms": 23.797200061380863,
"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": 0.9997102618217468,
"observation_ms": 19.446899998001754,
"policy_ms": 2.3861000081524253,
"execution_ms": 22.44800003245473,
"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": 0.9994478821754456,
"observation_ms": 19.34529992286116,
"policy_ms": 1.6651999903842807,
"execution_ms": 2.9511998873203993,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 57,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.44330001808703,
"policy_ms": 2.0528999157249928,
"execution_ms": 54.767899913713336,
"status": "ok",
"code": "CLICK"
},
{
"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": 20.317499991506338,
"policy_ms": 2.5025999639183283,
"execution_ms": 22.964300005696714,
"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": 18.604999990202487,
"policy_ms": 1.416000071913004,
"execution_ms": 21.546700038015842,
"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": 1.0,
"observation_ms": 18.402900081127882,
"policy_ms": 2.1657999604940414,
"execution_ms": 23.002700065262616,
"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": 0.9999998807907104,
"observation_ms": 19.693100010044873,
"policy_ms": 2.4681999348104,
"execution_ms": 23.930200026370585,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 62,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.8983810544013977,
"target_confidence": 1.0,
"observation_ms": 23.263600072823465,
"policy_ms": 2.2478000028058887,
"execution_ms": 15.640300000086427,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 63,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9983367919921875,
"target_confidence": 0.85873943567276,
"observation_ms": 21.32920001167804,
"policy_ms": 2.138499985449016,
"execution_ms": 3.9785000262781978,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 64,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9829460382461548,
"target_confidence": 1.0,
"observation_ms": 20.072199986316264,
"policy_ms": 1.874100067652762,
"execution_ms": 22.601000033318996,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 65,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.5237547159194946,
"target_confidence": 1.0,
"observation_ms": 19.744299934245646,
"policy_ms": 1.6528000123798847,
"execution_ms": 3.1644999980926514,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 66,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 23.615000071004033,
"policy_ms": 2.410199958831072,
"execution_ms": 42.36810002475977,
"status": "ok",
"code": "CLICK"
},
{
"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": 18.37950001936406,
"policy_ms": 1.804900006391108,
"execution_ms": 23.62260001245886,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 68,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.995500053279102,
"policy_ms": 1.645199954509735,
"execution_ms": 32.227500109001994,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 69,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9998936653137207,
"target_confidence": 0.5836381912231445,
"observation_ms": 18.146500107832253,
"policy_ms": 1.6587999416515231,
"execution_ms": 3.0242999782785773,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 70,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.674799987114966,
"policy_ms": 2.2829000372439623,
"execution_ms": 58.3354999544099,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 71,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.07989992853254,
"policy_ms": 1.7679999582469463,
"execution_ms": 22.723899921402335,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 72,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "O",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.6719118356704712,
"observation_ms": 20.61340003274381,
"policy_ms": 2.3207999765872955,
"execution_ms": 3.163499990478158,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 73,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9052738547325134,
"observation_ms": 16.669899923726916,
"policy_ms": 1.638100016862154,
"execution_ms": 22.68329996149987,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 74,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 21.329900017008185,
"policy_ms": 1.9255999941378832,
"execution_ms": 23.794899927452207,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 75,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 43.32369996700436,
"policy_ms": 1.9292000215500593,
"execution_ms": 25.223999982699752,
"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": 16.537899966351688,
"policy_ms": 1.6442000633105636,
"execution_ms": 22.20050001051277,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 77,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.999998927116394,
"target_confidence": 1.0,
"observation_ms": 19.53789999242872,
"policy_ms": 2.0939999958500266,
"execution_ms": 21.898900042288005,
"status": "ok",
"code": "TYPE"
},
{
"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": 17.23720005247742,
"policy_ms": 1.4942999696359038,
"execution_ms": 20.16330009792,
"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": 20.72490006685257,
"policy_ms": 2.668099943548441,
"execution_ms": 20.48149995971471,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 80,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.801099901087582,
"policy_ms": 2.180800074711442,
"execution_ms": 39.21910002827644,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 81,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999997615814209,
"target_confidence": 0.9999921321868896,
"observation_ms": 17.265999922528863,
"policy_ms": 1.5931000234559178,
"execution_ms": 39.03109999373555,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 82,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.587499951943755,
"policy_ms": 1.7686000792309642,
"execution_ms": 54.260200005955994,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 83,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9128974080085754,
"target_confidence": 1.0,
"observation_ms": 21.60480001475662,
"policy_ms": 1.6494999872520566,
"execution_ms": 26.27339994069189,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 84,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 22.096799919381738,
"policy_ms": 2.284600050188601,
"execution_ms": 23.54269998613745,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 85,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.568500040099025,
"policy_ms": 2.6114999782294035,
"execution_ms": 22.038600058294833,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 86,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.049999933689833,
"policy_ms": 1.8260000506415963,
"execution_ms": 33.05269998963922,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 87,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 21.442299941554666,
"policy_ms": 1.7699000891298056,
"execution_ms": 46.82319995481521,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 88,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 25.167400017380714,
"policy_ms": 2.3444999242201447,
"execution_ms": 60.75640011113137,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 89,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 20.64460003748536,
"policy_ms": 2.152100089006126,
"execution_ms": 22.202300024218857,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 90,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9992997646331787,
"target_confidence": 0.9984721541404724,
"observation_ms": 23.232600069604814,
"policy_ms": 2.1249999990686774,
"execution_ms": 53.32009994890541,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 91,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 24.84650001861155,
"policy_ms": 2.548099961131811,
"execution_ms": 27.10760000627488,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 92,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999769926071167,
"target_confidence": 0.9999783039093018,
"observation_ms": 21.894300007261336,
"policy_ms": 2.4238000623881817,
"execution_ms": 24.46879993658513,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 93,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.086599932052195,
"policy_ms": 1.950700068846345,
"execution_ms": 26.81089995894581,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 94,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 27.7623999863863,
"policy_ms": 1.9869999960064888,
"execution_ms": 55.17740000505,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 95,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 24.448600015603006,
"policy_ms": 1.9808000652119517,
"execution_ms": 56.22260004747659,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 96,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 27.35049999319017,
"policy_ms": 2.7284000534564257,
"execution_ms": 56.82669999077916,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 97,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 26.53720008675009,
"policy_ms": 2.753300010226667,
"execution_ms": 28.886200045235455,
"status": "ok",
"code": "TYPE"
},
{
"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": 19.75300000049174,
"policy_ms": 1.8582999473437667,
"execution_ms": 27.006000047549605,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 99,
"template": "table",
"success": true,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.5633274912834167,
"target_confidence": 1.0,
"observation_ms": 26.3063000747934,
"policy_ms": 2.529999939724803,
"execution_ms": 4.016100079752505,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 100,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9986655712127686,
"target_confidence": 0.9999961853027344,
"observation_ms": 24.024399928748608,
"policy_ms": 2.307699993252754,
"execution_ms": 3.3103000605478883,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 101,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9980510473251343,
"target_confidence": 1.0,
"observation_ms": 20.079100038856268,
"policy_ms": 1.4865999110043049,
"execution_ms": 37.717900006100535,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 102,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999996423721313,
"target_confidence": 1.0,
"observation_ms": 23.466199985705316,
"policy_ms": 2.661900012753904,
"execution_ms": 25.023799971677363,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 103,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.584399997256696,
"policy_ms": 2.478900016285479,
"execution_ms": 24.177800049073994,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 104,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9814552664756775,
"target_confidence": 0.9991796612739563,
"observation_ms": 21.240900037810206,
"policy_ms": 2.6496999198570848,
"execution_ms": 15.518000000156462,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 105,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.418700085021555,
"policy_ms": 2.1063999738544226,
"execution_ms": 24.387600016780198,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 106,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 19.328000023961067,
"policy_ms": 2.288699964992702,
"execution_ms": 24.971900042146444,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 107,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9998756647109985,
"observation_ms": 24.564399966038764,
"policy_ms": 2.544500050134957,
"execution_ms": 22.7174999890849,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 108,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9161800742149353,
"target_confidence": 0.9998284578323364,
"observation_ms": 22.466100053861737,
"policy_ms": 2.624599961563945,
"execution_ms": 3.638099995441735,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 109,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 31.51220001745969,
"policy_ms": 2.2133999736979604,
"execution_ms": 27.044099988415837,
"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": 18.84640008211136,
"policy_ms": 2.81360000371933,
"execution_ms": 23.55599997099489,
"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": 23.418699973262846,
"policy_ms": 2.1739000221714377,
"execution_ms": 25.060700019821525,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 112,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 23.06119992863387,
"policy_ms": 2.1838999819010496,
"execution_ms": 27.73279999382794,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 113,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 26.08530002180487,
"policy_ms": 2.0496000070124865,
"execution_ms": 52.54499998409301,
"status": "ok",
"code": "CLICK"
},
{
"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": 21.78979991003871,
"policy_ms": 2.9105000430718064,
"execution_ms": 27.780500007793307,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 115,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999645948410034,
"target_confidence": 1.0,
"observation_ms": 21.985100000165403,
"policy_ms": 2.178400056436658,
"execution_ms": 25.093400035984814,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 116,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 21.745900041423738,
"policy_ms": 2.273899968713522,
"execution_ms": 25.786099955439568,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 117,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 22.26999995764345,
"policy_ms": 2.4512000381946564,
"execution_ms": 59.026199975050986,
"status": "ok",
"code": "CLICK"
},
{
"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": 21.8062000349164,
"policy_ms": 2.3586000315845013,
"execution_ms": 23.766899947077036,
"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": 0.9999450445175171,
"observation_ms": 25.91029996983707,
"policy_ms": 2.724300022237003,
"execution_ms": 26.5594000229612,
"status": "ok",
"code": "SELECT"
}
]
}