{ "protocol_sha256": "23ca33b71c7723cb6c67586e7805b74a0988ca5f8b7139b637420bbb5ec89d61", "comparison_sha256": "5b6144be9d2325b224acf29be30940241f3c75c2cf35b1d4d910458ce2aa580b", "dns_comparison_sha256": "3978d60071fd70c519a6bc8240eaa5b043dd136a486850789cc14a3c16b75462", "checks": { "policy_false_alert_rate": false, "policy_useful_change": true, "dns_no_regression": false, "development/excytin_file": true, "development/excytin_parent_join": true, "development/excytin_process": true, "development/excytin_signin": true, "development/sev_guide_detector": true, "development/sev_guide_triage": true, "development/sev_swarmtraces_static": true, "development/sev_sysmon_native_file": true, "development/sev_sysmon_native_join": true, "development/sev_sysmon_native_other_effect": true, "development/sev_sysmon_native_process": true, "development/sev_sysmon_native_registry": true, "transfer/composition_holdout": true, "transfer/emotion": true, "transfer/legacy_holdout": true, "transfer/mmlu": true, "transfer/otrf_sysmon_file": true, "transfer/otrf_sysmon_join": true, "transfer/otrf_sysmon_process": true, "transfer/otrf_sysmon_registry": true, "transfer/paws": true, "transfer/qnli": true, "transfer/sciq": true, "transfer/sev_swarmtraces_manual_v1": true, "transfer/tweet_offensive": true }, "passed": false, "failed": [ "policy_false_alert_rate", "dns_no_regression" ], "retained_development": [ { "source": "excytin_file", "questions": 80, "parent_correct": 80, "candidate_correct": 80, "parent_calibrated_nll": 0.0030639977354718724, "candidate_calibrated_nll": 0.0025800477441721577, "parent_calibrated_brier": 5.723205099455454e-05, "candidate_calibrated_brier": 4.4624375778219304e-05 }, { "source": "excytin_parent_join", "questions": 78, "parent_correct": 78, "candidate_correct": 78, "parent_calibrated_nll": 0.01903091706838521, "candidate_calibrated_nll": 0.014932533018017379, "parent_calibrated_brier": 0.0013900388516520708, "candidate_calibrated_brier": 0.0008621856358382366 }, { "source": "excytin_process", "questions": 120, "parent_correct": 120, "candidate_correct": 120, "parent_calibrated_nll": 0.007587462315793864, "candidate_calibrated_nll": 0.007136704365819422, "parent_calibrated_brier": 0.00023474191911792246, "candidate_calibrated_brier": 0.00021856930435733632 }, { "source": "excytin_signin", "questions": 120, "parent_correct": 120, "candidate_correct": 120, "parent_calibrated_nll": 0.009411479962491658, "candidate_calibrated_nll": 0.00847100086283192, "parent_calibrated_brier": 0.0010010974637190823, "candidate_calibrated_brier": 0.0008193865392318428 }, { "source": "sev_guide_detector", "questions": 1064, "parent_correct": 638, "candidate_correct": 639, "parent_calibrated_nll": 0.785071927880167, "candidate_calibrated_nll": 0.7966730081647482, "parent_calibrated_brier": 0.46075730837789786, "candidate_calibrated_brier": 0.46843654552918773 }, { "source": "sev_guide_triage", "questions": 231, "parent_correct": 130, "candidate_correct": 131, "parent_calibrated_nll": 0.7793526965750157, "candidate_calibrated_nll": 0.7761249864817235, "parent_calibrated_brier": 0.4718856823661165, "candidate_calibrated_brier": 0.46407372894941223 }, { "source": "sev_swarmtraces_static", "questions": 354, "parent_correct": 345, "candidate_correct": 347, "parent_calibrated_nll": 0.08603305952328294, "candidate_calibrated_nll": 0.06588860080731399, "parent_calibrated_brier": 0.03970483443698841, "candidate_calibrated_brier": 0.028907916842541088 }, { "source": "sev_sysmon_native_file", "questions": 62, "parent_correct": 62, "candidate_correct": 62, "parent_calibrated_nll": 0.04080521144437412, "candidate_calibrated_nll": 0.03509983435601263, "parent_calibrated_brier": 0.008675036111100168, "candidate_calibrated_brier": 0.007419485561600889 }, { "source": "sev_sysmon_native_join", "questions": 120, "parent_correct": 120, "candidate_correct": 120, "parent_calibrated_nll": 0.013824573239669817, "candidate_calibrated_nll": 0.009879536093519296, "parent_calibrated_brier": 0.00044603592410257366, "candidate_calibrated_brier": 0.00022722202758135087 }, { "source": "sev_sysmon_native_other_effect", "questions": 88, "parent_correct": 88, "candidate_correct": 88, "parent_calibrated_nll": 0.03669008514897713, "candidate_calibrated_nll": 0.02789592785139411, "parent_calibrated_brier": 0.006053607090618847, "candidate_calibrated_brier": 0.004783993285232044 }, { "source": "sev_sysmon_native_process", "questions": 74, "parent_correct": 74, "candidate_correct": 74, "parent_calibrated_nll": 0.02430026482825407, "candidate_calibrated_nll": 0.023528453108139967, "parent_calibrated_brier": 0.004038757822471681, "candidate_calibrated_brier": 0.004027925361032504 }, { "source": "sev_sysmon_native_registry", "questions": 66, "parent_correct": 65, "candidate_correct": 65, "parent_calibrated_nll": 0.03908316195438624, "candidate_calibrated_nll": 0.03582391955947498, "parent_calibrated_brier": 0.01748193378444616, "candidate_calibrated_brier": 0.016990289728223678 } ], "training_metrics": { "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 }, "candidate_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 }, "candidate_temperature_fit": { "temperature": 1.6817928305074288, "aggregation": "micro", "objective": "raw-logit NLL", "split": "calibration", "rows_sha256": "026b68705b7ac76bc4361bc2fda1cbfe74265b436a807ea68bca77f87d3cf9da", "suite_sha256": "3b9a80dfd212b6932b66ea520c35ab1a3b19e132a81af1b6b7b306d776a70a02", "n": 2674 }, "fit_recomputed": true, "run_seconds": 1285.6242614819998, "decision": "Keep checkpoint as a conditional-policy research result; do not replace published model. Fixed false-alert gate and DNS regression gate fail. No threshold retuning on development." }