devils-agent / reports /policy-browser-novel-v000.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/v000-mean",
"quantized": false,
"platform": "Windows-11-10.0.26200-SP0",
"torch_threads": 2,
"model_load_ms": 9.840800077654421,
"samples": 120,
"success_rate": 0.6166666666666667,
"abstention_rate": 0.15833333333333333,
"median_observation_ms": 15.722550044301897,
"median_policy_ms": 2.642350038513541,
"median_execution_ms": 17.39390002330765,
"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": 0.6028217077255249,
"observation_ms": 41.0907999612391,
"policy_ms": 4.931100062094629,
"execution_ms": 5.35310001578182,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 1,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999998807907104,
"target_confidence": 1.0,
"observation_ms": 16.348800039850175,
"policy_ms": 2.6072999462485313,
"execution_ms": 46.392700052820146,
"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": 29.954700032249093,
"policy_ms": 2.511699916794896,
"execution_ms": 31.195999938063323,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 3,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999649524688721,
"target_confidence": 1.0,
"observation_ms": 15.29299991670996,
"policy_ms": 2.1188000682741404,
"execution_ms": 32.14030002709478,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 4,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.9261236786842346,
"target_confidence": 1.0,
"observation_ms": 17.166699981316924,
"policy_ms": 3.0170000391080976,
"execution_ms": 2.691800007596612,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 5,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9993553757667542,
"observation_ms": 18.30679993145168,
"policy_ms": 2.898600068874657,
"execution_ms": 13.020699960179627,
"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": 0.9194011688232422,
"observation_ms": 20.474000019021332,
"policy_ms": 3.6683999933302402,
"execution_ms": 21.632199990563095,
"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": 0.9984651803970337,
"observation_ms": 18.28419999219477,
"policy_ms": 3.329100087285042,
"execution_ms": 23.86119996663183,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 8,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999978542327881,
"observation_ms": 18.28289998229593,
"policy_ms": 3.1875999411568046,
"execution_ms": 18.8400000333786,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 9,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.720268964767456,
"target_confidence": 1.0,
"observation_ms": 15.088799991644919,
"policy_ms": 1.9933999283239245,
"execution_ms": 2.431600005365908,
"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": 17.001499887555838,
"policy_ms": 2.0283000776544213,
"execution_ms": 18.627900048159063,
"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": 0.6273818016052246,
"observation_ms": 15.724600059911609,
"policy_ms": 2.161799930036068,
"execution_ms": 2.5417000288143754,
"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": 1.0,
"observation_ms": 18.226400017738342,
"policy_ms": 2.511899918317795,
"execution_ms": 13.394499896094203,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 13,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999972581863403,
"target_confidence": 1.0,
"observation_ms": 14.533399953506887,
"policy_ms": 2.852100064046681,
"execution_ms": 47.78600006829947,
"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": 15.751499915495515,
"policy_ms": 2.3541999980807304,
"execution_ms": 17.82499998807907,
"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": 14.72710003145039,
"policy_ms": 1.6965999966487288,
"execution_ms": 12.583900010213256,
"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": 18.40279996395111,
"policy_ms": 3.0305000254884362,
"execution_ms": 18.68630002718419,
"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": 16.897099907509983,
"policy_ms": 2.886700094677508,
"execution_ms": 19.381599966436625,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 18,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9988070726394653,
"target_confidence": 1.0,
"observation_ms": 15.318899997510016,
"policy_ms": 2.181699965149164,
"execution_ms": 55.76350004412234,
"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": 17.741200048476458,
"policy_ms": 2.4813999189063907,
"execution_ms": 21.54819993302226,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 20,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9989357590675354,
"target_confidence": 1.0,
"observation_ms": 19.367799977771938,
"policy_ms": 3.077700035646558,
"execution_ms": 28.341200086288154,
"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": 17.52290001604706,
"policy_ms": 2.6355000445619226,
"execution_ms": 54.26959996111691,
"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": 16.09010004904121,
"policy_ms": 2.549300086684525,
"execution_ms": 55.372499977238476,
"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": 15.668199979700148,
"policy_ms": 3.1169999856501818,
"execution_ms": 19.12760001141578,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 24,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999839067459106,
"target_confidence": 1.0,
"observation_ms": 18.24030000716448,
"policy_ms": 2.835199935361743,
"execution_ms": 53.59849997330457,
"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": 15.502800000831485,
"policy_ms": 2.149400068446994,
"execution_ms": 57.814099942333996,
"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": 17.772700055502355,
"policy_ms": 3.4591000294312835,
"execution_ms": 11.525699985213578,
"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": 17.285500071011484,
"policy_ms": 1.628599944524467,
"execution_ms": 17.25599996279925,
"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": 13.44849995803088,
"policy_ms": 1.9515000749379396,
"execution_ms": 11.138500063680112,
"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": 12.951699900440872,
"policy_ms": 2.086500055156648,
"execution_ms": 36.58199997153133,
"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": 15.507000032812357,
"policy_ms": 2.9299999587237835,
"execution_ms": 10.971100069582462,
"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": 17.220500041730702,
"policy_ms": 2.926700050011277,
"execution_ms": 20.08299995213747,
"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": 15.720500028692186,
"policy_ms": 2.1554999984800816,
"execution_ms": 18.35559995379299,
"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": 0.9999918937683105,
"observation_ms": 14.345600036904216,
"policy_ms": 1.8833000212907791,
"execution_ms": 2.653100062161684,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 34,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9991865754127502,
"target_confidence": 1.0,
"observation_ms": 17.341499915346503,
"policy_ms": 3.9911000058054924,
"execution_ms": 18.907299963757396,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 35,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999992847442627,
"target_confidence": 1.0,
"observation_ms": 14.940900029614568,
"policy_ms": 1.7117999959737062,
"execution_ms": 55.279399966821074,
"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": 14.2782999901101,
"policy_ms": 2.2227000445127487,
"execution_ms": 11.639100033789873,
"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": 18.447200069203973,
"policy_ms": 2.64920003246516,
"execution_ms": 22.73369999602437,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 38,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9380846619606018,
"target_confidence": 1.0,
"observation_ms": 18.356399959884584,
"policy_ms": 2.828199998475611,
"execution_ms": 11.570300091989338,
"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": 0.9524294137954712,
"observation_ms": 13.235999969765544,
"policy_ms": 3.237399971112609,
"execution_ms": 12.619900051504374,
"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": 0.9989209175109863,
"observation_ms": 14.78179998230189,
"policy_ms": 2.5893000420182943,
"execution_ms": 2.7925000758841634,
"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": 14.161800034344196,
"policy_ms": 2.2444999776780605,
"execution_ms": 20.212199888192117,
"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": 15.984900062903762,
"policy_ms": 3.330400097183883,
"execution_ms": 18.50799995008856,
"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": 14.629499986767769,
"policy_ms": 1.6976000042632222,
"execution_ms": 18.62929994240403,
"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": 18.890900071710348,
"policy_ms": 3.423499991185963,
"execution_ms": 44.28839997854084,
"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": 18.07880005799234,
"policy_ms": 1.881699892692268,
"execution_ms": 21.7675999738276,
"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": 15.39379998575896,
"policy_ms": 2.288699964992702,
"execution_ms": 17.625999986194074,
"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": 0.9999927282333374,
"observation_ms": 14.32419999036938,
"policy_ms": 2.470299950800836,
"execution_ms": 12.402099906466901,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"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": 16.879200004041195,
"policy_ms": 2.7562000323086977,
"execution_ms": 12.391900061629713,
"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": 15.33019996713847,
"policy_ms": 1.9475000444799662,
"execution_ms": 11.631699977442622,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 50,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.6744232177734375,
"target_confidence": 1.0,
"observation_ms": 16.53129991609603,
"policy_ms": 2.243799972347915,
"execution_ms": 2.6498999213799834,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 51,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 14.148900052532554,
"policy_ms": 2.399299992248416,
"execution_ms": 16.850900021381676,
"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": 15.341399936005473,
"policy_ms": 2.228700090199709,
"execution_ms": 20.004799938760698,
"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": 0.9999998807907104,
"observation_ms": 16.835800022818148,
"policy_ms": 2.710500033572316,
"execution_ms": 2.8714999789372087,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 54,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.999863862991333,
"target_confidence": 1.0,
"observation_ms": 16.745399916544557,
"policy_ms": 2.9193999944254756,
"execution_ms": 18.452899996191263,
"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": 1.0,
"observation_ms": 16.656399937346578,
"policy_ms": 2.845000009983778,
"execution_ms": 18.603299977257848,
"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": 0.9999996423721313,
"observation_ms": 15.194299980066717,
"policy_ms": 3.7309000035747886,
"execution_ms": 2.539800014346838,
"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": 15.091400011442602,
"policy_ms": 2.4770000018179417,
"execution_ms": 46.00049997679889,
"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": 17.82049995381385,
"policy_ms": 3.619199967943132,
"execution_ms": 17.847699928097427,
"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": 15.140800038352609,
"policy_ms": 3.8938000798225403,
"execution_ms": 18.620199989527464,
"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": 16.123799956403673,
"policy_ms": 2.451400039717555,
"execution_ms": 18.99300003424287,
"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": 19.06960003543645,
"policy_ms": 4.310499993152916,
"execution_ms": 18.57810001820326,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 62,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9984056353569031,
"target_confidence": 1.0,
"observation_ms": 16.65180001873523,
"policy_ms": 2.936400007456541,
"execution_ms": 11.463699978776276,
"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": 0.9954480528831482,
"observation_ms": 16.483900020830333,
"policy_ms": 4.453599918633699,
"execution_ms": 3.3304999815300107,
"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": 16.926200012676418,
"policy_ms": 2.8759000124409795,
"execution_ms": 11.980699957348406,
"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": 15.666200080886483,
"policy_ms": 2.0320999901741743,
"execution_ms": 2.2483000066131353,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 66,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9823814034461975,
"target_confidence": 1.0,
"observation_ms": 17.019399907439947,
"policy_ms": 3.4302000422030687,
"execution_ms": 48.08139998931438,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 67,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9998229146003723,
"target_confidence": 1.0,
"observation_ms": 16.775500029325485,
"policy_ms": 1.930900034494698,
"execution_ms": 18.81799998227507,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 68,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 0.999362051486969,
"target_confidence": 1.0,
"observation_ms": 14.861600007861853,
"policy_ms": 1.7525999573990703,
"execution_ms": 2.316199941560626,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 69,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "C",
"predicted_action": "A",
"action_confidence": 1.0,
"target_confidence": 0.999445378780365,
"observation_ms": 20.707699935883284,
"policy_ms": 2.239100052975118,
"execution_ms": 3.15140001475811,
"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": 17.91260007303208,
"policy_ms": 2.6763000059872866,
"execution_ms": 26.25090000219643,
"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": 15.43979998677969,
"policy_ms": 2.317399950698018,
"execution_ms": 16.30629994906485,
"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": 0.8963271975517273,
"observation_ms": 16.73909998498857,
"policy_ms": 2.9506999999284744,
"execution_ms": 11.113999993540347,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 73,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9999988079071045,
"observation_ms": 13.182500028051436,
"policy_ms": 1.789500005543232,
"execution_ms": 16.17940003052354,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 74,
"template": "nested",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.6012862920761108,
"target_confidence": 1.0,
"observation_ms": 14.6752999862656,
"policy_ms": 3.1855000415816903,
"execution_ms": 2.329000039026141,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 75,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.364199967123568,
"policy_ms": 1.8962000031024218,
"execution_ms": 18.064500065520406,
"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": 13.066100073046982,
"policy_ms": 1.602599979378283,
"execution_ms": 17.419800045900047,
"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": 17.11209991481155,
"policy_ms": 3.523800056427717,
"execution_ms": 12.085000053048134,
"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": 15.945799998007715,
"policy_ms": 2.0475999917834997,
"execution_ms": 18.963399925269186,
"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": 18.105900031514466,
"policy_ms": 4.0596999460831285,
"execution_ms": 17.803399940021336,
"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": 15.763400006107986,
"policy_ms": 2.6825000531971455,
"execution_ms": 55.71610003244132,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 81,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999572038650513,
"target_confidence": 1.0,
"observation_ms": 15.868999995291233,
"policy_ms": 2.6097999652847648,
"execution_ms": 54.374199942685664,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 82,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.8975507616996765,
"target_confidence": 1.0,
"observation_ms": 15.959199983626604,
"policy_ms": 3.017399925738573,
"execution_ms": 56.86929996591061,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 83,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9982919096946716,
"target_confidence": 1.0,
"observation_ms": 19.22529994044453,
"policy_ms": 2.697200048714876,
"execution_ms": 11.397000052966177,
"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": 17.615900025703013,
"policy_ms": 3.63880000077188,
"execution_ms": 13.063999940641224,
"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": 14.511700021103024,
"policy_ms": 2.7857000241056085,
"execution_ms": 17.01329997740686,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 86,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999996423721313,
"target_confidence": 1.0,
"observation_ms": 14.36120003927499,
"policy_ms": 1.8855000380426645,
"execution_ms": 24.41690000705421,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 87,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9854127764701843,
"target_confidence": 1.0,
"observation_ms": 19.69929994083941,
"policy_ms": 2.6805000379681587,
"execution_ms": 50.03080004826188,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 88,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9993982315063477,
"target_confidence": 1.0,
"observation_ms": 19.228799967095256,
"policy_ms": 3.0580000020563602,
"execution_ms": 49.42660010419786,
"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": 22.761099971830845,
"policy_ms": 5.15910005196929,
"execution_ms": 22.098699933849275,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 90,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9993982315063477,
"target_confidence": 0.9999520778656006,
"observation_ms": 15.120600000955164,
"policy_ms": 3.2110000029206276,
"execution_ms": 27.894600061699748,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 91,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9313865303993225,
"target_confidence": 1.0,
"observation_ms": 13.383200042881072,
"policy_ms": 2.8343999292701483,
"execution_ms": 16.3021000334993,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 92,
"template": "table",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9995154142379761,
"observation_ms": 15.163899981416762,
"policy_ms": 2.8198999352753162,
"execution_ms": 10.540399933233857,
"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": 12.40700006019324,
"policy_ms": 1.7691999673843384,
"execution_ms": 10.332000092603266,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 94,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9896392822265625,
"target_confidence": 1.0,
"observation_ms": 14.853800064884126,
"policy_ms": 2.810999983921647,
"execution_ms": 29.672999982722104,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 95,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9500922560691833,
"target_confidence": 1.0,
"observation_ms": 13.254300109110773,
"policy_ms": 2.440100070089102,
"execution_ms": 23.67790008429438,
"status": "ok",
"code": "CLICK"
},
{
"sample_id": 96,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9655914902687073,
"target_confidence": 1.0,
"observation_ms": 13.774699997156858,
"policy_ms": 2.7686000103130937,
"execution_ms": 9.721900103613734,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 97,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9535804390907288,
"target_confidence": 1.0,
"observation_ms": 11.383499950170517,
"policy_ms": 2.25639995187521,
"execution_ms": 16.029999940656126,
"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": 13.237299979664385,
"policy_ms": 1.9378999713808298,
"execution_ms": 17.197499983012676,
"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": 17.470300081185997,
"policy_ms": 3.1556999310851097,
"execution_ms": 2.621099934913218,
"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": 0.9999998807907104,
"observation_ms": 13.75969999935478,
"policy_ms": 2.693300019018352,
"execution_ms": 2.2585000842809677,
"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": 12.587200035341084,
"policy_ms": 2.363799954764545,
"execution_ms": 2.671200083568692,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 102,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9827704429626465,
"target_confidence": 1.0,
"observation_ms": 17.5406999187544,
"policy_ms": 3.0599000165238976,
"execution_ms": 17.11390004493296,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 103,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9999997615814209,
"target_confidence": 1.0,
"observation_ms": 12.314500054344535,
"policy_ms": 1.8863000441342592,
"execution_ms": 16.594600048847497,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 104,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9209970831871033,
"observation_ms": 14.165100059472024,
"policy_ms": 2.4361000396311283,
"execution_ms": 15.23400004953146,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 105,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 12.003300013020635,
"policy_ms": 1.6154000768437982,
"execution_ms": 18.52439995855093,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 106,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9997993111610413,
"target_confidence": 1.0,
"observation_ms": 13.28109996393323,
"policy_ms": 1.9484000513330102,
"execution_ms": 10.351400007493794,
"status": "rejected",
"code": "SELECT_ROLE_MISMATCH"
},
{
"sample_id": 107,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 0.9982926249504089,
"observation_ms": 14.476899988949299,
"policy_ms": 3.381800022907555,
"execution_ms": 15.20399993751198,
"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": 14.83090000692755,
"policy_ms": 3.055799985304475,
"execution_ms": 2.2097000619396567,
"status": "ok",
"code": "ASK_USER"
},
{
"sample_id": 109,
"template": "nested",
"success": false,
"abstained": false,
"expected_action": "T",
"predicted_action": "O",
"action_confidence": 0.9956113696098328,
"target_confidence": 1.0,
"observation_ms": 15.895100077614188,
"policy_ms": 3.56480001937598,
"execution_ms": 12.63380004093051,
"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": 13.509899959899485,
"policy_ms": 1.84599997010082,
"execution_ms": 15.045200008898973,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 111,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "O",
"predicted_action": "O",
"action_confidence": 1.0,
"target_confidence": 1.0,
"observation_ms": 16.48460002616048,
"policy_ms": 2.6233999524265528,
"execution_ms": 16.111999982967973,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 112,
"template": "table",
"success": false,
"abstained": true,
"expected_action": "T",
"predicted_action": "A",
"action_confidence": 0.8389744758605957,
"target_confidence": 1.0,
"observation_ms": 17.920400016009808,
"policy_ms": 2.507500001229346,
"execution_ms": 2.3775999434292316,
"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": 13.258200022391975,
"policy_ms": 2.506399992853403,
"execution_ms": 22.85220008343458,
"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": 14.853500062599778,
"policy_ms": 3.9912000065669417,
"execution_ms": 19.208399928174913,
"status": "ok",
"code": "SELECT"
},
{
"sample_id": 115,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9923478364944458,
"target_confidence": 1.0,
"observation_ms": 13.800600077956915,
"policy_ms": 2.797399996779859,
"execution_ms": 16.694299993105233,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 116,
"template": "table",
"success": true,
"abstained": false,
"expected_action": "T",
"predicted_action": "T",
"action_confidence": 0.9923343062400818,
"target_confidence": 1.0,
"observation_ms": 14.609100064262748,
"policy_ms": 2.129599917680025,
"execution_ms": 17.368000000715256,
"status": "ok",
"code": "TYPE"
},
{
"sample_id": 117,
"template": "nested",
"success": true,
"abstained": false,
"expected_action": "C",
"predicted_action": "C",
"action_confidence": 0.9999951124191284,
"target_confidence": 1.0,
"observation_ms": 15.091100009158254,
"policy_ms": 1.891499967314303,
"execution_ms": 21.638500038534403,
"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": 13.210700009949505,
"policy_ms": 2.4665999226272106,
"execution_ms": 14.696700032800436,
"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": 0.9999986886978149,
"observation_ms": 13.8888000510633,
"policy_ms": 3.2760000322014093,
"execution_ms": 15.402200049720705,
"status": "ok",
"code": "SELECT"
}
]
}