{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RCIOLNJZZVCVCH2LW4P52IMU6I","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":"e7a1ec0ef7e688620d6e583af0bcfa03a00e4b9b9a75a787705f5223d6a55ef2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T00:05:03Z","title_canon_sha256":"9239b9cc68c529547f294970c997ecc13869d28e5a0dd0e3a21bc2329535a4df"},"schema_version":"1.0","source":{"id":"2205.09251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.09251","created_at":"2026-07-05T04:24:42Z"},{"alias_kind":"arxiv_version","alias_value":"2205.09251v1","created_at":"2026-07-05T04:24:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.09251","created_at":"2026-07-05T04:24:42Z"},{"alias_kind":"pith_short_12","alias_value":"RCIOLNJZZVCV","created_at":"2026-07-05T04:24:42Z"},{"alias_kind":"pith_short_16","alias_value":"RCIOLNJZZVCVCH2L","created_at":"2026-07-05T04:24:42Z"},{"alias_kind":"pith_short_8","alias_value":"RCIOLNJZ","created_at":"2026-07-05T04:24:42Z"}],"graph_snapshots":[{"event_id":"sha256:57f1423ff01117b57b6fcf681e0d20e655380c90846d4b54d28eb4c389f0eff2","target":"graph","created_at":"2026-07-05T04:24:42Z","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/2205.09251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an algorithm for Inverse Reinforcement Learning (IRL) from expert state observations only. Our approach decouples reward modelling from policy learning, unlike state-of-the-art adversarial methods which require updating the reward model during policy search and are known to be unstable and difficult to optimize. Our method, IL-flOw, recovers the expert policy by modelling state-state transitions, by generating rewards using deep density estimators trained on the demonstration trajectories, avoiding the instability issues of adversarial methods. We demonstrate that using the state tr","authors_text":"David Meger, Gregory Dudek, Juan Camilo Gamboa Higuera, Scott Fujimoto, Wei-Di Chang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T00:05:03Z","title":"IL-flOw: Imitation Learning from Observation using Normalizing Flows"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.09251","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":"sha256:9862007b8c88ae9d575269e0d79a7493180a76bc867d56a5210c1ce20d7761f6","target":"record","created_at":"2026-07-05T04:24:42Z","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":"e7a1ec0ef7e688620d6e583af0bcfa03a00e4b9b9a75a787705f5223d6a55ef2","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-19T00:05:03Z","title_canon_sha256":"9239b9cc68c529547f294970c997ecc13869d28e5a0dd0e3a21bc2329535a4df"},"schema_version":"1.0","source":{"id":"2205.09251","kind":"arxiv","version":1}},"canonical_sha256":"8890e5b539cd45511f4bb71fdd2194f22e129d02cb4f080037674d017e7faea3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8890e5b539cd45511f4bb71fdd2194f22e129d02cb4f080037674d017e7faea3","first_computed_at":"2026-07-05T04:24:42.658503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:42.658503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RLbfgAdy2cdrBcgcP8xUleTvEY9g2l4BceLVcmcDbIw+a+O5z3qfMycUbiyBZc/UAZwlg4BV6xY22OG42qmcDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:42.658919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.09251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9862007b8c88ae9d575269e0d79a7493180a76bc867d56a5210c1ce20d7761f6","sha256:57f1423ff01117b57b6fcf681e0d20e655380c90846d4b54d28eb4c389f0eff2"],"state_sha256":"0ff852e74d91e2b6e87a98dbfd1e9ee4596071b2c4ecc99220e45f2ae717687a"}