{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:XECUU45EXYWP76SEECXZWUER4W","short_pith_number":"pith:XECUU45E","canonical_record":{"source":{"id":"2207.10050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:29:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"017dafe5ee25483ab0a9de5f29f358fa01b32421f740cce66456ee86ccf09d3d","abstract_canon_sha256":"2debdb0221f97469bf9f4f63150588da3229a51d08994e42e73a886c13c7a8a0"},"schema_version":"1.0"},"canonical_sha256":"b9054a73a4be2cfffa4420af9b5091e5979df98f60a5b5714444a2e4cbb76838","source":{"kind":"arxiv","id":"2207.10050","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10050","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10050v1","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10050","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"XECUU45EXYWP","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"pith_short_16","alias_value":"XECUU45EXYWP76SE","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"pith_short_8","alias_value":"XECUU45E","created_at":"2026-07-05T04:42:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:XECUU45EXYWP76SEECXZWUER4W","target":"record","payload":{"canonical_record":{"source":{"id":"2207.10050","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:29:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"017dafe5ee25483ab0a9de5f29f358fa01b32421f740cce66456ee86ccf09d3d","abstract_canon_sha256":"2debdb0221f97469bf9f4f63150588da3229a51d08994e42e73a886c13c7a8a0"},"schema_version":"1.0"},"canonical_sha256":"b9054a73a4be2cfffa4420af9b5091e5979df98f60a5b5714444a2e4cbb76838","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:42:10.772483Z","signature_b64":"L9S0qHc1R8DOYYSP8hABnodnkiu7aTngKlVWcyFilEZnRERVBX5VQ6QTdueCQmSZJrxHOm6Ug5di59QRaYWCCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9054a73a4be2cfffa4420af9b5091e5979df98f60a5b5714444a2e4cbb76838","last_reissued_at":"2026-07-05T04:42:10.772070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:42:10.772070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.10050","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JFq9XNytP81BxsDu5ht6w1TWhOcNqG2Z9znXPq0Bc9gAnWLEzmgTEMVoK/kKYqmiaw6W+BQwRAONuSklUt4ADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:10:43.105239Z"},"content_sha256":"6e118c3a51db7e27796fe0c29a991d0625b7b6d8e08499b77b796a39afce14c2","schema_version":"1.0","event_id":"sha256:6e118c3a51db7e27796fe0c29a991d0625b7b6d8e08499b77b796a39afce14c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:XECUU45EXYWP76SEECXZWUER4W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haoran Xu, Honglei Yin, Huiling Qin, Xianyuan Zhan","submitted_at":"2022-07-20T17:29:04Z","abstract_excerpt":"We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset from suboptimal behaviors. Prior works that address this problem either require that expert data occupies the majority proportion of the offline dataset, or need to learn a reward function and perform offline reinforcement learning (RL) afterwards. In this paper, we aim to address the problem without additional steps of reward learning and offline RL training"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10050","kind":"arxiv","version":1},"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/2207.10050/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":"2026-07-05T04:42:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xGqPN3d+MNZPiC3De+jVfThGmdf93eKRf5okEr1FN0UkAbRdyMhqYS5ypctGiTgXevfk6RPDIzZMD7/Ue4IcDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:10:43.106200Z"},"content_sha256":"bea56d0c1e89dfcf52a32d913f911012a9add619e9917e251d9db81e02685d4e","schema_version":"1.0","event_id":"sha256:bea56d0c1e89dfcf52a32d913f911012a9add619e9917e251d9db81e02685d4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XECUU45EXYWP76SEECXZWUER4W/bundle.json","state_url":"https://pith.science/pith/XECUU45EXYWP76SEECXZWUER4W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XECUU45EXYWP76SEECXZWUER4W/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":"2026-08-05T23:10:43Z","links":{"resolver":"https://pith.science/pith/XECUU45EXYWP76SEECXZWUER4W","bundle":"https://pith.science/pith/XECUU45EXYWP76SEECXZWUER4W/bundle.json","state":"https://pith.science/pith/XECUU45EXYWP76SEECXZWUER4W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XECUU45EXYWP76SEECXZWUER4W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:XECUU45EXYWP76SEECXZWUER4W","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":"2debdb0221f97469bf9f4f63150588da3229a51d08994e42e73a886c13c7a8a0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:29:04Z","title_canon_sha256":"017dafe5ee25483ab0a9de5f29f358fa01b32421f740cce66456ee86ccf09d3d"},"schema_version":"1.0","source":{"id":"2207.10050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.10050","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"arxiv_version","alias_value":"2207.10050v1","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.10050","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"pith_short_12","alias_value":"XECUU45EXYWP","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"pith_short_16","alias_value":"XECUU45EXYWP76SE","created_at":"2026-07-05T04:42:10Z"},{"alias_kind":"pith_short_8","alias_value":"XECUU45E","created_at":"2026-07-05T04:42:10Z"}],"graph_snapshots":[{"event_id":"sha256:bea56d0c1e89dfcf52a32d913f911012a9add619e9917e251d9db81e02685d4e","target":"graph","created_at":"2026-07-05T04:42:10Z","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/2207.10050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study the problem of offline Imitation Learning (IL) where an agent aims to learn an optimal expert behavior policy without additional online environment interactions. Instead, the agent is provided with a supplementary offline dataset from suboptimal behaviors. Prior works that address this problem either require that expert data occupies the majority proportion of the offline dataset, or need to learn a reward function and perform offline reinforcement learning (RL) afterwards. In this paper, we aim to address the problem without additional steps of reward learning and offline RL training","authors_text":"Haoran Xu, Honglei Yin, Huiling Qin, Xianyuan Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:29:04Z","title":"Discriminator-Weighted Offline Imitation Learning from Suboptimal Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.10050","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":"sha256:6e118c3a51db7e27796fe0c29a991d0625b7b6d8e08499b77b796a39afce14c2","target":"record","created_at":"2026-07-05T04:42:10Z","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":"2debdb0221f97469bf9f4f63150588da3229a51d08994e42e73a886c13c7a8a0","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-20T17:29:04Z","title_canon_sha256":"017dafe5ee25483ab0a9de5f29f358fa01b32421f740cce66456ee86ccf09d3d"},"schema_version":"1.0","source":{"id":"2207.10050","kind":"arxiv","version":1}},"canonical_sha256":"b9054a73a4be2cfffa4420af9b5091e5979df98f60a5b5714444a2e4cbb76838","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9054a73a4be2cfffa4420af9b5091e5979df98f60a5b5714444a2e4cbb76838","first_computed_at":"2026-07-05T04:42:10.772070Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:10.772070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L9S0qHc1R8DOYYSP8hABnodnkiu7aTngKlVWcyFilEZnRERVBX5VQ6QTdueCQmSZJrxHOm6Ug5di59QRaYWCCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:10.772483Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.10050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e118c3a51db7e27796fe0c29a991d0625b7b6d8e08499b77b796a39afce14c2","sha256:bea56d0c1e89dfcf52a32d913f911012a9add619e9917e251d9db81e02685d4e"],"state_sha256":"77f02da0a9d9c292d248aa85c44b030c22890933b0f4d490ce7db561c2d6c35f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nkpngeajlXgtXnZKTD8CwnG5AIXq+9il9nAeEoXOr75tFNlgNK+0fs70xf3vfLdmncPP0NXMs1ClJ3mlZfUVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:10:43.112384Z","bundle_sha256":"17149473d208f1f188433ae16081f4bd64d4e6cdcb31a2e82e4c232b40cfe768"}}