{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZJRJFP6OZHDESN74U3F4YSJKKP","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":"6f8d237fd58c906e895334150524fc851ecec9866933e5c566776389c53cae6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T17:24:37Z","title_canon_sha256":"7901af6e15df0839b964b0711dd47d9887406437061ab3e1c428f2f0f810129b"},"schema_version":"1.0","source":{"id":"2306.07919","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.07919","created_at":"2026-07-05T06:20:10Z"},{"alias_kind":"arxiv_version","alias_value":"2306.07919v1","created_at":"2026-07-05T06:20:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.07919","created_at":"2026-07-05T06:20:10Z"},{"alias_kind":"pith_short_12","alias_value":"ZJRJFP6OZHDE","created_at":"2026-07-05T06:20:10Z"},{"alias_kind":"pith_short_16","alias_value":"ZJRJFP6OZHDESN74","created_at":"2026-07-05T06:20:10Z"},{"alias_kind":"pith_short_8","alias_value":"ZJRJFP6O","created_at":"2026-07-05T06:20:10Z"}],"graph_snapshots":[{"event_id":"sha256:8260c9de47d25f7eddd1726192b237080f36c912a0512cf41fd70f138d05f429","target":"graph","created_at":"2026-07-05T06:20:10Z","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/2306.07919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning has achieved great success in many sequential decision-making tasks, in which a neural agent is learned by imitating collected human demonstrations. However, existing algorithms typically require a large number of high-quality demonstrations that are difficult and expensive to collect. Usually, a trade-off needs to be made between demonstration quality and quantity in practice. Targeting this problem, in this work we consider the imitation of sub-optimal demonstrations, with both a small clean demonstration set and a large noisy set. Some pioneering works have been proposed,","authors_text":"Haifeng Chen, Lu Wang, Suhang Wang, Tianxiang Zhao, Wei Cheng, Wenchao Yu, Xiang Zhang, Yanchi Liu, Yuncong Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T17:24:37Z","title":"Skill Disentanglement for Imitation Learning from Suboptimal Demonstrations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.07919","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":"sha256:03418c2786a4c3423a10fd3ff4fcef904d84a2d7303e8990fab2ca6b845e4db8","target":"record","created_at":"2026-07-05T06:20:10Z","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":"6f8d237fd58c906e895334150524fc851ecec9866933e5c566776389c53cae6c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-13T17:24:37Z","title_canon_sha256":"7901af6e15df0839b964b0711dd47d9887406437061ab3e1c428f2f0f810129b"},"schema_version":"1.0","source":{"id":"2306.07919","kind":"arxiv","version":1}},"canonical_sha256":"ca6292bfcec9c64937fca6cbcc492a53c77aeb55c99fdfe0fd9749fd8dcd13ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca6292bfcec9c64937fca6cbcc492a53c77aeb55c99fdfe0fd9749fd8dcd13ee","first_computed_at":"2026-07-05T06:20:10.771481Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:20:10.771481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UpOPMA7+OOh8MMAj8l8jf8Ed1B6y8nIr9QMKxw74zNKIfJCyLLV9wVCLQ0BfgjAhCOz+5EteywAHJFrOORANAA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:20:10.771978Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.07919","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03418c2786a4c3423a10fd3ff4fcef904d84a2d7303e8990fab2ca6b845e4db8","sha256:8260c9de47d25f7eddd1726192b237080f36c912a0512cf41fd70f138d05f429"],"state_sha256":"3442a522b9420dd566a95c31694b6373c82b599a7dc63064634c93cc494917c8"}