{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T4MMAUXIQFSLZRUXZKKIG7K6YR","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c1a0c0f1b7ed8123312f7826bb338297534e748786407f955eef44f9bbe351d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T20:41:45Z","title_canon_sha256":"d69c037e15e260b13993dd23d0a9d4e29de85d6aede1a04cbbcece6b1cc5fbad"},"schema_version":"1.0","source":{"id":"2607.08925","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08925","created_at":"2026-07-13T00:17:27Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08925v1","created_at":"2026-07-13T00:17:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08925","created_at":"2026-07-13T00:17:27Z"},{"alias_kind":"pith_short_12","alias_value":"T4MMAUXIQFSL","created_at":"2026-07-13T00:17:27Z"},{"alias_kind":"pith_short_16","alias_value":"T4MMAUXIQFSLZRUX","created_at":"2026-07-13T00:17:27Z"},{"alias_kind":"pith_short_8","alias_value":"T4MMAUXI","created_at":"2026-07-13T00:17:27Z"}],"graph_snapshots":[{"event_id":"sha256:d6fc6afba2830e201afc9cd202068b17a31b87e0ebc239da27321ad052b227e6","target":"graph","created_at":"2026-07-13T00:17:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.08925/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training reinforcement-learning agents directly on physical robots makes every fall costly, since a fall can damage the platform and cannot be undone like a simulator reset; the goal is therefore to minimize falls during training rather than trade them off against return, as constrained Markov decision process (MDP) formulations do. A standard mitigation hands control to a separate recovery policy whenever the agent leaves a designer-specified safe region (a subset of state space it should stay within), but the resulting mixed-policy rollouts silently bias every on-policy update, and the impor","authors_text":"Elham Daneshmand, Glen Berseth, Hsiu-Chin Lin, Majid Khadiv","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T20:41:45Z","title":"SafeExplorer: An Unbiased Policy Gradient for Reinforcement Learning with Recovery Interventions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08925","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a2085fbe2000825634f6ad83e7e6d23e704c2d45bae3a4e0c9c3638d3649dda8","target":"record","created_at":"2026-07-13T00:17:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c1a0c0f1b7ed8123312f7826bb338297534e748786407f955eef44f9bbe351d7","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-09T20:41:45Z","title_canon_sha256":"d69c037e15e260b13993dd23d0a9d4e29de85d6aede1a04cbbcece6b1cc5fbad"},"schema_version":"1.0","source":{"id":"2607.08925","kind":"arxiv","version":1}},"canonical_sha256":"9f18c052e88164bcc697ca94837d5ec457accd2b7a854a19a199d254de75bdb4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f18c052e88164bcc697ca94837d5ec457accd2b7a854a19a199d254de75bdb4","first_computed_at":"2026-07-13T00:17:27.358969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T00:17:27.358969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XKq9i8r2OCN7Rv7LjiuLcsBcg2aBeVizcBCxlqq2J8vzFC5s8IyOVKVtWZSCpYZYBLSWGW/cRySGXphSrtkBCA==","signature_status":"signed_v1","signed_at":"2026-07-13T00:17:27.359965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08925","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a2085fbe2000825634f6ad83e7e6d23e704c2d45bae3a4e0c9c3638d3649dda8","sha256:d6fc6afba2830e201afc9cd202068b17a31b87e0ebc239da27321ad052b227e6","sha256:d00488c7c7ffe72dec4958f1a2b8d524151346f36bed4c8e76e9001fe04ad4ba"],"state_sha256":"4efc6e2099645ab42952001b0563460a525c7beb44e02d76f4f7fa5d3aefa51f"}