devils-agent / reports /policy-browser-novel-v001.json
devildasdf's picture
Upload experimental BAIM code, research checkpoints and measured evaluations
795f737 verified
Raw History Blame Contribute Delete
52.5 kB
{
"checkpoint": "models/v001-no-lexical",
"quantized": false,
"platform": "Windows-11-10.0.26200-SP0",
"torch_threads": 2,
"model_load_ms": 7.755500031635165,
"samples": 120,
"success_rate": 0.5833333333333334,
"abstention_rate": 0.175,
"median_observation_ms": 14.387400005944073,
"median_policy_ms": 2.590400050394237,
"median_execution_ms": 15.836199978366494,
"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": 0.9999039173126221,
"observation_ms": 48.155799973756075,
"policy_ms": 4.100500023923814,
"execution_ms": 3.78839997574687,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 1,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999996423721313,
"target_confidence": 1.0,
"observation_ms": 14.890599995851517,
"policy_ms": 2.4492000229656696,
"execution_ms": 39.766900008544326,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 2,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 37.80180006287992,
"policy_ms": 2.3002999369055033,
"execution_ms": 18.543299986049533,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 3,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 14.828799990937114,
"policy_ms": 2.4418000830337405,
"execution_ms": 31.127299997024238,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 4,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.8566849827766418,
"target_confidence": 1.0,
"observation_ms": 15.973599976859987,
"policy_ms": 2.631800016388297,
"execution_ms": 2.5369999930262566,
"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": 1.0,
"observation_ms": 15.66629996523261,
"policy_ms": 2.7742000529542565,
"execution_ms": 10.593199986033142,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 6,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.330099992454052,
"policy_ms": 2.7721000369638205,
"execution_ms": 19.744400051422417,
"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": 0.999404788017273,
"observation_ms": 15.696700080297887,
"policy_ms": 2.842400106601417,
"execution_ms": 17.253799946047366,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 8,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9946579337120056,
"observation_ms": 15.824000001884997,
"policy_ms": 2.9687000205740333,
"execution_ms": 16.37490000575781,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 9,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.5657387971878052,
"target_confidence": 1.0,
"observation_ms": 13.3670000359416,
"policy_ms": 1.8517000135034323,
"execution_ms": 2.1585000213235617,
"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": 1.0,
"observation_ms": 13.34619999397546,
"policy_ms": 2.0665000192821026,
"execution_ms": 16.778600052930415,
"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": 0.9999995231628418,
"observation_ms": 18.10390001628548,
"policy_ms": 2.118099946528673,
"execution_ms": 2.3756999289616942,
"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": 0.9999984502792358,
"observation_ms": 14.613799983635545,
"policy_ms": 2.5136000476777554,
"execution_ms": 10.11360005941242,
"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": 14.006900019012392,
"policy_ms": 2.845599898137152,
"execution_ms": 57.12309991940856,
"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": 14.414299977943301,
"policy_ms": 2.4254999589174986,
"execution_ms": 17.154800007119775,
"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": 16.039400012232363,
"policy_ms": 1.5656000468879938,
"execution_ms": 13.976700021885335,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 16,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.034599954262376,
"policy_ms": 3.0512999510392547,
"execution_ms": 18.35849997587502,
"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": 16.637500026263297,
"policy_ms": 3.009999985806644,
"execution_ms": 15.937500051222742,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 18,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999964237213135,
"target_confidence": 1.0,
"observation_ms": 13.905499945394695,
"policy_ms": 2.189300023019314,
"execution_ms": 28.85450003668666,
"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": 14.958699932321906,
"policy_ms": 2.4140001041814685,
"execution_ms": 16.44000003580004,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 20,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999957084655762,
"target_confidence": 1.0,
"observation_ms": 15.601499937474728,
"policy_ms": 2.930799964815378,
"execution_ms": 26.539099984802306,
"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": 14.49610001873225,
"policy_ms": 2.6504999259486794,
"execution_ms": 59.45119995158166,
"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": 15.534300007857382,
"policy_ms": 2.8038000455126166,
"execution_ms": 54.541900055482984,
"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": 13.405699981376529,
"policy_ms": 2.187600010074675,
"execution_ms": 15.721399919129908,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 24,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999997615814209,
"target_confidence": 1.0,
"observation_ms": 14.66660003643483,
"policy_ms": 3.554799943231046,
"execution_ms": 48.90890000388026,
"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": 13.233899953775108,
"policy_ms": 1.8354000058025122,
"execution_ms": 25.838000001385808,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 26,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 18.253899994306266,
"policy_ms": 3.1340999994426966,
"execution_ms": 13.132599997334182,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 14.520599972456694,
"policy_ms": 1.7303000204265118,
"execution_ms": 16.68460003565997,
"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": 1.0,
"observation_ms": 13.085299986414611,
"policy_ms": 1.9613999174907804,
"execution_ms": 9.540400002151728,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 13.150600017979741,
"policy_ms": 2.2929999977350235,
"execution_ms": 24.475399986840785,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 30,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.633000013418496,
"policy_ms": 3.142800065688789,
"execution_ms": 10.01420000102371,
"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": 16.44879998639226,
"policy_ms": 2.66519992146641,
"execution_ms": 16.52860001195222,
"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": 1.0,
"observation_ms": 12.910100049339235,
"policy_ms": 2.1643999498337507,
"execution_ms": 15.578899998217821,
"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": 0.9468345046043396,
"observation_ms": 13.298999983817339,
"policy_ms": 2.1152000408619642,
"execution_ms": 2.374800038523972,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 34,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.98715740442276,
"target_confidence": 1.0,
"observation_ms": 14.753099996596575,
"policy_ms": 3.1820000149309635,
"execution_ms": 18.66950001567602,
"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": 13.49889999255538,
"policy_ms": 1.9891000119969249,
"execution_ms": 30.96399991773069,
"status": "ok",
"code": "CLICK"
},
{
"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": 13.855400029569864,
"policy_ms": 1.9989999709650874,
"execution_ms": 10.228500002995133,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 14.236199902370572,
"policy_ms": 2.596600097604096,
"execution_ms": 15.496000065468252,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 38,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9890561103820801,
"target_confidence": 1.0,
"observation_ms": 16.398599953390658,
"policy_ms": 2.4811000330373645,
"execution_ms": 10.626500006765127,
"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": 0.9998949766159058,
"observation_ms": 12.702600099146366,
"policy_ms": 2.3571999045088887,
"execution_ms": 10.468199965544045,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 40,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9305520057678223,
"observation_ms": 14.912900049239397,
"policy_ms": 2.680000034160912,
"execution_ms": 2.3592000361531973,
"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": 12.922900030389428,
"policy_ms": 2.2016000002622604,
"execution_ms": 16.15399995353073,
"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": 14.27980000153184,
"policy_ms": 2.9817000031471252,
"execution_ms": 20.689299912191927,
"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": 14.495000010356307,
"policy_ms": 1.7315000295639038,
"execution_ms": 16.5631000418216,
"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": 16.022499999962747,
"policy_ms": 2.5951999705284834,
"execution_ms": 28.8407999323681,
"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": 12.994099990464747,
"policy_ms": 1.922299969010055,
"execution_ms": 15.168599900789559,
"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": 12.887299992144108,
"policy_ms": 2.1222999785095453,
"execution_ms": 15.42199996765703,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 47,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.8051379323005676,
"observation_ms": 15.364399994723499,
"policy_ms": 2.498099929653108,
"execution_ms": 2.7083000168204308,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 48,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.14170001912862,
"policy_ms": 1.8744999542832375,
"execution_ms": 9.740900015458465,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 49,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.013899977318943,
"policy_ms": 2.550999983213842,
"execution_ms": 11.068299994803965,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 50,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9796527624130249,
"target_confidence": 1.0,
"observation_ms": 12.284099939279258,
"policy_ms": 1.7565001035109162,
"execution_ms": 22.017300012521446,
"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": 13.864399981684983,
"policy_ms": 2.271600067615509,
"execution_ms": 15.552200027741492,
"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": 13.490600045770407,
"policy_ms": 2.149399952031672,
"execution_ms": 14.547700062394142,
"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": 0.9997931122779846,
"observation_ms": 15.169100021012127,
"policy_ms": 3.2730000093579292,
"execution_ms": 2.885499969124794,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 54,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9972251653671265,
"target_confidence": 1.0,
"observation_ms": 14.367499970830977,
"policy_ms": 3.09520005248487,
"execution_ms": 16.815399983897805,
"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": 0.9999972581863403,
"observation_ms": 15.827800030820072,
"policy_ms": 3.6145999329164624,
"execution_ms": 17.35270000062883,
"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": 1.0,
"observation_ms": 14.40730004105717,
"policy_ms": 2.7208999963477254,
"execution_ms": 2.3763999342918396,
"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": 13.356899959035218,
"policy_ms": 2.341100014746189,
"execution_ms": 48.094899975694716,
"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": 14.218099997378886,
"policy_ms": 3.1998000340536237,
"execution_ms": 15.435200068168342,
"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": 13.307899935171008,
"policy_ms": 2.1096999989822507,
"execution_ms": 15.629699919372797,
"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": 12.890400015749037,
"policy_ms": 2.027299953624606,
"execution_ms": 15.748900012113154,
"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": 13.705399935133755,
"policy_ms": 3.4446000354364514,
"execution_ms": 16.00020006299019,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 62,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.999985933303833,
"target_confidence": 1.0,
"observation_ms": 15.249400050379336,
"policy_ms": 2.678500022739172,
"execution_ms": 10.372799937613308,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 63,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.9900351166725159,
"observation_ms": 15.276299905963242,
"policy_ms": 2.547200070694089,
"execution_ms": 2.489199978299439,
"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": 0.9999909400939941,
"observation_ms": 14.591599931009114,
"policy_ms": 2.7464000741019845,
"execution_ms": 10.19070006441325,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 65,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.814099947921932,
"policy_ms": 1.896600006148219,
"execution_ms": 2.2869999520480633,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 66,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.999858021736145,
"target_confidence": 1.0,
"observation_ms": 15.144100063480437,
"policy_ms": 2.86400003824383,
"execution_ms": 34.816599916666746,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 67,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9981772899627686,
"target_confidence": 1.0,
"observation_ms": 12.527500046417117,
"policy_ms": 1.9356999546289444,
"execution_ms": 16.11970004159957,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 68,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9811867475509644,
"target_confidence": 1.0,
"observation_ms": 11.66930003091693,
"policy_ms": 1.8606000812724233,
"execution_ms": 2.3653999669477344,
"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": 1.0,
"observation_ms": 12.11489993147552,
"policy_ms": 1.9087999826297164,
"execution_ms": 2.070999937132001,
"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": 13.464600080624223,
"policy_ms": 2.668699948117137,
"execution_ms": 23.93499994650483,
"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": 0.999996542930603,
"observation_ms": 12.95220002066344,
"policy_ms": 2.4679999332875013,
"execution_ms": 16.157799982465804,
"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": 0.9893146753311157,
"observation_ms": 15.717100002802908,
"policy_ms": 3.7606999976560473,
"execution_ms": 16.984299989417195,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 73,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.583000098355114,
"policy_ms": 1.9235999789088964,
"execution_ms": 15.615000040270388,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 74,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.8770361542701721,
"target_confidence": 1.0,
"observation_ms": 15.939899953082204,
"policy_ms": 2.9320999747142196,
"execution_ms": 10.032300022430718,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 12.446000007912517,
"policy_ms": 1.9451999105513096,
"execution_ms": 15.01169998664409,
"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": 12.012399965897202,
"policy_ms": 1.7288000090047717,
"execution_ms": 16.6993000311777,
"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": 0.9999998807907104,
"observation_ms": 12.958699953742325,
"policy_ms": 2.9100000392645597,
"execution_ms": 9.939000010490417,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 12.985300039872527,
"policy_ms": 1.9712999928742647,
"execution_ms": 14.669200056232512,
"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": 16.078799962997437,
"policy_ms": 3.023100085556507,
"execution_ms": 15.87969996035099,
"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": 13.870000024326146,
"policy_ms": 2.5908000534400344,
"execution_ms": 54.726800066418946,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 81,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999955892562866,
"target_confidence": 1.0,
"observation_ms": 14.03229997958988,
"policy_ms": 2.6039000367745757,
"execution_ms": 21.69069997034967,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 82,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9874667525291443,
"target_confidence": 1.0,
"observation_ms": 13.66629998665303,
"policy_ms": 3.2644999446347356,
"execution_ms": 22.565199993550777,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 83,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999885559082031,
"target_confidence": 1.0,
"observation_ms": 13.963400037027895,
"policy_ms": 2.765199984423816,
"execution_ms": 9.677199996076524,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 84,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.606799930334091,
"policy_ms": 2.8017000295221806,
"execution_ms": 10.312799946404994,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 14.567699981853366,
"policy_ms": 3.14990000333637,
"execution_ms": 16.22500002849847,
"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": 14.63089999742806,
"policy_ms": 1.9193000625818968,
"execution_ms": 26.472300058230758,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 87,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9978881478309631,
"target_confidence": 1.0,
"observation_ms": 14.111700002104044,
"policy_ms": 3.0320000369101763,
"execution_ms": 22.802699939347804,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 88,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999955892562866,
"target_confidence": 1.0,
"observation_ms": 15.391700086183846,
"policy_ms": 3.0305999098345637,
"execution_ms": 39.677699911408126,
"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": 16.580999945290387,
"policy_ms": 3.050200059078634,
"execution_ms": 16.045400057919323,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 90,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999955892562866,
"target_confidence": 0.9998617172241211,
"observation_ms": 16.759400023147464,
"policy_ms": 3.5053000319749117,
"execution_ms": 23.27140001580119,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 91,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.7773793935775757,
"target_confidence": 1.0,
"observation_ms": 14.848099905066192,
"policy_ms": 2.7843000134453177,
"execution_ms": 2.3981999838724732,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 92,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 13.715100008994341,
"policy_ms": 3.015700029209256,
"execution_ms": 9.715899941511452,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 93,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.955100042745471,
"policy_ms": 2.0581999560818076,
"execution_ms": 12.647299910895526,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 94,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.999945878982544,
"target_confidence": 1.0,
"observation_ms": 14.752999995835125,
"policy_ms": 2.7809999883174896,
"execution_ms": 54.606499965302646,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 95,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9988864064216614,
"target_confidence": 1.0,
"observation_ms": 13.102500000968575,
"policy_ms": 2.5030000833794475,
"execution_ms": 23.343699984252453,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 96,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9808314442634583,
"target_confidence": 1.0,
"observation_ms": 13.83519999217242,
"policy_ms": 2.760999952442944,
"execution_ms": 9.711199905723333,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 97,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9050796627998352,
"target_confidence": 1.0,
"observation_ms": 11.939999996684492,
"policy_ms": 1.9660999532788992,
"execution_ms": 16.0264999140054,
"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": 11.875799973495305,
"policy_ms": 2.076099975965917,
"execution_ms": 15.792699996381998,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 99,
"template": "table",
"success": true,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.462799929082394,
"policy_ms": 3.6057999823242426,
"execution_ms": 2.986599924042821,
"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": 0.9999902248382568,
"observation_ms": 15.135299996472895,
"policy_ms": 2.6094999630004168,
"execution_ms": 2.2055000299587846,
"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": 11.98309997562319,
"policy_ms": 1.9260999979451299,
"execution_ms": 2.0203000167384744,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 102,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.8218594193458557,
"target_confidence": 1.0,
"observation_ms": 15.545599977485836,
"policy_ms": 3.12780006788671,
"execution_ms": 2.2397999418899417,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 103,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999995231628418,
"target_confidence": 1.0,
"observation_ms": 11.621500016190112,
"policy_ms": 1.8804999999701977,
"execution_ms": 18.729500006884336,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 104,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.6922178864479065,
"observation_ms": 16.361800022423267,
"policy_ms": 2.5900000473484397,
"execution_ms": 2.6360000483691692,
"status": "ok",
"code": "ASK_USER"
},
{
"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": 12.549699982628226,
"policy_ms": 1.6466000815853477,
"execution_ms": 17.236400046385825,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 106,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999979734420776,
"target_confidence": 1.0,
"observation_ms": 13.705999939702451,
"policy_ms": 1.84449995867908,
"execution_ms": 12.095400015823543,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 107,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9943962097167969,
"observation_ms": 15.221600071527064,
"policy_ms": 3.771199961192906,
"execution_ms": 15.91529999859631,
"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": 14.304100070148706,
"policy_ms": 2.8521999483928084,
"execution_ms": 2.2107999539002776,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 109,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9992850422859192,
"target_confidence": 1.0,
"observation_ms": 14.743900042958558,
"policy_ms": 2.9267999343574047,
"execution_ms": 10.188999935053289,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 12.455100077204406,
"policy_ms": 1.881500007584691,
"execution_ms": 16.300100018270314,
"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": 14.463100000284612,
"policy_ms": 2.7065000031143427,
"execution_ms": 15.26350004132837,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 112,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.7560167908668518,
"target_confidence": 1.0,
"observation_ms": 13.202299945987761,
"policy_ms": 2.3172999499365687,
"execution_ms": 2.1214999724179506,
"status": "ok",
"code": "ASK_USER"
},
{
"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": 12.698400067165494,
"policy_ms": 2.3204999743029475,
"execution_ms": 45.52929999772459,
"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": 15.901500009931624,
"policy_ms": 3.0267999973148108,
"execution_ms": 17.193299951031804,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 115,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9989173412322998,
"target_confidence": 1.0,
"observation_ms": 16.38369995635003,
"policy_ms": 2.64620000962168,
"execution_ms": 22.608300088904798,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 116,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9819120168685913,
"target_confidence": 1.0,
"observation_ms": 16.344000003300607,
"policy_ms": 2.8233000775799155,
"execution_ms": 22.272499976679683,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 117,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 13.907600077800453,
"policy_ms": 1.9036999437958002,
"execution_ms": 25.179299991577864,
"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": 13.256300007924438,
"policy_ms": 2.396099967882037,
"execution_ms": 15.387500054202974,
"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": 0.9981478452682495,
"observation_ms": 14.962199958972633,
"policy_ms": 3.0468000331893563,
"execution_ms": 15.09010000154376,
"status": "ok",
"code": "SELECT"
}
]
}