devils-agent / reports /policy-browser-novel-v003.json
devildasdf's picture
Upload experimental BAIM code, research checkpoints and measured evaluations
795f737 verified
Raw History Blame Contribute Delete
52.1 kB
{
"checkpoint": "models/v003-transformer",
"quantized": false,
"platform": "Windows-11-10.0.26200-SP0",
"torch_threads": 2,
"model_load_ms": 11.723599978722632,
"samples": 120,
"success_rate": 0.49166666666666664,
"abstention_rate": 0.15,
"median_observation_ms": 14.34735005022958,
"median_policy_ms": 4.208899976219982,
"median_execution_ms": 16.347200027666986,
"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": 1.0,
"observation_ms": 43.33179991226643,
"policy_ms": 6.381200044415891,
"execution_ms": 3.6983999889343977,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 1,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999996423721313,
"observation_ms": 15.646400046534836,
"policy_ms": 3.6445000441744924,
"execution_ms": 43.543800013139844,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 2,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999963045120239,
"target_confidence": 0.9999997615814209,
"observation_ms": 29.71329994034022,
"policy_ms": 4.3830000795423985,
"execution_ms": 18.738399958238006,
"status": "ok",
"code": "SELECT"
},
{
"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": 14.353300095535815,
"policy_ms": 3.6409999011084437,
"execution_ms": 58.37500002235174,
"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": 16.350400052033365,
"policy_ms": 4.532700055278838,
"execution_ms": 32.714600092731416,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 5,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.697097897529602,
"observation_ms": 16.117900027893484,
"policy_ms": 4.587300005368888,
"execution_ms": 2.7254000306129456,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 6,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.944299986585975,
"policy_ms": 4.615599988028407,
"execution_ms": 16.94929995574057,
"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": 0.9999443292617798,
"observation_ms": 15.260900021530688,
"policy_ms": 5.21530001424253,
"execution_ms": 16.81660010945052,
"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": 17.323400010354817,
"policy_ms": 4.924600012600422,
"execution_ms": 17.00610003899783,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 9,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 15.643000020645559,
"policy_ms": 3.2848999835550785,
"execution_ms": 11.316700023598969,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 13.301400002092123,
"policy_ms": 3.5921999951824546,
"execution_ms": 16.197599936276674,
"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": 0.9445252418518066,
"observation_ms": 13.399999937973917,
"policy_ms": 3.580200020223856,
"execution_ms": 2.6394000742584467,
"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": 0.9546310901641846,
"observation_ms": 15.233399928547442,
"policy_ms": 3.8636999670416117,
"execution_ms": 16.240400029346347,
"status": "ok",
"code": "SELECT"
},
{
"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": 14.776699943467975,
"policy_ms": 4.08179999794811,
"execution_ms": 26.79060003720224,
"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": 0.9981576800346375,
"observation_ms": 13.14350008033216,
"policy_ms": 5.236499942839146,
"execution_ms": 15.965000027790666,
"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": 12.12550001218915,
"policy_ms": 3.0944999307394028,
"execution_ms": 16.255500027909875,
"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": 0.9995447993278503,
"observation_ms": 14.992900076322258,
"policy_ms": 5.350299994461238,
"execution_ms": 16.49599999655038,
"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": 15.71680000051856,
"policy_ms": 4.569399985484779,
"execution_ms": 17.183199990540743,
"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": 15.53019997663796,
"policy_ms": 4.76769998203963,
"execution_ms": 30.86950001306832,
"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": 15.703300014138222,
"policy_ms": 5.213299999013543,
"execution_ms": 16.328300000168383,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 20,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9988501071929932,
"target_confidence": 1.0,
"observation_ms": 15.607999986968935,
"policy_ms": 5.30409999191761,
"execution_ms": 54.43910008762032,
"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": 13.421499985270202,
"policy_ms": 4.855699953623116,
"execution_ms": 57.28349997662008,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 22,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.5187785625457764,
"observation_ms": 15.052200062200427,
"policy_ms": 3.6743999226018786,
"execution_ms": 2.2890999680384994,
"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": 14.341400004923344,
"policy_ms": 4.631799994967878,
"execution_ms": 19.049499998800457,
"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": 16.394600039348006,
"policy_ms": 4.865199909545481,
"execution_ms": 55.08479999843985,
"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": 12.264099903404713,
"policy_ms": 3.420600085519254,
"execution_ms": 24.465400027111173,
"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": 0.9999994039535522,
"observation_ms": 14.181600068695843,
"policy_ms": 4.615299985744059,
"execution_ms": 16.70240005478263,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 27,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999845027923584,
"observation_ms": 13.807500014081597,
"policy_ms": 3.414599923416972,
"execution_ms": 17.513599945232272,
"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": 13.458800036460161,
"policy_ms": 4.299599910154939,
"execution_ms": 15.959499985910952,
"status": "ok",
"code": "SELECT"
},
{
"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": 13.318099896423519,
"policy_ms": 3.613900044001639,
"execution_ms": 30.32110002823174,
"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": 0.9935959577560425,
"observation_ms": 15.342000056989491,
"policy_ms": 6.037199986167252,
"execution_ms": 18.762000021524727,
"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": 13.748099911026657,
"policy_ms": 4.332500044256449,
"execution_ms": 15.600200043991208,
"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": 13.30940006300807,
"policy_ms": 3.552400041371584,
"execution_ms": 15.391999972052872,
"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": 0.9999959468841553,
"observation_ms": 13.883200008422136,
"policy_ms": 3.6560000153258443,
"execution_ms": 2.3434999166056514,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 34,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9908668994903564,
"observation_ms": 19.056000048294663,
"policy_ms": 5.479299928992987,
"execution_ms": 16.300899907946587,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 35,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 0.999966025352478,
"observation_ms": 12.62619998306036,
"policy_ms": 2.8918000170961022,
"execution_ms": 28.523200075142086,
"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": 13.42769991606474,
"policy_ms": 3.3411000622436404,
"execution_ms": 14.98800003901124,
"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": 14.420899911783636,
"policy_ms": 4.462899989448488,
"execution_ms": 15.945799998007715,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 38,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999078512191772,
"observation_ms": 14.410600066184998,
"policy_ms": 4.018999985419214,
"execution_ms": 15.776899992488325,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 39,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.7229601740837097,
"observation_ms": 13.835499994456768,
"policy_ms": 3.4531999845057726,
"execution_ms": 2.393100061453879,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 40,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.8199255466461182,
"target_confidence": 0.9622209072113037,
"observation_ms": 13.003399944864213,
"policy_ms": 4.216299974359572,
"execution_ms": 2.3136999225243926,
"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": 14.038600027561188,
"policy_ms": 3.758199978619814,
"execution_ms": 19.614299992099404,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 42,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9906959533691406,
"observation_ms": 15.380099997855723,
"policy_ms": 5.174900055862963,
"execution_ms": 16.194800031371415,
"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": 16.09920000191778,
"policy_ms": 2.9875999316573143,
"execution_ms": 16.857200069352984,
"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": 19.488100078888237,
"policy_ms": 4.6657000202685595,
"execution_ms": 45.196899911388755,
"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": 14.174100011587143,
"policy_ms": 3.612800035625696,
"execution_ms": 16.329400008544326,
"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": 13.86790000833571,
"policy_ms": 3.732500015757978,
"execution_ms": 15.6872000079602,
"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": 0.9994713664054871,
"observation_ms": 14.796999981626868,
"policy_ms": 4.007799900136888,
"execution_ms": 17.369800014421344,
"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": 0.9999954700469971,
"observation_ms": 17.278900020755827,
"policy_ms": 3.432299941778183,
"execution_ms": 16.455199918709695,
"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": 1.0,
"observation_ms": 12.219800031743944,
"policy_ms": 3.06679995264858,
"execution_ms": 15.623299987055361,
"status": "ok",
"code": "SELECT"
},
{
"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": 12.64410000294447,
"policy_ms": 2.9203000012785196,
"execution_ms": 28.96669995971024,
"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": 13.099399977363646,
"policy_ms": 4.649800015613437,
"execution_ms": 15.478800050914288,
"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": 0.9999995231628418,
"observation_ms": 14.24969988875091,
"policy_ms": 3.487100009806454,
"execution_ms": 16.336900065653026,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 53,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9994637370109558,
"target_confidence": 1.0,
"observation_ms": 13.493999955244362,
"policy_ms": 4.184499965049326,
"execution_ms": 2.6196999242529273,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 54,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.671700006350875,
"policy_ms": 5.404000054113567,
"execution_ms": 16.411299933679402,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 55,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.105199931189418,
"policy_ms": 4.387599998153746,
"execution_ms": 15.674199908971786,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 56,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9999959468841553,
"target_confidence": 0.9999991655349731,
"observation_ms": 13.736499939113855,
"policy_ms": 3.7805000320076942,
"execution_ms": 2.331000054255128,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 57,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 0.99505215883255,
"observation_ms": 13.307199929840863,
"policy_ms": 4.483100026845932,
"execution_ms": 24.10740009509027,
"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": 14.891300001181662,
"policy_ms": 4.842999973334372,
"execution_ms": 16.17439999245107,
"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": 13.18480004556477,
"policy_ms": 3.7406999617815018,
"execution_ms": 16.027100034989417,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 60,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9976951479911804,
"observation_ms": 13.399000046774745,
"policy_ms": 4.2375000193715096,
"execution_ms": 15.702300006523728,
"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": 16.998699982650578,
"policy_ms": 5.065600038506091,
"execution_ms": 16.46650000475347,
"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": 0.8148142695426941,
"observation_ms": 14.55389999318868,
"policy_ms": 4.31150000076741,
"execution_ms": 2.500499947927892,
"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": 1.0,
"observation_ms": 16.428599948994815,
"policy_ms": 7.091199979186058,
"execution_ms": 3.336200024932623,
"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": 1.0,
"observation_ms": 18.28289998229593,
"policy_ms": 4.436500021256506,
"execution_ms": 16.73330005723983,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 65,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9999277591705322,
"target_confidence": 1.0,
"observation_ms": 14.230200089514256,
"policy_ms": 3.7158000050112605,
"execution_ms": 2.4012000067159534,
"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": 14.288099948316813,
"policy_ms": 4.775100038386881,
"execution_ms": 55.68130000028759,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 67,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9995371103286743,
"target_confidence": 1.0,
"observation_ms": 15.914499992504716,
"policy_ms": 3.272100002504885,
"execution_ms": 18.482700106687844,
"status": "ok",
"code": "SELECT"
},
{
"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": 13.357700081542134,
"policy_ms": 2.761899959295988,
"execution_ms": 25.26570006739348,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 69,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.999994158744812,
"target_confidence": 0.9998956918716431,
"observation_ms": 12.45879998896271,
"policy_ms": 3.260800032876432,
"execution_ms": 2.2203000262379646,
"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": 13.865799992345273,
"policy_ms": 4.4874000595882535,
"execution_ms": 45.95060006249696,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 71,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.713100062683225,
"policy_ms": 3.830699948593974,
"execution_ms": 17.074699979275465,
"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": 0.9999479055404663,
"observation_ms": 17.204499919898808,
"policy_ms": 6.514200009405613,
"execution_ms": 17.975800088606775,
"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": 1.0,
"observation_ms": 12.782400008291006,
"policy_ms": 2.8341999277472496,
"execution_ms": 14.98929993249476,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 74,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999997615814209,
"observation_ms": 14.468500041402876,
"policy_ms": 5.100599955767393,
"execution_ms": 15.640300000086427,
"status": "ok",
"code": "SELECT"
},
{
"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": 12.580499984323978,
"policy_ms": 2.9826000100001693,
"execution_ms": 15.16129996161908,
"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": 13.51810002233833,
"policy_ms": 2.7628999669104815,
"execution_ms": 16.3880999898538,
"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": 13.518700026907027,
"policy_ms": 5.012999987229705,
"execution_ms": 16.357499989680946,
"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": 14.556200010702014,
"policy_ms": 4.080199985764921,
"execution_ms": 16.73739997204393,
"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": 14.642500085756183,
"policy_ms": 5.334799992851913,
"execution_ms": 15.943299978971481,
"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": 13.948100036941469,
"policy_ms": 4.190700012259185,
"execution_ms": 55.901499930769205,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 81,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.45890003722161,
"policy_ms": 3.8262000307440758,
"execution_ms": 23.478199960663915,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 82,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 0.99989914894104,
"observation_ms": 15.5745999654755,
"policy_ms": 6.229200051166117,
"execution_ms": 51.97759997099638,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 83,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9656752943992615,
"observation_ms": 14.372300007380545,
"policy_ms": 5.383600015193224,
"execution_ms": 16.966499970294535,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 84,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.8647266626358032,
"observation_ms": 16.160600003786385,
"policy_ms": 5.140200024470687,
"execution_ms": 15.700799995101988,
"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": 0.9447211623191833,
"observation_ms": 13.18640005774796,
"policy_ms": 4.051100113429129,
"execution_ms": 15.234699938446283,
"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": 13.797399937175214,
"policy_ms": 3.194599994458258,
"execution_ms": 29.889099998399615,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 87,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 15.166900004260242,
"policy_ms": 4.183799959719181,
"execution_ms": 33.83550001308322,
"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": 17.07990001887083,
"policy_ms": 5.7897999649867415,
"execution_ms": 50.41929997969419,
"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": 14.78339999448508,
"policy_ms": 5.097899935208261,
"execution_ms": 15.670100110583007,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 90,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.454099979251623,
"policy_ms": 5.093200015835464,
"execution_ms": 23.459500051103532,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 91,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999957084655762,
"target_confidence": 0.9984277486801147,
"observation_ms": 13.411599909886718,
"policy_ms": 3.9958000415936112,
"execution_ms": 15.878699952736497,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 92,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999996423721313,
"observation_ms": 14.981499989517033,
"policy_ms": 4.761700052767992,
"execution_ms": 18.03700008895248,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 93,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999998807907104,
"observation_ms": 14.161000028252602,
"policy_ms": 3.060900024138391,
"execution_ms": 14.705299981869757,
"status": "ok",
"code": "SELECT"
},
{
"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": 15.453200088813901,
"policy_ms": 4.6984999207779765,
"execution_ms": 24.97989998664707,
"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": 13.531000004149973,
"policy_ms": 4.265900002792478,
"execution_ms": 21.575899911113083,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 96,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.8603801131248474,
"observation_ms": 14.894000021740794,
"policy_ms": 4.233099985867739,
"execution_ms": 17.60569994803518,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 97,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999197721481323,
"observation_ms": 18.818299984559417,
"policy_ms": 3.515999997034669,
"execution_ms": 18.676399951800704,
"status": "ok",
"code": "SELECT"
},
{
"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": 13.14169995021075,
"policy_ms": 3.1015999848023057,
"execution_ms": 17.227199976332486,
"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": 0.8986082077026367,
"observation_ms": 15.760399983264506,
"policy_ms": 4.673700081184506,
"execution_ms": 2.6542999548837543,
"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": 0.9999239444732666,
"observation_ms": 14.298899914138019,
"policy_ms": 4.248299985192716,
"execution_ms": 2.7375000063329935,
"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": 11.684700031764805,
"policy_ms": 3.019999945536256,
"execution_ms": 2.2021998884156346,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 102,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9922630786895752,
"observation_ms": 17.184600001201034,
"policy_ms": 4.535899963229895,
"execution_ms": 15.5123999575153,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 103,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999997615814209,
"target_confidence": 1.0,
"observation_ms": 13.034500065259635,
"policy_ms": 2.9252999229356647,
"execution_ms": 15.785699943080544,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 104,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.99896240234375,
"observation_ms": 13.376299990341067,
"policy_ms": 4.238800029270351,
"execution_ms": 15.408799983561039,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 105,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9708772897720337,
"observation_ms": 11.8101000552997,
"policy_ms": 3.440900007262826,
"execution_ms": 11.12519996240735,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 106,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 11.58169994596392,
"policy_ms": 3.676300053484738,
"execution_ms": 16.66079997085035,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 107,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 15.241799992509186,
"policy_ms": 7.07180006429553,
"execution_ms": 16.849200008437037,
"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": 14.715700061060488,
"policy_ms": 4.35160007327795,
"execution_ms": 2.422400051727891,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 109,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.0886999219656,
"policy_ms": 6.280199973843992,
"execution_ms": 17.354499897919595,
"status": "ok",
"code": "SELECT"
},
{
"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": 12.413999997079372,
"policy_ms": 3.1624999828636646,
"execution_ms": 14.989799936302006,
"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": 14.437800040468574,
"policy_ms": 4.201499978080392,
"execution_ms": 15.381600009277463,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 112,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9999994039535522,
"target_confidence": 0.9972097277641296,
"observation_ms": 13.343900092877448,
"policy_ms": 4.147200030274689,
"execution_ms": 10.750599903985858,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 113,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 12.769999913871288,
"policy_ms": 4.013400059193373,
"execution_ms": 37.7233000472188,
"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": 14.909100020304322,
"policy_ms": 5.094700027257204,
"execution_ms": 16.464499989524484,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 115,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 13.641499914228916,
"policy_ms": 3.7711000768467784,
"execution_ms": 15.856500016525388,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 116,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.7579777240753174,
"observation_ms": 16.42950007226318,
"policy_ms": 3.464199951849878,
"execution_ms": 2.3365000961348414,
"status": "ok",
"code": "ASK_USER"
},
{
"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": 12.082099914550781,
"policy_ms": 3.243400016799569,
"execution_ms": 43.12389995902777,
"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": 0.9999833106994629,
"observation_ms": 12.96540000475943,
"policy_ms": 3.94099997356534,
"execution_ms": 16.32010005414486,
"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": 0.9794986844062805,
"observation_ms": 16.84259995818138,
"policy_ms": 4.989200038835406,
"execution_ms": 15.340300044044852,
"status": "ok",
"code": "SELECT"
}
]
}