| { |
| "version": "v0.3.0-response-policy-research", |
| "repo": "macmacmacmac/Sev-4B", |
| "selected_run": "sev-r2-response-policy-4b-v2/00-trial-0", |
| "parent": "macmacmacmac/Sev-4B@a1824aefba305fda86e3503b895a7d9b3871f79a", |
| "raw_checkpoint": { |
| "head.pt": "506dcd3587847917a288d95757c497c15a2aef8e2d4bc6523b04ad991c961a2b", |
| "adapter_model.safetensors": "fa1916b34fe1eeb10d15c36927c225df43115407d7c97b4f879bba3102c3ed21" |
| }, |
| "release_head_sha256": "12112262e1822fa4ab2981650bd10ceac46929bb29fbbdd843a39ec9de7dbe82", |
| "temperature": 1.6817928305074288, |
| "registered_gates": { |
| "passed": 26, |
| "total": 28, |
| "overall_passed": false, |
| "failed": [ |
| "policy_false_alert_rate", |
| "dns_no_regression" |
| ] |
| }, |
| "selection": "User-authorized research publication accepting the measured improvements and tradeoffs. The failed checks remain failures. Further experiments are paused.", |
| "comparison_sha256": "5b6144be9d2325b224acf29be30940241f3c75c2cf35b1d4d910458ce2aa580b", |
| "dns_comparison_sha256": "3978d60071fd70c519a6bc8240eaa5b043dd136a486850789cc14a3c16b75462", |
| "no_locked_test_read": true, |
| "dataset_repositories": [ |
| "macmacmacmac/Sev-behavioral-research-v1", |
| "macmacmacmac/openai-agent-swarmtraces" |
| ] |
| } |
|
|
