{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D4ZJMLAYMSMGMEVQCMMQKEYBCG","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":"73185dfbb62d9cf3fd3e779c4d6d4d6a8c7ced709d22499c360bcea4f427c403","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T11:53:23Z","title_canon_sha256":"4acd7664d17f1a6953d69f3e5df71a2a768daf45eb014cc91e15c1709a4134bf"},"schema_version":"1.0","source":{"id":"2405.16194","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16194","created_at":"2026-07-05T09:40:17Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16194v4","created_at":"2026-07-05T09:40:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16194","created_at":"2026-07-05T09:40:17Z"},{"alias_kind":"pith_short_12","alias_value":"D4ZJMLAYMSMG","created_at":"2026-07-05T09:40:17Z"},{"alias_kind":"pith_short_16","alias_value":"D4ZJMLAYMSMGMEVQ","created_at":"2026-07-05T09:40:17Z"},{"alias_kind":"pith_short_8","alias_value":"D4ZJMLAY","created_at":"2026-07-05T09:40:17Z"}],"graph_snapshots":[{"event_id":"sha256:728f818489e109f3666d27432182f96c63b050fbfe99e45982ea51ddb4254443","target":"graph","created_at":"2026-07-05T09:40:17Z","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/2405.16194/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imitation learning aims to learn a policy from observing expert demonstrations without access to reward signals from environments. Generative adversarial imitation learning (GAIL) formulates imitation learning as adversarial learning, employing a generator policy learning to imitate expert behaviors and discriminator learning to distinguish the expert demonstrations from agent trajectories. Despite its encouraging results, GAIL training is often brittle and unstable. Inspired by the recent dominance of diffusion models in generative modeling, we propose Diffusion-Reward Adversarial Imitation L","authors_text":"Chun-Mao Lai, Hsiang-Chun Wang, Min-Hung Chen, Ping-Chun Hsieh, Shao-Hua Sun, Yu-Chiang Frank Wang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T11:53:23Z","title":"Diffusion-Reward Adversarial Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16194","kind":"arxiv","version":4},"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":"sha256:955a48827f5b9bdd643be8dd73ae80cf0d5d6e9085094d097aad511c9d29679f","target":"record","created_at":"2026-07-05T09:40:17Z","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":"73185dfbb62d9cf3fd3e779c4d6d4d6a8c7ced709d22499c360bcea4f427c403","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-25T11:53:23Z","title_canon_sha256":"4acd7664d17f1a6953d69f3e5df71a2a768daf45eb014cc91e15c1709a4134bf"},"schema_version":"1.0","source":{"id":"2405.16194","kind":"arxiv","version":4}},"canonical_sha256":"1f32962c1864986612b0131905130111a3a5cb8f866039a5545dcff971c2e959","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1f32962c1864986612b0131905130111a3a5cb8f866039a5545dcff971c2e959","first_computed_at":"2026-07-05T09:40:17.551847Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:40:17.551847Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dxVoUtexvCKZ7QnTNAYjqDii6TqohL6aMNaRKmAtV2E+pDWzYO8n9DNrkLkba/jEM7sxNB5HZPeq3cUA7mHeCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:40:17.552338Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16194","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:955a48827f5b9bdd643be8dd73ae80cf0d5d6e9085094d097aad511c9d29679f","sha256:728f818489e109f3666d27432182f96c63b050fbfe99e45982ea51ddb4254443"],"state_sha256":"2f0814da1c7bc3160130b86d8f63fc6ac4dff0068343801332a73528a3179f9a"}