{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:JWT5XBCBBJZJASDR2PFT46RVGK","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":"c7adaef99243021bc6018a611625a533d6974a6d310235d126de1c479f739090","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-27T02:27:46Z","title_canon_sha256":"daa5b87b9ec8eed67add82579d096a54ca171d6ca1b4ea2fa6917758adfb0477"},"schema_version":"1.0","source":{"id":"2002.11879","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.11879","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"arxiv_version","alias_value":"2002.11879v1","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.11879","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_12","alias_value":"JWT5XBCBBJZJ","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_16","alias_value":"JWT5XBCBBJZJASDR","created_at":"2026-07-05T00:44:09Z"},{"alias_kind":"pith_short_8","alias_value":"JWT5XBCB","created_at":"2026-07-05T00:44:09Z"}],"graph_snapshots":[{"event_id":"sha256:5af30102968382ae3ace6c926abd54b00e75118718612da47dcfeeb43bc866a8","target":"graph","created_at":"2026-07-05T00:44:09Z","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/2002.11879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation Learning (IL) is a popular paradigm for training agents to achieve complicated goals by leveraging expert behavior, rather than dealing with the hardships of designing a correct reward function. With the environment modeled as a Markov Decision Process (MDP), most of the existing IL algorithms are contingent on the availability of expert demonstrations in the same MDP as the one in which a new imitator policy is to be learned. This is uncharacteristic of many real-life scenarios where discrepancies between the expert and the imitator MDPs are common, especially in the transition dyna","authors_text":"Jian Peng, Tanmay Gangwani","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-27T02:27:46Z","title":"State-only Imitation with Transition Dynamics Mismatch"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.11879","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":"sha256:8bc98ab79a2d731c7e0cba99638727db07eb5b58944d1e236c73b1bb21afa0d1","target":"record","created_at":"2026-07-05T00:44:09Z","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":"c7adaef99243021bc6018a611625a533d6974a6d310235d126de1c479f739090","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2020-02-27T02:27:46Z","title_canon_sha256":"daa5b87b9ec8eed67add82579d096a54ca171d6ca1b4ea2fa6917758adfb0477"},"schema_version":"1.0","source":{"id":"2002.11879","kind":"arxiv","version":1}},"canonical_sha256":"4da7db84410a72904871d3cb3e7a3532b46691a8cacb532202161f8a7f97a5a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4da7db84410a72904871d3cb3e7a3532b46691a8cacb532202161f8a7f97a5a0","first_computed_at":"2026-07-05T00:44:09.860034Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:09.860034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RZRT8r2EUXPrps5iqVt78wpL9gY7zPpKHu44yCmVv5laLGS2oHEtY7x0pD+gsM7m6szCkgNPJHcZjPKOdreBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:09.860475Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.11879","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bc98ab79a2d731c7e0cba99638727db07eb5b58944d1e236c73b1bb21afa0d1","sha256:5af30102968382ae3ace6c926abd54b00e75118718612da47dcfeeb43bc866a8"],"state_sha256":"f0ad1fba5be9d6c7d6f78e6f91932ae63ac34e974e3d063efe3b669099b7a116"}