{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:MNDM4FE6YI4TQYDAFLM4TDHVJ6","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":"229c6bd96c8fa026377a7679401ac60a8e029891333a0dc0cc47aaa3e6517233","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T06:59:16Z","title_canon_sha256":"c44a66331abea76a1d5b0f0ee081c605accbeb38dfa6793509e9e95c1343c43c"},"schema_version":"1.0","source":{"id":"2405.20351","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.20351","created_at":"2026-07-05T09:59:47Z"},{"alias_kind":"arxiv_version","alias_value":"2405.20351v3","created_at":"2026-07-05T09:59:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20351","created_at":"2026-07-05T09:59:47Z"},{"alias_kind":"pith_short_12","alias_value":"MNDM4FE6YI4T","created_at":"2026-07-05T09:59:47Z"},{"alias_kind":"pith_short_16","alias_value":"MNDM4FE6YI4TQYDA","created_at":"2026-07-05T09:59:47Z"},{"alias_kind":"pith_short_8","alias_value":"MNDM4FE6","created_at":"2026-07-05T09:59:47Z"}],"graph_snapshots":[{"event_id":"sha256:cab892cbbca9643caa09c78907b1aadab7358be86ee8b9d25dfad72923ac3c41","target":"graph","created_at":"2026-07-05T09:59:47Z","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/2405.20351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a novel one-step supervised imitation learning (IL) framework called Adversarial Density Regression (ADR). This IL framework aims to correct the policy learned on unknown-quality to match the expert distribution by utilizing demonstrations, without relying on the Bellman operator. Specifically, ADR addresses several limitations in previous IL algorithms: First, most IL algorithms are based on the Bellman operator, which inevitably suffer from cumulative offsets from sub-optimal rewards during multi-step update processes. Additionally, off-policy training frameworks suffer from Out-o","authors_text":"Donglin Wang, Jingzehua Xu, Shuai Zhang, Yiyuan Yang, Yubo Huang, Zifeng Zhuang, Ziqi Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T06:59:16Z","title":"Imitating from auxiliary imperfect demonstrations via Adversarial Density Weighted Regression"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20351","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":"sha256:63a70e7f309be4d947d96c51c98a06fb1b47efe1f791f5c240a4bc162603881d","target":"record","created_at":"2026-07-05T09:59:47Z","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":"229c6bd96c8fa026377a7679401ac60a8e029891333a0dc0cc47aaa3e6517233","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-28T06:59:16Z","title_canon_sha256":"c44a66331abea76a1d5b0f0ee081c605accbeb38dfa6793509e9e95c1343c43c"},"schema_version":"1.0","source":{"id":"2405.20351","kind":"arxiv","version":3}},"canonical_sha256":"6346ce149ec2393860602ad9c98cf54fb2753d6390f3209e65906d671b800991","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6346ce149ec2393860602ad9c98cf54fb2753d6390f3209e65906d671b800991","first_computed_at":"2026-07-05T09:59:47.846232Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:59:47.846232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Lw0DW+eBUUnH6YRHzeiC0er8gsPw1BP8GzsumCb+FqjoRFlmrwCnuy28W/YVGqscsPotqu6ffvBQ9qsdMl7AA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:59:47.846720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.20351","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63a70e7f309be4d947d96c51c98a06fb1b47efe1f791f5c240a4bc162603881d","sha256:cab892cbbca9643caa09c78907b1aadab7358be86ee8b9d25dfad72923ac3c41"],"state_sha256":"533c1103bff1f2a16405de2ca80d01edac56b338347874a98c4261a9a6f4af83"}