{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:52FYJCSGP5CQWSESUIYUNUBZEY","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":"2de58da67ddc89e3d46c47dd63c756b31e7c56a4400f072bedaab9412f3d01c0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-01T07:28:18Z","title_canon_sha256":"77f2dee98b77d6f6a0d29160f4f0fb916606470cfb6a371b3b02fc78d7aae78c"},"schema_version":"1.0","source":{"id":"2207.00244","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00244","created_at":"2026-07-05T05:31:51Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00244v3","created_at":"2026-07-05T05:31:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00244","created_at":"2026-07-05T05:31:51Z"},{"alias_kind":"pith_short_12","alias_value":"52FYJCSGP5CQ","created_at":"2026-07-05T05:31:51Z"},{"alias_kind":"pith_short_16","alias_value":"52FYJCSGP5CQWSES","created_at":"2026-07-05T05:31:51Z"},{"alias_kind":"pith_short_8","alias_value":"52FYJCSG","created_at":"2026-07-05T05:31:51Z"}],"graph_snapshots":[{"event_id":"sha256:9d2960e1bed6ede6a8a38b94e775b8492f7072046bea31d66db8b638673f78f6","target":"graph","created_at":"2026-07-05T05:31:51Z","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/2207.00244/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline imitation learning (IL) is a powerful method to solve decision-making problems from expert demonstrations without reward labels. Existing offline IL methods suffer from severe performance degeneration under limited expert data. Including a learned dynamics model can potentially improve the state-action space coverage of expert data, however, it also faces challenging issues like model approximation/generalization errors and suboptimality of rollout data. In this paper, we propose the Discriminator-guided Model-based offline Imitation Learning (DMIL) framework, which introduces a discri","authors_text":"Guyue Zhou, Haoran Xu, Haoyi Niu, Heming Zhang, Ming Li, Peng Cheng, Wenjia Zhang, Xianyuan Zhan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-01T07:28:18Z","title":"Discriminator-Guided Model-Based Offline Imitation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00244","kind":"arxiv","version":3},"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":"sha256:1b8f16ed2cbed8df50c99394c9c6f9c83aca7bd6ce2256093c802d3a614bde4f","target":"record","created_at":"2026-07-05T05:31:51Z","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":"2de58da67ddc89e3d46c47dd63c756b31e7c56a4400f072bedaab9412f3d01c0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-07-01T07:28:18Z","title_canon_sha256":"77f2dee98b77d6f6a0d29160f4f0fb916606470cfb6a371b3b02fc78d7aae78c"},"schema_version":"1.0","source":{"id":"2207.00244","kind":"arxiv","version":3}},"canonical_sha256":"ee8b848a467f450b4892a23146d039261b29c6bb79e00e8ecdc394161bab7dd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee8b848a467f450b4892a23146d039261b29c6bb79e00e8ecdc394161bab7dd4","first_computed_at":"2026-07-05T05:31:51.179875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:31:51.179875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TCjEq1pqVOjFQhySk3WGwG7rD+fSaOnm6TUldNxUJhdpF0sNRNYlCT4Pq1tU88bOG7XQ40ghEcfvOQaKyXsXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:31:51.180363Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00244","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b8f16ed2cbed8df50c99394c9c6f9c83aca7bd6ce2256093c802d3a614bde4f","sha256:9d2960e1bed6ede6a8a38b94e775b8492f7072046bea31d66db8b638673f78f6"],"state_sha256":"0808898906a6c755acf0ee16335d56b30ce7f5ba55c1761e8d07faea6a4210db"}