{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5","short_pith_number":"pith:OZ2UPLYE","canonical_record":{"source":{"id":"2510.01479","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T21:43:04Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"76230e71545d3788229a71ca36cd01ec1ebfb0696d26dd15814a97e9616be5fb","abstract_canon_sha256":"8adc8eff32c77aec85bc319426f2ba223e2d4b59d226351187f73ed820e8a106"},"schema_version":"1.0"},"canonical_sha256":"767547af043c3a8e231c2c23b127f6cf548f1fa8c2defff00a0e8f9ae07db66c","source":{"kind":"arxiv","id":"2510.01479","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01479","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01479v2","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01479","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"OZ2UPLYEHQ5I","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"OZ2UPLYEHQ5I4IY4","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"OZ2UPLYE","created_at":"2026-05-20T00:04:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5","target":"record","payload":{"canonical_record":{"source":{"id":"2510.01479","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T21:43:04Z","cross_cats_sorted":["cs.SY","eess.SY"],"title_canon_sha256":"76230e71545d3788229a71ca36cd01ec1ebfb0696d26dd15814a97e9616be5fb","abstract_canon_sha256":"8adc8eff32c77aec85bc319426f2ba223e2d4b59d226351187f73ed820e8a106"},"schema_version":"1.0"},"canonical_sha256":"767547af043c3a8e231c2c23b127f6cf548f1fa8c2defff00a0e8f9ae07db66c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:14.131727Z","signature_b64":"1HTjdtS9Pgks5PpVLstyIUvI+suUJP9/zQB6cV3jQCeoc8PsfLFZpVd3kulVZLb1p28zIq1pzgB5zhKAIajhAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"767547af043c3a8e231c2c23b127f6cf548f1fa8c2defff00a0e8f9ae07db66c","last_reissued_at":"2026-05-20T00:04:14.130935Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:14.130935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.01479","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G8L+NzahxkcNkcYK8A2/30YCNHW0o0v9Decu8FCVUy6RXmSQvapOhMXpRzJgImLG+KbFFE9S89Q+Txa9kwMMAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:01:00.179087Z"},"content_sha256":"c187d6e4aad5261a08e802cb9ec64d2a297b0ceab483931d5cdf5df881a74095","schema_version":"1.0","event_id":"sha256:c187d6e4aad5261a08e802cb9ec64d2a297b0ceab483931d5cdf5df881a74095"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Ali Baheri, Shriram Karpoora Sundara Pandian","submitted_at":"2025-10-01T21:43:04Z","abstract_excerpt":"Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contaminated by adversarial poisoning, system errors, or low-quality samples, leading to degraded policy performance in standard behavioral cloning (BC) and offline RL methods. This paper introduces Density-Ratio Weighted Behavioral Cloning (Weighted BC), a robust imitation learning approach that uses a small, verified clean reference set to estimate trajectory-level density ratios via "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01479","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2510.01479/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:04:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XyntZtYAhKMyHXcS3Mes1Lurq5Rx5MEYJcioh0hb/YzL+gAQlb1CbdxaXxPAKQefGfbbyWDznE/T9lWo1MhsBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T20:01:00.179491Z"},"content_sha256":"bfa0f1a6f6f2dfbe32a0552d82b3ec85e3615825263ed42bfc040c440077ef08","schema_version":"1.0","event_id":"sha256:bfa0f1a6f6f2dfbe32a0552d82b3ec85e3615825263ed42bfc040c440077ef08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5/bundle.json","state_url":"https://pith.science/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T20:01:00Z","links":{"resolver":"https://pith.science/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5","bundle":"https://pith.science/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5/bundle.json","state":"https://pith.science/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:OZ2UPLYEHQ5I4IY4FQR3CJ7WZ5","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8adc8eff32c77aec85bc319426f2ba223e2d4b59d226351187f73ed820e8a106","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T21:43:04Z","title_canon_sha256":"76230e71545d3788229a71ca36cd01ec1ebfb0696d26dd15814a97e9616be5fb"},"schema_version":"1.0","source":{"id":"2510.01479","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.01479","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2510.01479v2","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01479","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"OZ2UPLYEHQ5I","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"OZ2UPLYEHQ5I4IY4","created_at":"2026-05-20T00:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"OZ2UPLYE","created_at":"2026-05-20T00:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:bfa0f1a6f6f2dfbe32a0552d82b3ec85e3615825263ed42bfc040c440077ef08","target":"graph","created_at":"2026-05-20T00:04:14Z","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/2510.01479/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) enables policy optimization from fixed datasets, making it suitable for safety-critical applications where online exploration is infeasible. However, these datasets are often contaminated by adversarial poisoning, system errors, or low-quality samples, leading to degraded policy performance in standard behavioral cloning (BC) and offline RL methods. This paper introduces Density-Ratio Weighted Behavioral Cloning (Weighted BC), a robust imitation learning approach that uses a small, verified clean reference set to estimate trajectory-level density ratios via ","authors_text":"Ali Baheri, Shriram Karpoora Sundara Pandian","cross_cats":["cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T21:43:04Z","title":"Density-Ratio Weighted Behavioral Cloning: Learning Control Policies from Corrupted Datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01479","kind":"arxiv","version":2},"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:c187d6e4aad5261a08e802cb9ec64d2a297b0ceab483931d5cdf5df881a74095","target":"record","created_at":"2026-05-20T00:04:14Z","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":"8adc8eff32c77aec85bc319426f2ba223e2d4b59d226351187f73ed820e8a106","cross_cats_sorted":["cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-10-01T21:43:04Z","title_canon_sha256":"76230e71545d3788229a71ca36cd01ec1ebfb0696d26dd15814a97e9616be5fb"},"schema_version":"1.0","source":{"id":"2510.01479","kind":"arxiv","version":2}},"canonical_sha256":"767547af043c3a8e231c2c23b127f6cf548f1fa8c2defff00a0e8f9ae07db66c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"767547af043c3a8e231c2c23b127f6cf548f1fa8c2defff00a0e8f9ae07db66c","first_computed_at":"2026-05-20T00:04:14.130935Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:04:14.130935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1HTjdtS9Pgks5PpVLstyIUvI+suUJP9/zQB6cV3jQCeoc8PsfLFZpVd3kulVZLb1p28zIq1pzgB5zhKAIajhAQ==","signature_status":"signed_v1","signed_at":"2026-05-20T00:04:14.131727Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.01479","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c187d6e4aad5261a08e802cb9ec64d2a297b0ceab483931d5cdf5df881a74095","sha256:bfa0f1a6f6f2dfbe32a0552d82b3ec85e3615825263ed42bfc040c440077ef08"],"state_sha256":"2ef10a3ea05ced8985a7f574a69d8af17528260dd08f33fc77f8332f1324e036"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IeX/vI/A1NGoJFQt3yws83y20LyGf43yB/plIlbcV7+wBP5NVpus3/umxYqdjiZs86mwSLVv60yeZiM08qj6AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T20:01:00.181449Z","bundle_sha256":"24ba67cdde8ffce4528b463dc11a8efed0aea98c786ea954bff1b3f2768dfa42"}}