PEFT
Safetensors
English
sev
research
cybersecurity
agent-activity
decision-model
lora
Sev-4B / result.json
macmacmacmac's picture
Publish Sev-4B v0.3.0 response-policy research checkpoint
da0a131 verified
Raw History Blame Contribute Delete
82.1 kB
{
"objective": -0.17643950559609828,
"paired_flip": null,
"unknowable": null,
"clean": {
"n": 2632,
"nll": 0.4626010690091542,
"acc": 0.7868541033434651,
"ece": 0.0822959829967011,
"brier": 0.2695405506463609,
"mean_conf": 0.8650301490049586,
"confident_error_rate": 0.014437689969604863,
"coverage_at_0_9": 0.6565349544072948,
"accuracy_at_0_9": 0.9780092592592593,
"coverage_at_5pct_error": 0.6808510638297872,
"coverage_at_1pct_error": 0.5828267477203647,
"aurc": 0.04539486327850754,
"error_rate_at_0_9": 0.02199074074074074,
"confidence_bias": 0.0781760456614935,
"top_bins": {
"0.9": {
"n": 1728,
"errors": 38,
"error_rate": 0.02199074074074074
},
"0.95": {
"n": 1675,
"errors": 28,
"error_rate": 0.01671641791044776
},
"0.99": {
"n": 1519,
"errors": 15,
"error_rate": 0.009874917709019092
}
},
"selective": {
"0.5": {
"coverage": 0.5155775075987842,
"accuracy": 0.9918938835666913,
"confidence_cutoff": 0.9953955617749282
},
"0.8": {
"coverage": 0.8028115501519757,
"accuracy": 0.8920965451964032,
"confidence_cutoff": 0.658356020724118
}
}
},
"tasks": {
"excytin_file": {
"n": 80,
"nll": 8.416562133899781e-05,
"acc": 1.0,
"ece": 8.407504508700647e-05,
"brier": 3.608306194877327e-07,
"mean_conf": 0.999915924954913,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -8.407504508700647e-05,
"top_bins": {
"0.9": {
"n": 80,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 80,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 80,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999870465451609
},
"0.8": {
"coverage": 0.8,
"accuracy": 1.0,
"confidence_cutoff": 0.9999445146924221
}
}
},
"excytin_parent_join": {
"n": 78,
"nll": 0.0010931532029286512,
"acc": 1.0,
"ece": 0.0010890559164937752,
"brier": 1.524968968159761e-05,
"mean_conf": 0.9989109440835062,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.0010890559164937752,
"top_bins": {
"0.9": {
"n": 78,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 78,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 77,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9997808486535813
},
"0.8": {
"coverage": 0.8076923076923077,
"accuracy": 1.0,
"confidence_cutoff": 0.9985521003494622
}
}
},
"excytin_process": {
"n": 120,
"nll": 0.00038924968205708544,
"acc": 1.0,
"ece": 0.00038892368944332123,
"brier": 1.2813112890567744e-06,
"mean_conf": 0.9996110763105567,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.00038892368944332123,
"top_bins": {
"0.9": {
"n": 120,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 120,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 120,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999547557532524
},
"0.8": {
"coverage": 0.8,
"accuracy": 1.0,
"confidence_cutoff": 0.9992749850755753
}
}
},
"excytin_signin": {
"n": 120,
"nll": 0.0009466221977245799,
"acc": 1.0,
"ece": 0.0009222842581878554,
"brier": 7.013154556645113e-05,
"mean_conf": 0.9990777157418121,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.0009222842581878554,
"top_bins": {
"0.9": {
"n": 120,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 119,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 119,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999016374480455
},
"0.8": {
"coverage": 0.8,
"accuracy": 1.0,
"confidence_cutoff": 0.9997216681533668
}
}
},
"sev_guide_detector": {
"n": 1064,
"nll": 0.8605571101399087,
"acc": 0.6005639097744361,
"ece": 0.14734385206430384,
"brier": 0.5008109312564021,
"mean_conf": 0.7382136284198534,
"confident_error_rate": 0.017857142857142856,
"coverage_at_0_9": 0.33270676691729323,
"accuracy_at_0_9": 0.9463276836158192,
"coverage_at_5pct_error": 0.3082706766917293,
"coverage_at_1pct_error": 0.0,
"aurc": 0.19350209200158913,
"error_rate_at_0_9": 0.05367231638418079,
"confidence_bias": 0.1376497186454173,
"top_bins": {
"0.9": {
"n": 354,
"errors": 19,
"error_rate": 0.05367231638418079
},
"0.95": {
"n": 327,
"errors": 13,
"error_rate": 0.039755351681957186
},
"0.99": {
"n": 319,
"errors": 12,
"error_rate": 0.03761755485893417
}
},
"selective": {
"0.5": {
"coverage": 0.5028195488721805,
"accuracy": 0.8205607476635514,
"confidence_cutoff": 0.7059991149306561
},
"0.8": {
"coverage": 0.8035714285714286,
"accuracy": 0.6596491228070176,
"confidence_cutoff": 0.5473316703985754
}
}
},
"sev_guide_triage": {
"n": 231,
"nll": 0.8396428451107271,
"acc": 0.5670995670995671,
"ece": 0.1889188281653689,
"brier": 0.5162927524049745,
"mean_conf": 0.7421494516023849,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.3593073593073593,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.3722943722943723,
"coverage_at_1pct_error": 0.36363636363636365,
"aurc": 0.20987091476964936,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.17504988450281778,
"top_bins": {
"0.9": {
"n": 83,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 80,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 14,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5627705627705628,
"accuracy": 0.7153846153846154,
"confidence_cutoff": 0.7564145922660828
},
"0.8": {
"coverage": 0.8051948051948052,
"accuracy": 0.5806451612903226,
"confidence_cutoff": 0.51023405030021
}
}
},
"sev_swarmtraces_response_policy": {
"n": 175,
"nll": 0.49844721765472333,
"acc": 0.84,
"ece": 0.1173563845984423,
"brier": 0.26967228692055817,
"mean_conf": 0.955988843320762,
"confident_error_rate": 0.10285714285714286,
"coverage_at_0_9": 0.8742857142857143,
"accuracy_at_0_9": 0.8823529411764706,
"coverage_at_5pct_error": 0.6114285714285714,
"coverage_at_1pct_error": 0.44,
"aurc": 0.044632779737602504,
"error_rate_at_0_9": 0.11764705882352941,
"confidence_bias": 0.11598884332076198,
"top_bins": {
"0.9": {
"n": 153,
"errors": 18,
"error_rate": 0.11764705882352941
},
"0.95": {
"n": 140,
"errors": 14,
"error_rate": 0.1
},
"0.99": {
"n": 92,
"errors": 3,
"error_rate": 0.03260869565217391
}
},
"selective": {
"0.5": {
"coverage": 0.5028571428571429,
"accuracy": 0.9772727272727273,
"confidence_cutoff": 0.9904485381783863
},
"0.8": {
"coverage": 0.8,
"accuracy": 0.9,
"confidence_cutoff": 0.9516673045977523
}
}
},
"sev_swarmtraces_static": {
"n": 354,
"nll": 0.04944532768977841,
"acc": 0.980225988700565,
"ece": 0.01487544035693287,
"brier": 0.024608535342050798,
"mean_conf": 0.9802643779708107,
"confident_error_rate": 0.002824858757062147,
"coverage_at_0_9": 0.9463276836158192,
"accuracy_at_0_9": 0.9970149253731343,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 0.9858757062146892,
"aurc": 0.0005032049402250012,
"error_rate_at_0_9": 0.0029850746268656717,
"confidence_bias": 3.8389270245686724e-05,
"top_bins": {
"0.9": {
"n": 335,
"errors": 1,
"error_rate": 0.0029850746268656717
},
"0.95": {
"n": 330,
"errors": 1,
"error_rate": 0.0030303030303030303
},
"0.99": {
"n": 308,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999276209511099
},
"0.8": {
"coverage": 0.8022598870056498,
"accuracy": 1.0,
"confidence_cutoff": 0.997796467038603
}
}
},
"sev_sysmon_native_file": {
"n": 62,
"nll": 0.008428780795422771,
"acc": 1.0,
"ece": 0.007810434776248104,
"brier": 0.0017443201233063612,
"mean_conf": 0.9921895652237519,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.9838709677419355,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.0078104347762480986,
"top_bins": {
"0.9": {
"n": 61,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 59,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 57,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9991686260052061
},
"0.8": {
"coverage": 0.8064516129032258,
"accuracy": 1.0,
"confidence_cutoff": 0.9962482122843107
}
}
},
"sev_sysmon_native_join": {
"n": 120,
"nll": 0.00039767294618876087,
"acc": 1.0,
"ece": 0.0003974740966455892,
"brier": 7.310901229709924e-07,
"mean_conf": 0.9996025259033544,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.0003974740966455892,
"top_bins": {
"0.9": {
"n": 120,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 120,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 120,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9997660582574378
},
"0.8": {
"coverage": 0.8,
"accuracy": 1.0,
"confidence_cutoff": 0.9994606035447323
}
}
},
"sev_sysmon_native_other_effect": {
"n": 88,
"nll": 0.005466714567741097,
"acc": 1.0,
"ece": 0.005048372154544871,
"brier": 0.0014126265728775101,
"mean_conf": 0.994951627845455,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.9886363636363636,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.005048372154545011,
"top_bins": {
"0.9": {
"n": 87,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 86,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 83,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9997677646417501
},
"0.8": {
"coverage": 0.8068181818181818,
"accuracy": 1.0,
"confidence_cutoff": 0.9978176224669177
}
}
},
"sev_sysmon_native_process": {
"n": 74,
"nll": 0.004798899209615666,
"acc": 1.0,
"ece": 0.004644321057477101,
"brier": 0.0005716684001551928,
"mean_conf": 0.995355678942523,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.9864864864864865,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.00464432105747703,
"top_bins": {
"0.9": {
"n": 73,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 72,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 68,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999268900168323
},
"0.8": {
"coverage": 0.8108108108108109,
"accuracy": 1.0,
"confidence_cutoff": 0.9973453419434639
}
}
},
"sev_sysmon_native_registry": {
"n": 66,
"nll": 0.024015813931122083,
"acc": 0.9848484848484849,
"ece": 0.016913465896023366,
"brier": 0.01690246747159733,
"mean_conf": 0.9866786138448916,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.9696969696969697,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 0.9696969696969697,
"aurc": 0.00046266864448682633,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.0018301289964067768,
"top_bins": {
"0.9": {
"n": 64,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 64,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 62,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9998656142719909
},
"0.8": {
"coverage": 0.803030303030303,
"accuracy": 1.0,
"confidence_cutoff": 0.9982153954384291
}
}
}
},
"variants": {
"clean": {
"n": 2632,
"nll": 0.4626010690091542,
"acc": 0.7868541033434651,
"ece": 0.0822959829967011,
"brier": 0.2695405506463609,
"mean_conf": 0.8650301490049586,
"confident_error_rate": 0.014437689969604863,
"coverage_at_0_9": 0.6565349544072948,
"accuracy_at_0_9": 0.9780092592592593,
"coverage_at_5pct_error": 0.6808510638297872,
"coverage_at_1pct_error": 0.5828267477203647,
"aurc": 0.04539486327850754,
"error_rate_at_0_9": 0.02199074074074074,
"confidence_bias": 0.0781760456614935,
"top_bins": {
"0.9": {
"n": 1728,
"errors": 38,
"error_rate": 0.02199074074074074
},
"0.95": {
"n": 1675,
"errors": 28,
"error_rate": 0.01671641791044776
},
"0.99": {
"n": 1519,
"errors": 15,
"error_rate": 0.009874917709019092
}
},
"selective": {
"0.5": {
"coverage": 0.5155775075987842,
"accuracy": 0.9918938835666913,
"confidence_cutoff": 0.9953955617749282
},
"0.8": {
"coverage": 0.8028115501519757,
"accuracy": 0.8920965451964032,
"confidence_cutoff": 0.658356020724118
}
}
}
},
"heldout_tasks": {},
"permutation": {
"n": 0,
"mean_max_delta": null,
"flip_rate": null
},
"temperature": 1.6817928305074288,
"calibrated_clean": {
"n": 2632,
"nll": 0.42892992382965894,
"acc": 0.7868541033434651,
"ece": 0.04404789769068498,
"brier": 0.25086130169182097,
"mean_conf": 0.8094973007371603,
"confident_error_rate": 0.007978723404255319,
"coverage_at_0_9": 0.6196808510638298,
"accuracy_at_0_9": 0.9871244635193133,
"coverage_at_5pct_error": 0.6918693009118541,
"coverage_at_1pct_error": 0.5395136778115501,
"aurc": 0.045402363700726256,
"error_rate_at_0_9": 0.012875536480686695,
"confidence_bias": 0.022643197393695247,
"top_bins": {
"0.9": {
"n": 1631,
"errors": 21,
"error_rate": 0.012875536480686695
},
"0.95": {
"n": 1153,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 776,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5208966565349544,
"accuracy": 0.9912472647702407,
"confidence_cutoff": 0.9486799539412789
},
"0.8": {
"coverage": 0.8111702127659575,
"accuracy": 0.8861826697892272,
"confidence_cutoff": 0.52766162421842
}
}
},
"metric_policy": {
"version": 2,
"selective_ties": "whole_confidence_groups",
"coverage_at_error": "in-sample maximum over confidence thresholds; not a deployed error guarantee",
"aurc": "right-step integral over whole confidence groups",
"confident_error_rate": "high-confidence errors divided by all questions",
"error_rate_at_0_9": "errors divided by questions accepted at p_max >= 0.9",
"nll": "exact from logits when recorded; otherwise from floored probabilities",
"nll_floor": 1e-09,
"renormalize_returned_probabilities": true,
"raw_sums_outside_1e_5": 0,
"returned_zeros": 0
},
"coverage": {
"requested_records": 1828,
"requested_questions": 2632,
"evaluated_records": 1828,
"evaluated_questions": 2632,
"rejected_records": 0,
"truncated_records": 0
},
"latency_ms": {
"median": 54.25747899994349,
"p95": 161.14951469993457
},
"calibration": {
"inference_temperature": 1.0,
"additional_temperature": 1.6817928305074288,
"logits_recorded": true
},
"transfer": {
"objective": -0.4988755241804635,
"paired_flip": {
"pairs": 16,
"flip_rate": 0.9375,
"both_correct_rate": 0.9375,
"invariant_pairs": 8,
"invariance_rate": 1.0,
"invariant_both_correct_rate": 0.875
},
"unknowable": null,
"clean": {
"n": 243,
"nll": 0.6065943824685833,
"acc": 0.8683127572016461,
"ece": 0.09195653550207036,
"brier": 0.23499321102178952,
"mean_conf": 0.9525644631029061,
"confident_error_rate": 0.09053497942386832,
"coverage_at_0_9": 0.8600823045267489,
"accuracy_at_0_9": 0.8947368421052632,
"coverage_at_5pct_error": 0.6872427983539094,
"coverage_at_1pct_error": 0.42386831275720166,
"aurc": 0.034793809228677,
"error_rate_at_0_9": 0.10526315789473684,
"confidence_bias": 0.08425170590125997,
"top_bins": {
"0.9": {
"n": 209,
"errors": 22,
"error_rate": 0.10526315789473684
},
"0.95": {
"n": 193,
"errors": 13,
"error_rate": 0.06735751295336788
},
"0.99": {
"n": 154,
"errors": 4,
"error_rate": 0.025974025974025976
}
},
"selective": {
"0.5": {
"coverage": 0.5020576131687243,
"accuracy": 0.9836065573770492,
"confidence_cutoff": 0.9985267483650163
},
"0.8": {
"coverage": 0.8024691358024691,
"accuracy": 0.9230769230769231,
"confidence_cutoff": 0.946113674977154
}
}
},
"tasks": {
"composition_held_and_or": {
"n": 32,
"nll": 0.24171629359001318,
"acc": 0.90625,
"ece": 0.08267706695037225,
"brier": 0.1580607438572586,
"mean_conf": 0.9889270669503722,
"confident_error_rate": 0.09375,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 0.90625,
"coverage_at_5pct_error": 0.9375,
"coverage_at_1pct_error": 0.90625,
"aurc": 0.0069010416666666664,
"error_rate_at_0_9": 0.09375,
"confidence_bias": 0.08267706695037225,
"top_bins": {
"0.9": {
"n": 32,
"errors": 3,
"error_rate": 0.09375
},
"0.95": {
"n": 30,
"errors": 1,
"error_rate": 0.03333333333333333
},
"0.99": {
"n": 26,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999364856833449
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.9996934954887139
}
}
},
"contrastive_authorization": {
"n": 16,
"nll": 1.502653141036028e-05,
"acc": 1.0,
"ece": 1.50264042420023e-05,
"brier": 5.139828295030656e-10,
"mean_conf": 0.999984973595758,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -1.50264042420023e-05,
"top_bins": {
"0.9": {
"n": 16,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 16,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 16,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999862890472545
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.9999813198967473
}
}
},
"emotion": {
"n": 8,
"nll": 1.4194273414243654,
"acc": 0.625,
"ece": 0.3420785503418361,
"brier": 0.6845960520300963,
"mean_conf": 0.967078550341836,
"confident_error_rate": 0.25,
"coverage_at_0_9": 0.875,
"accuracy_at_0_9": 0.7142857142857143,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.12842261904761904,
"error_rate_at_0_9": 0.2857142857142857,
"confidence_bias": 0.342078550341836,
"top_bins": {
"0.9": {
"n": 7,
"errors": 2,
"error_rate": 0.2857142857142857
},
"0.95": {
"n": 5,
"errors": 1,
"error_rate": 0.2
},
"0.99": {
"n": 3,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9869563807629563
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.7142857142857143,
"confidence_cutoff": 0.936063568486461
}
}
},
"mmlu": {
"n": 8,
"nll": 1.3129749769552814,
"acc": 0.625,
"ece": 0.15765322690405312,
"brier": 0.6484351711065982,
"mean_conf": 0.7567759888850003,
"confident_error_rate": 0.125,
"coverage_at_0_9": 0.5,
"accuracy_at_0_9": 0.75,
"coverage_at_5pct_error": 0.375,
"coverage_at_1pct_error": 0.375,
"aurc": 0.22336309523809525,
"error_rate_at_0_9": 0.25,
"confidence_bias": 0.1317759888850003,
"top_bins": {
"0.9": {
"n": 4,
"errors": 1,
"error_rate": 0.25
},
"0.95": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 1,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.75,
"confidence_cutoff": 0.9327223999584052
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.5714285714285714,
"confidence_cutoff": 0.485476400811401
}
}
},
"otrf_sysmon_file": {
"n": 16,
"nll": 0.008605175298168915,
"acc": 1.0,
"ece": 0.008437849080092708,
"brier": 0.0005211762382657875,
"mean_conf": 0.9915621509199073,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.008437849080092708,
"top_bins": {
"0.9": {
"n": 16,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 15,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 13,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9989837483137961
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.9925042879134804
}
}
},
"otrf_sysmon_join": {
"n": 16,
"nll": 0.12967885980971613,
"acc": 0.9375,
"ece": 0.0857233928404766,
"brier": 0.08146985002971384,
"mean_conf": 0.946506108546294,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.6875,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.9375,
"coverage_at_1pct_error": 0.9375,
"aurc": 0.00390625,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.009006108546294023,
"top_bins": {
"0.9": {
"n": 11,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 11,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 9,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9970209747654696
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.8702734279589676
}
}
},
"otrf_sysmon_process": {
"n": 24,
"nll": 0.16156109121321785,
"acc": 0.9583333333333334,
"ece": 0.05273169620250518,
"brier": 0.0899182770612567,
"mean_conf": 0.9768730534919899,
"confident_error_rate": 0.041666666666666664,
"coverage_at_0_9": 0.9583333333333334,
"accuracy_at_0_9": 0.9565217391304348,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 0.9166666666666666,
"aurc": 0.0035477053140096615,
"error_rate_at_0_9": 0.043478260869565216,
"confidence_bias": 0.01853972015865657,
"top_bins": {
"0.9": {
"n": 23,
"errors": 1,
"error_rate": 0.043478260869565216
},
"0.95": {
"n": 22,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 19,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9994396085787187
},
"0.8": {
"coverage": 0.8333333333333334,
"accuracy": 1.0,
"confidence_cutoff": 0.9832554759400715
}
}
},
"otrf_sysmon_registry": {
"n": 8,
"nll": 0.010723606364118954,
"acc": 1.0,
"ece": 0.010542385937563847,
"brier": 0.0006959554565011166,
"mean_conf": 0.9894576140624362,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.010542385937563847,
"top_bins": {
"0.9": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 5,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9972651302471073
},
"0.8": {
"coverage": 0.875,
"accuracy": 1.0,
"confidence_cutoff": 0.9840692701748682
}
}
},
"paws": {
"n": 8,
"nll": 1.0368545966100273,
"acc": 0.75,
"ece": 0.22498828525853157,
"brier": 0.34163600039007924,
"mean_conf": 0.9122532529823204,
"confident_error_rate": 0.125,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 0.8333333333333334,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.09494047619047619,
"error_rate_at_0_9": 0.16666666666666666,
"confidence_bias": 0.1622532529823204,
"top_bins": {
"0.9": {
"n": 6,
"errors": 1,
"error_rate": 0.16666666666666666
},
"0.95": {
"n": 6,
"errors": 1,
"error_rate": 0.16666666666666666
},
"0.99": {
"n": 6,
"errors": 1,
"error_rate": 0.16666666666666666
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9992691391151949
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.8571428571428571,
"confidence_cutoff": 0.749059870895155
}
}
},
"qnli": {
"n": 8,
"nll": 0.005181466224742151,
"acc": 1.0,
"ece": 0.005129334884136472,
"brier": 0.00020524982613720548,
"mean_conf": 0.9948706651158635,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.005129334884136472,
"top_bins": {
"0.9": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 6,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.999952371295075
},
"0.8": {
"coverage": 0.875,
"accuracy": 1.0,
"confidence_cutoff": 0.98872862957213
}
}
},
"sciq": {
"n": 8,
"nll": 0.00023928943016782004,
"acc": 1.0,
"ece": 0.0002391650142747892,
"brier": 4.955209174865095e-07,
"mean_conf": 0.9997608349857252,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.0002391650142747892,
"top_bins": {
"0.9": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 8,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999911919978735
},
"0.8": {
"coverage": 0.875,
"accuracy": 1.0,
"confidence_cutoff": 0.9994259298933852
}
}
},
"sev_swarmtraces_manual_credential": {
"n": 40,
"nll": 0.9530052125004369,
"acc": 0.825,
"ece": 0.17316335764162732,
"brier": 0.3580423587545788,
"mean_conf": 0.9202306277592299,
"confident_error_rate": 0.15,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 0.8,
"coverage_at_5pct_error": 0.225,
"coverage_at_1pct_error": 0.225,
"aurc": 0.10718612602417658,
"error_rate_at_0_9": 0.2,
"confidence_bias": 0.09523062775922997,
"top_bins": {
"0.9": {
"n": 30,
"errors": 6,
"error_rate": 0.2
},
"0.95": {
"n": 26,
"errors": 3,
"error_rate": 0.11538461538461539
},
"0.99": {
"n": 15,
"errors": 1,
"error_rate": 0.06666666666666667
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.9,
"confidence_cutoff": 0.9774245184450835
},
"0.8": {
"coverage": 0.8,
"accuracy": 0.8125,
"confidence_cutoff": 0.8542392185801473
}
}
},
"sev_swarmtraces_manual_flow": {
"n": 40,
"nll": 1.485896746743676,
"acc": 0.75,
"ece": 0.21977756775377905,
"brier": 0.43299049842888415,
"mean_conf": 0.9214803040956191,
"confident_error_rate": 0.15,
"coverage_at_0_9": 0.725,
"accuracy_at_0_9": 0.7931034482758621,
"coverage_at_5pct_error": 0.1,
"coverage_at_1pct_error": 0.1,
"aurc": 0.14190456225170725,
"error_rate_at_0_9": 0.20689655172413793,
"confidence_bias": 0.1714803040956191,
"top_bins": {
"0.9": {
"n": 29,
"errors": 6,
"error_rate": 0.20689655172413793
},
"0.95": {
"n": 27,
"errors": 6,
"error_rate": 0.2222222222222222
},
"0.99": {
"n": 21,
"errors": 2,
"error_rate": 0.09523809523809523
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.9,
"confidence_cutoff": 0.9901066734665328
},
"0.8": {
"coverage": 0.8,
"accuracy": 0.8125,
"confidence_cutoff": 0.8291658959545783
}
}
},
"sev_swarmtraces_manual_prerequisite": {
"n": 3,
"nll": 1.0331257533433365e-05,
"acc": 1.0,
"ece": 1.0331183196821137e-05,
"brier": 2.5195789327524225e-10,
"mean_conf": 0.9999896688168032,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -1.0331183196821137e-05,
"top_bins": {
"0.9": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 3,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.6666666666666666,
"accuracy": 1.0,
"confidence_cutoff": 0.9999897312178962
},
"0.8": {
"coverage": 1.0,
"accuracy": 1.0,
"confidence_cutoff": 0.9999810314632929
}
}
},
"tweet_offensive": {
"n": 8,
"nll": 0.7172428487540772,
"acc": 0.75,
"ece": 0.2179639808956667,
"brier": 0.44120571426799937,
"mean_conf": 0.9679639808956667,
"confident_error_rate": 0.25,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 0.75,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.09494047619047619,
"error_rate_at_0_9": 0.25,
"confidence_bias": 0.2179639808956667,
"top_bins": {
"0.9": {
"n": 8,
"errors": 2,
"error_rate": 0.25
},
"0.95": {
"n": 5,
"errors": 1,
"error_rate": 0.2
},
"0.99": {
"n": 3,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9897168920827885
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.8571428571428571,
"confidence_cutoff": 0.940377631626033
}
}
}
},
"variants": {
"authorized_dns_diagnostic": {
"n": 4,
"nll": 0.2732991829356235,
"acc": 0.75,
"ece": 0.2014060191596143,
"brier": 0.1826209474615037,
"mean_conf": 0.8245034642731555,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.5,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.75,
"coverage_at_1pct_error": 0.75,
"aurc": 0.0625,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.07450346427315546,
"top_bins": {
"0.9": {
"n": 2,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 2,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 2,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9941628768025105
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.75,
"confidence_cutoff": 0.5518189668655396
}
}
},
"cache_denied_no_reply": {
"n": 4,
"nll": 0.6290998127898555,
"acc": 0.5,
"ece": 0.19783432109801047,
"brier": 0.45073491547326267,
"mean_conf": 0.6842140294824197,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.25,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.25,
"coverage_at_1pct_error": 0.25,
"aurc": 0.41666666666666663,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.18421402948241972,
"top_bins": {
"0.9": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 0,
"errors": 0,
"error_rate": null
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.5,
"confidence_cutoff": 0.5997726159351691
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.5,
"confidence_cutoff": 0.5818420334307344
}
}
},
"clean": {
"n": 243,
"nll": 0.6065943824685833,
"acc": 0.8683127572016461,
"ece": 0.09195653550207036,
"brier": 0.23499321102178952,
"mean_conf": 0.9525644631029061,
"confident_error_rate": 0.09053497942386832,
"coverage_at_0_9": 0.8600823045267489,
"accuracy_at_0_9": 0.8947368421052632,
"coverage_at_5pct_error": 0.6872427983539094,
"coverage_at_1pct_error": 0.42386831275720166,
"aurc": 0.034793809228677,
"error_rate_at_0_9": 0.10526315789473684,
"confidence_bias": 0.08425170590125997,
"top_bins": {
"0.9": {
"n": 209,
"errors": 22,
"error_rate": 0.10526315789473684
},
"0.95": {
"n": 193,
"errors": 13,
"error_rate": 0.06735751295336788
},
"0.99": {
"n": 154,
"errors": 4,
"error_rate": 0.025974025974025976
}
},
"selective": {
"0.5": {
"coverage": 0.5020576131687243,
"accuracy": 0.9836065573770492,
"confidence_cutoff": 0.9985267483650163
},
"0.8": {
"coverage": 0.8024691358024691,
"accuracy": 0.9230769230769231,
"confidence_cutoff": 0.946113674977154
}
}
},
"dns_off_task_reply": {
"n": 4,
"nll": 2.500105858228899,
"acc": 0.25,
"ece": 0.7354215562262277,
"brier": 1.1856881009881057,
"mean_conf": 0.7180991063824902,
"confident_error_rate": 0.25,
"coverage_at_0_9": 0.25,
"accuracy_at_0_9": 0.0,
"coverage_at_5pct_error": 0.0,
"coverage_at_1pct_error": 0.0,
"aurc": 0.9375,
"error_rate_at_0_9": 1.0,
"confidence_bias": 0.4680991063824902,
"top_bins": {
"0.9": {
"n": 1,
"errors": 1,
"error_rate": 1.0
},
"0.95": {
"n": 1,
"errors": 1,
"error_rate": 1.0
},
"0.99": {
"n": 1,
"errors": 1,
"error_rate": 1.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.0,
"confidence_cutoff": 0.7394568794916744
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.25,
"confidence_cutoff": 0.465355100312525
}
}
},
"dns_unhelpful_reply": {
"n": 4,
"nll": 0.6130712887407269,
"acc": 0.75,
"ece": 0.2694959031277442,
"brier": 0.34519095756377294,
"mean_conf": 0.7624970557751488,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.5,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.75,
"coverage_at_1pct_error": 0.75,
"aurc": 0.0625,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.012497055775148813,
"top_bins": {
"0.9": {
"n": 2,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 0,
"errors": 0,
"error_rate": null
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9232891824527384
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.75,
"confidence_cutoff": 0.563985917805786
}
}
},
"dns_without_reply": {
"n": 4,
"nll": 0.6878185272523656,
"acc": 0.5,
"ece": 0.20221082782282854,
"brier": 0.5043315891024525,
"mean_conf": 0.7000800429377261,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.25,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.25,
"coverage_at_1pct_error": 0.25,
"aurc": 0.41666666666666663,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.20008004293772608,
"top_bins": {
"0.9": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 1,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.5,
"confidence_cutoff": 0.6943924514728984
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.5,
"confidence_cutoff": 0.5490827128017757
}
}
},
"none_absent": {
"n": 3,
"nll": 1.3777335821359413,
"acc": 0.6666666666666666,
"ece": 0.24885046106665176,
"brier": 0.5885968900899531,
"mean_conf": 0.9151737396988762,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.3333333333333333,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.6666666666666666,
"coverage_at_1pct_error": 0.6666666666666666,
"aurc": 0.1111111111111111,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.24850707303220954,
"top_bins": {
"0.9": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 1,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.6666666666666666,
"accuracy": 1.0,
"confidence_cutoff": 0.8739663040318306
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.6666666666666666,
"confidence_cutoff": 0.8720699971164613
}
}
},
"none_present": {
"n": 3,
"nll": 3.3971590445247757,
"acc": 0.0,
"ece": 0.806803931885096,
"brier": 1.589050038207996,
"mean_conf": 0.8068039318850961,
"confident_error_rate": 0.3333333333333333,
"coverage_at_0_9": 0.3333333333333333,
"accuracy_at_0_9": 0.0,
"coverage_at_5pct_error": 0.0,
"coverage_at_1pct_error": 0.0,
"aurc": 1.0,
"error_rate_at_0_9": 1.0,
"confidence_bias": 0.8068039318850961,
"top_bins": {
"0.9": {
"n": 1,
"errors": 1,
"error_rate": 1.0
},
"0.95": {
"n": 1,
"errors": 1,
"error_rate": 1.0
},
"0.99": {
"n": 0,
"errors": 0,
"error_rate": null
}
},
"selective": {
"0.5": {
"coverage": 0.6666666666666666,
"accuracy": 0.0,
"confidence_cutoff": 0.8592945698759779
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.0,
"confidence_cutoff": 0.5949657569957464
}
}
},
"operator_terminated": {
"n": 4,
"nll": 1.0359158594833722,
"acc": 0.75,
"ece": 0.2925896655492872,
"brier": 0.4933779585120464,
"mean_conf": 0.9106235817198012,
"confident_error_rate": 0.25,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 0.6666666666666666,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.14583333333333331,
"error_rate_at_0_9": 0.3333333333333333,
"confidence_bias": 0.16062358171980118,
"top_bins": {
"0.9": {
"n": 3,
"errors": 1,
"error_rate": 0.3333333333333333
},
"0.95": {
"n": 2,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 1,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9713811910576418
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.75,
"confidence_cutoff": 0.736067832341028
}
}
},
"ordinary_resolution": {
"n": 4,
"nll": 0.04811475260764305,
"acc": 1.0,
"ece": 0.04485818654799875,
"brier": 0.011362447845748204,
"mean_conf": 0.9551418134520012,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.04485818654799878,
"top_bins": {
"0.9": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 2,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9973615074301722
},
"0.8": {
"coverage": 1.0,
"accuracy": 1.0,
"confidence_cutoff": 0.848997818390719
}
}
},
"permuted": {
"n": 3,
"nll": 1.5849320188552285,
"acc": 0.3333333333333333,
"ece": 0.5115039138500523,
"brier": 0.948500922906351,
"mean_conf": 0.834218301404813,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.3333333333333333,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.3333333333333333,
"coverage_at_1pct_error": 0.3333333333333333,
"aurc": 0.38888888888888884,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.5008849680714798,
"top_bins": {
"0.9": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 0,
"errors": 0,
"error_rate": null
}
},
"selective": {
"0.5": {
"coverage": 0.6666666666666666,
"accuracy": 0.5,
"confidence_cutoff": 0.8701283299219073
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.3333333333333333,
"confidence_cutoff": 0.6484549929603911
}
}
},
"review_acknowledged": {
"n": 4,
"nll": 0.9430886337427746,
"acc": 0.75,
"ece": 0.26428833978133903,
"brier": 0.46621510579801406,
"mean_conf": 0.9076209540563065,
"confident_error_rate": 0.25,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 0.6666666666666666,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.14583333333333331,
"error_rate_at_0_9": 0.3333333333333333,
"confidence_bias": 0.1576209540563065,
"top_bins": {
"0.9": {
"n": 3,
"errors": 1,
"error_rate": 0.3333333333333333
},
"0.95": {
"n": 1,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 1,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9371813046912169
},
"0.8": {
"coverage": 1.0,
"accuracy": 0.75,
"confidence_cutoff": 0.786665228549935
}
}
}
},
"heldout_tasks": {
"composition_held_and_or": {
"n": 32,
"nll": 0.24171629359001318,
"acc": 0.90625,
"ece": 0.08267706695037225,
"brier": 0.1580607438572586,
"mean_conf": 0.9889270669503722,
"confident_error_rate": 0.09375,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 0.90625,
"coverage_at_5pct_error": 0.9375,
"coverage_at_1pct_error": 0.90625,
"aurc": 0.0069010416666666664,
"error_rate_at_0_9": 0.09375,
"confidence_bias": 0.08267706695037225,
"top_bins": {
"0.9": {
"n": 32,
"errors": 3,
"error_rate": 0.09375
},
"0.95": {
"n": 30,
"errors": 1,
"error_rate": 0.03333333333333333
},
"0.99": {
"n": 26,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999364856833449
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.9996934954887139
}
}
},
"contrastive_authorization": {
"n": 16,
"nll": 1.502653141036028e-05,
"acc": 1.0,
"ece": 1.50264042420023e-05,
"brier": 5.139828295030656e-10,
"mean_conf": 0.999984973595758,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -1.50264042420023e-05,
"top_bins": {
"0.9": {
"n": 16,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 16,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 16,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999862890472545
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.9999813198967473
}
}
},
"emotion": {
"n": 8,
"nll": 1.4194273414243654,
"acc": 0.625,
"ece": 0.3420785503418361,
"brier": 0.6845960520300963,
"mean_conf": 0.967078550341836,
"confident_error_rate": 0.25,
"coverage_at_0_9": 0.875,
"accuracy_at_0_9": 0.7142857142857143,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.12842261904761904,
"error_rate_at_0_9": 0.2857142857142857,
"confidence_bias": 0.342078550341836,
"top_bins": {
"0.9": {
"n": 7,
"errors": 2,
"error_rate": 0.2857142857142857
},
"0.95": {
"n": 5,
"errors": 1,
"error_rate": 0.2
},
"0.99": {
"n": 3,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9869563807629563
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.7142857142857143,
"confidence_cutoff": 0.936063568486461
}
}
},
"mmlu": {
"n": 8,
"nll": 1.3129749769552814,
"acc": 0.625,
"ece": 0.15765322690405312,
"brier": 0.6484351711065982,
"mean_conf": 0.7567759888850003,
"confident_error_rate": 0.125,
"coverage_at_0_9": 0.5,
"accuracy_at_0_9": 0.75,
"coverage_at_5pct_error": 0.375,
"coverage_at_1pct_error": 0.375,
"aurc": 0.22336309523809525,
"error_rate_at_0_9": 0.25,
"confidence_bias": 0.1317759888850003,
"top_bins": {
"0.9": {
"n": 4,
"errors": 1,
"error_rate": 0.25
},
"0.95": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 1,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.75,
"confidence_cutoff": 0.9327223999584052
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.5714285714285714,
"confidence_cutoff": 0.485476400811401
}
}
},
"otrf_sysmon_file": {
"n": 16,
"nll": 0.008605175298168915,
"acc": 1.0,
"ece": 0.008437849080092708,
"brier": 0.0005211762382657875,
"mean_conf": 0.9915621509199073,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.008437849080092708,
"top_bins": {
"0.9": {
"n": 16,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 15,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 13,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9989837483137961
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.9925042879134804
}
}
},
"otrf_sysmon_join": {
"n": 16,
"nll": 0.12967885980971613,
"acc": 0.9375,
"ece": 0.0857233928404766,
"brier": 0.08146985002971384,
"mean_conf": 0.946506108546294,
"confident_error_rate": 0.0,
"coverage_at_0_9": 0.6875,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 0.9375,
"coverage_at_1pct_error": 0.9375,
"aurc": 0.00390625,
"error_rate_at_0_9": 0.0,
"confidence_bias": 0.009006108546294023,
"top_bins": {
"0.9": {
"n": 11,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 11,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 9,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9970209747654696
},
"0.8": {
"coverage": 0.8125,
"accuracy": 1.0,
"confidence_cutoff": 0.8702734279589676
}
}
},
"otrf_sysmon_process": {
"n": 24,
"nll": 0.16156109121321785,
"acc": 0.9583333333333334,
"ece": 0.05273169620250518,
"brier": 0.0899182770612567,
"mean_conf": 0.9768730534919899,
"confident_error_rate": 0.041666666666666664,
"coverage_at_0_9": 0.9583333333333334,
"accuracy_at_0_9": 0.9565217391304348,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 0.9166666666666666,
"aurc": 0.0035477053140096615,
"error_rate_at_0_9": 0.043478260869565216,
"confidence_bias": 0.01853972015865657,
"top_bins": {
"0.9": {
"n": 23,
"errors": 1,
"error_rate": 0.043478260869565216
},
"0.95": {
"n": 22,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 19,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9994396085787187
},
"0.8": {
"coverage": 0.8333333333333334,
"accuracy": 1.0,
"confidence_cutoff": 0.9832554759400715
}
}
},
"otrf_sysmon_registry": {
"n": 8,
"nll": 0.010723606364118954,
"acc": 1.0,
"ece": 0.010542385937563847,
"brier": 0.0006959554565011166,
"mean_conf": 0.9894576140624362,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.010542385937563847,
"top_bins": {
"0.9": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 5,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9972651302471073
},
"0.8": {
"coverage": 0.875,
"accuracy": 1.0,
"confidence_cutoff": 0.9840692701748682
}
}
},
"paws": {
"n": 8,
"nll": 1.0368545966100273,
"acc": 0.75,
"ece": 0.22498828525853157,
"brier": 0.34163600039007924,
"mean_conf": 0.9122532529823204,
"confident_error_rate": 0.125,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 0.8333333333333334,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.09494047619047619,
"error_rate_at_0_9": 0.16666666666666666,
"confidence_bias": 0.1622532529823204,
"top_bins": {
"0.9": {
"n": 6,
"errors": 1,
"error_rate": 0.16666666666666666
},
"0.95": {
"n": 6,
"errors": 1,
"error_rate": 0.16666666666666666
},
"0.99": {
"n": 6,
"errors": 1,
"error_rate": 0.16666666666666666
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9992691391151949
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.8571428571428571,
"confidence_cutoff": 0.749059870895155
}
}
},
"qnli": {
"n": 8,
"nll": 0.005181466224742151,
"acc": 1.0,
"ece": 0.005129334884136472,
"brier": 0.00020524982613720548,
"mean_conf": 0.9948706651158635,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.005129334884136472,
"top_bins": {
"0.9": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 6,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.999952371295075
},
"0.8": {
"coverage": 0.875,
"accuracy": 1.0,
"confidence_cutoff": 0.98872862957213
}
}
},
"sciq": {
"n": 8,
"nll": 0.00023928943016782004,
"acc": 1.0,
"ece": 0.0002391650142747892,
"brier": 4.955209174865095e-07,
"mean_conf": 0.9997608349857252,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -0.0002391650142747892,
"top_bins": {
"0.9": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 8,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 8,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9999911919978735
},
"0.8": {
"coverage": 0.875,
"accuracy": 1.0,
"confidence_cutoff": 0.9994259298933852
}
}
},
"sev_swarmtraces_manual_credential": {
"n": 40,
"nll": 0.9530052125004369,
"acc": 0.825,
"ece": 0.17316335764162732,
"brier": 0.3580423587545788,
"mean_conf": 0.9202306277592299,
"confident_error_rate": 0.15,
"coverage_at_0_9": 0.75,
"accuracy_at_0_9": 0.8,
"coverage_at_5pct_error": 0.225,
"coverage_at_1pct_error": 0.225,
"aurc": 0.10718612602417658,
"error_rate_at_0_9": 0.2,
"confidence_bias": 0.09523062775922997,
"top_bins": {
"0.9": {
"n": 30,
"errors": 6,
"error_rate": 0.2
},
"0.95": {
"n": 26,
"errors": 3,
"error_rate": 0.11538461538461539
},
"0.99": {
"n": 15,
"errors": 1,
"error_rate": 0.06666666666666667
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.9,
"confidence_cutoff": 0.9774245184450835
},
"0.8": {
"coverage": 0.8,
"accuracy": 0.8125,
"confidence_cutoff": 0.8542392185801473
}
}
},
"sev_swarmtraces_manual_flow": {
"n": 40,
"nll": 1.485896746743676,
"acc": 0.75,
"ece": 0.21977756775377905,
"brier": 0.43299049842888415,
"mean_conf": 0.9214803040956191,
"confident_error_rate": 0.15,
"coverage_at_0_9": 0.725,
"accuracy_at_0_9": 0.7931034482758621,
"coverage_at_5pct_error": 0.1,
"coverage_at_1pct_error": 0.1,
"aurc": 0.14190456225170725,
"error_rate_at_0_9": 0.20689655172413793,
"confidence_bias": 0.1714803040956191,
"top_bins": {
"0.9": {
"n": 29,
"errors": 6,
"error_rate": 0.20689655172413793
},
"0.95": {
"n": 27,
"errors": 6,
"error_rate": 0.2222222222222222
},
"0.99": {
"n": 21,
"errors": 2,
"error_rate": 0.09523809523809523
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 0.9,
"confidence_cutoff": 0.9901066734665328
},
"0.8": {
"coverage": 0.8,
"accuracy": 0.8125,
"confidence_cutoff": 0.8291658959545783
}
}
},
"sev_swarmtraces_manual_prerequisite": {
"n": 3,
"nll": 1.0331257533433365e-05,
"acc": 1.0,
"ece": 1.0331183196821137e-05,
"brier": 2.5195789327524225e-10,
"mean_conf": 0.9999896688168032,
"confident_error_rate": 0.0,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 1.0,
"coverage_at_5pct_error": 1.0,
"coverage_at_1pct_error": 1.0,
"aurc": 0.0,
"error_rate_at_0_9": 0.0,
"confidence_bias": -1.0331183196821137e-05,
"top_bins": {
"0.9": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.95": {
"n": 3,
"errors": 0,
"error_rate": 0.0
},
"0.99": {
"n": 3,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.6666666666666666,
"accuracy": 1.0,
"confidence_cutoff": 0.9999897312178962
},
"0.8": {
"coverage": 1.0,
"accuracy": 1.0,
"confidence_cutoff": 0.9999810314632929
}
}
},
"tweet_offensive": {
"n": 8,
"nll": 0.7172428487540772,
"acc": 0.75,
"ece": 0.2179639808956667,
"brier": 0.44120571426799937,
"mean_conf": 0.9679639808956667,
"confident_error_rate": 0.25,
"coverage_at_0_9": 1.0,
"accuracy_at_0_9": 0.75,
"coverage_at_5pct_error": 0.5,
"coverage_at_1pct_error": 0.5,
"aurc": 0.09494047619047619,
"error_rate_at_0_9": 0.25,
"confidence_bias": 0.2179639808956667,
"top_bins": {
"0.9": {
"n": 8,
"errors": 2,
"error_rate": 0.25
},
"0.95": {
"n": 5,
"errors": 1,
"error_rate": 0.2
},
"0.99": {
"n": 3,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5,
"accuracy": 1.0,
"confidence_cutoff": 0.9897168920827885
},
"0.8": {
"coverage": 0.875,
"accuracy": 0.8571428571428571,
"confidence_cutoff": 0.940377631626033
}
}
}
},
"permutation": {
"n": 3,
"mean_max_delta": 0.04297798881434687,
"flip_rate": 0.0
},
"temperature": 1.6817928305074288,
"calibrated_clean": {
"n": 243,
"nll": 0.4460227427836622,
"acc": 0.8683127572016461,
"ece": 0.04490914804947624,
"brier": 0.21677989484802473,
"mean_conf": 0.9016047263613403,
"confident_error_rate": 0.024691358024691357,
"coverage_at_0_9": 0.6831275720164609,
"accuracy_at_0_9": 0.963855421686747,
"coverage_at_5pct_error": 0.7489711934156379,
"coverage_at_1pct_error": 0.4156378600823045,
"aurc": 0.03366327644063936,
"error_rate_at_0_9": 0.03614457831325301,
"confidence_bias": 0.033291969159694124,
"top_bins": {
"0.9": {
"n": 166,
"errors": 6,
"error_rate": 0.03614457831325301
},
"0.95": {
"n": 141,
"errors": 2,
"error_rate": 0.014184397163120567
},
"0.99": {
"n": 81,
"errors": 0,
"error_rate": 0.0
}
},
"selective": {
"0.5": {
"coverage": 0.5020576131687243,
"accuracy": 0.9836065573770492,
"confidence_cutoff": 0.9739727890189261
},
"0.8": {
"coverage": 0.8024691358024691,
"accuracy": 0.9282051282051282,
"confidence_cutoff": 0.8229542441861438
}
}
},
"metric_policy": {
"version": 2,
"selective_ties": "whole_confidence_groups",
"coverage_at_error": "in-sample maximum over confidence thresholds; not a deployed error guarantee",
"aurc": "right-step integral over whole confidence groups",
"confident_error_rate": "high-confidence errors divided by all questions",
"error_rate_at_0_9": "errors divided by questions accepted at p_max >= 0.9",
"nll": "exact from logits when recorded; otherwise from floored probabilities",
"nll_floor": 1e-09,
"renormalize_returned_probabilities": true,
"raw_sums_outside_1e_5": 0,
"returned_zeros": 0
},
"coverage": {
"requested_records": 185,
"requested_questions": 284,
"evaluated_records": 185,
"evaluated_questions": 284,
"rejected_records": 0,
"truncated_records": 0
},
"latency_ms": {
"median": 49.463423999895895,
"p95": 189.5706840000457
},
"calibration": {
"inference_temperature": 1.0,
"additional_temperature": 1.6817928305074288,
"logits_recorded": true
},
"suite_sha256": "adde94227c959c3bfd62ee2ca27d8a73d5b0fff96bf0500c627645e5a7d72f37"
},
"provenance": {
"config": {
"epochs": 1,
"seed": 4,
"lr": 2.5e-06,
"lora": 16,
"accum": 2,
"batch": 4,
"perm_kl": 0,
"perm_frac": 0.3,
"ord_w": 0.0,
"p_none": 0,
"p_none_distract": 0,
"p_distract": 0,
"p_none_pair": 0,
"synthetic_repeat": 1,
"public_frac": 1,
"head_lr": 0.0,
"weight_decay": 0.01,
"anchor_w": 0.0,
"label_smoothing": 0.0,
"brier_w": 0.0,
"focal_gamma": 0.0,
"base": "Qwen/Qwen3.5-4B-Base",
"base_revision": "1001bb4d826a52d1f399e183466143f4da7b741b",
"init_from": "macmacmacmac/Sev-4B@a1824aefba305fda86e3503b895a7d9b3871f79a",
"lora_targets": "all",
"head_dim": 256,
"weights_dtype": "fp32",
"dtype": "bf16",
"checkpointing": 1,
"option_isolation": 0,
"special_embeddings": 0
},
"config_sha256": "01ce0c9f84977e5c32d40dbd5c012634208c7770615b9e7d9d6f5950c042706f",
"suite_sha256": "3b9a80dfd212b6932b66ea520c35ab1a3b19e132a81af1b6b7b306d776a70a02",
"source_hashes": {
"kev/__init__.py": "e3b0c44298fc1c149afbf4c8996fb92427ae41e4649b934ca495991b7852b855",
"kev/anchors.py": "6963eafdb276db5a6c94d939eae675c761555553b8d0f963ffd803448beaabbb",
"kev/api.py": "7bffacfb762c626b8bc2f670f350295af5ccb0883dbe90239c7d2f8e5ef56582",
"kev/autoresearch.py": "f7d7fabb9c0df7065bee3fec4aa4bee7028c5d1565847aefe2d74e3d7d40ed8a",
"kev/benchmark.py": "8d486659a9036102386b077fcbd197fc0d85ae7752a4711666d6b3a95622b26f",
"kev/calibrate.py": "c1eff4744fabd349e8abca86777a7aa0cbea44904c8223d3b61fca3d43741519",
"kev/checkpoint.py": "9f1dbc5d3d7d3050aca4ee34e0578c9ad76b7a2a7467dfc7a4ad65e3c471db59",
"kev/compare.py": "3606dbf98bb305d66420158498cb837304d2edb8dab01cdaf2ec42964bef3435",
"kev/composition.py": "f335ed17e18e0a544893db5e22b9a059e6ce1b2e14dbb863ac7d7bbf8f3e0536",
"kev/contrastive.py": "cbb979aa5d40265ad0e64695f94b281d91751fa405811ddfa8212fede111edcf",
"kev/data.py": "a5a5e200f56b60e4bf30a195a4cc87a74afddae15999ec48c7543a4f9b59f71c",
"kev/device.py": "d1677fd98ec0979c7284546306e34e0d09298ca4042fc39eb2b32a74f4e975c4",
"kev/evaluate.py": "999264f2837dcfbf2ec93601aa4745e701698ab850a43ad89324672a6604965c",
"kev/experiment.py": "1a5ca47d2b3d236e53c87e8c4197704f162c6692aa008521d31ea491945693f0",
"kev/jev.py": "acd4cc3f1844e438cc83a8d409c15ef78a5ef64d39ea10f583d75a6c7646b243",
"kev/metrics.py": "db0930d470c0ce16f16dcaf726d49a7a103973a5296cefc5259d1e68707d882b",
"kev/mlx_model.py": "f582428796faf6bf962b772a69a6227ac3259ccbd3215c0c8b55ce28dbbd0909",
"kev/model.py": "eac0f56c807b85b5c4077483d922e6bb03f07890de2835efd9372cf20cd01b8e",
"kev/plot.py": "0874bcff2885d8155a1cceade0de8a275a7163d3c3fd6aa0c294e8ccf5ff7e02",
"kev/predictors.py": "b2a66dd9f0f0a8026bc94603383bacfdd622e75d1c935173997175606626a9b3",
"kev/publish.py": "8abc9bcf4a01365697b05cf3c5ad0013462bd92d005f5616954e40ab1100c7aa",
"kev/serve.py": "c210b1f4598e64b49c399f73603ed372f4314c165ceda50e1340c0466ec1c735",
"kev/study_v3.py": "7891150aa623e4479c7c789d4dc4662f186132b37b7bac1e1f072b9e08ee13e3",
"kev/suite.py": "c5e5e27f2fed871b547a021d180b0a7f4a0542a488cce4ee02ad936f433441db",
"kev/train.py": "a2d85632d73760fb3efe51627ff4fde6af3100ed1c34e75d290c1b00c9899aa9",
"kev/transfer_v9.py": "0902409742151250a28af1fd8f42258b70fcc161f3deed3ee35fe3f473f3c763",
"modal_app.py": "639577258f4d581daefa51dad639961280ce92de9da256316ab4124f005a53fb",
"pyproject.toml": "39ec40f14c88598dee7ac98fb859a5a44e22337235a3064ebd5e89036ce81e30",
"uv.lock": "a9922dbb89acdef78299fd2b4a8c3f7f0fa1b2bc08b55595b6926fa785a9c466"
},
"git_commit": "740b511bb562cf29430a85457b9e54389a3f21cd",
"platform": "Linux-4.19.0-gvisor-x86_64-with-glibc2.36",
"torch": "2.8.0+cu128",
"device": "cuda",
"gpu": "NVIDIA H100 80GB HBM3",
"legacy_checkpoint": false,
"measured_checkpoint": {
"requested": "/runs/sev-r2-response-policy-4b-v2/00-trial-0/checkpoint",
"resolved": "/runs/sev-r2-response-policy-4b-v2/00-trial-0/checkpoint",
"head_sha256": "506dcd3587847917a288d95757c497c15a2aef8e2d4bc6523b04ad991c961a2b",
"adapter_sha256": "fa1916b34fe1eeb10d15c36927c225df43115407d7c97b4f879bba3102c3ed21",
"inference_temperature": 1.0
}
},
"mechanism_checks": {
"n": 24,
"packed_max_delta": 1.923413947224617e-06,
"sibling_max_delta": 9.5367431640625e-07,
"tolerance": 0.001,
"passed": true
},
"gates": {
"passed": true,
"checks": {
"complete_coverage": true,
"isolation_and_packing": true,
"transfer_complete": true,
"heldout_pairs_at_least_70pct": true,
"transfer_confident_errors_below_10pct": true
},
"policy": "Research screening only: 0.001 isolation; 5pp task regression; 70% heldout pair correctness; <=10% confident errors; no automatic release."
},
"calibration_fit": {
"temperature": 1.6817928305074288,
"aggregation": "micro",
"objective": "raw-logit NLL",
"split": "calibration",
"rows_sha256": "026b68705b7ac76bc4361bc2fda1cbfe74265b436a807ea68bca77f87d3cf9da",
"suite_sha256": "3b9a80dfd212b6932b66ea520c35ab1a3b19e132a81af1b6b7b306d776a70a02",
"n": 2674
},
"wall_seconds": 1285.6242614819998,
"promotable": false,
"test_evaluated": false,
"training_resources": {
"wall_seconds": 887.5156674385071,
"records_seen": 6577,
"requested_records": 6577,
"truncated_records": 0,
"rejected_records": 0,
"optimizer_steps": 823,
"forward_tokens": 1505379,
"peak_device_bytes": 22225622528,
"device": "cuda",
"dtype": "bf16",
"batch": 4,
"peak_rss_bytes": 31556661248
}
}