{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RJSLWITTGKWHCXQIM2WRRR5CEM","short_pith_number":"pith:RJSLWITT","schema_version":"1.0","canonical_sha256":"8a64bb227332ac715e0866ad18c7a22329454deb335d2175224cfc3465f123d8","source":{"kind":"arxiv","id":"2605.27095","version":1},"attestation_state":"computed","paper":{"title":"Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo An, Chubin Zhang, Ivor W. Tsang, Jingxuan Wu, Mingcong Lei, Xingrui Yu, Yang You, Zhenglin Wan","submitted_at":"2026-05-26T14:38:03Z","abstract_excerpt":"Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised learners: the policy is trained only on expert states and receives no corrective signal on the states it actually visits. On-policy distillation (OPD) offers a natural remedy, but standard OPD assumes a strong fixed teacher, which is unavailable in demonstration-only control. We propose \\textbf{FA-OPD}, an \\emph{adversarial dual on-policy distillation} method"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.27095","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:38:03Z","cross_cats_sorted":[],"title_canon_sha256":"b6422b433d567dbfae64d151efdf69d4c52becdc64690e86b4d8f9f947826194","abstract_canon_sha256":"da18d78a400eefd665125d748e26b43d3f14fd089e357fdb66b29c67f5dde3d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:41.470224Z","signature_b64":"GBsjNSnHOfjywnTmoNkbLtuG2uqxOqBJ+5S+blK9qn8MxU3S3GKW8RPk0T9bc2M+/4QREYRGruedSOZKJOfHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a64bb227332ac715e0866ad18c7a22329454deb335d2175224cfc3465f123d8","last_reissued_at":"2026-05-27T02:05:41.469176Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:41.469176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo An, Chubin Zhang, Ivor W. Tsang, Jingxuan Wu, Mingcong Lei, Xingrui Yu, Yang You, Zhenglin Wan","submitted_at":"2026-05-26T14:38:03Z","abstract_excerpt":"Learning from demonstrations in embodied control is often cast as behavioral cloning, and recent diffusion or flow-matching policies improve this paradigm by modeling multi-modal expert actions. Yet these methods remain offline supervised learners: the policy is trained only on expert states and receives no corrective signal on the states it actually visits. On-policy distillation (OPD) offers a natural remedy, but standard OPD assumes a strong fixed teacher, which is unavailable in demonstration-only control. We propose \\textbf{FA-OPD}, an \\emph{adversarial dual on-policy distillation} method"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27095","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.27095/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27095","created_at":"2026-05-27T02:05:41.469338+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27095v1","created_at":"2026-05-27T02:05:41.469338+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27095","created_at":"2026-05-27T02:05:41.469338+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJSLWITTGKWH","created_at":"2026-05-27T02:05:41.469338+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJSLWITTGKWHCXQI","created_at":"2026-05-27T02:05:41.469338+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJSLWITT","created_at":"2026-05-27T02:05:41.469338+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM","json":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM.json","graph_json":"https://pith.science/api/pith-number/RJSLWITTGKWHCXQIM2WRRR5CEM/graph.json","events_json":"https://pith.science/api/pith-number/RJSLWITTGKWHCXQIM2WRRR5CEM/events.json","paper":"https://pith.science/paper/RJSLWITT"},"agent_actions":{"view_html":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM","download_json":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM.json","view_paper":"https://pith.science/paper/RJSLWITT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27095&json=true","fetch_graph":"https://pith.science/api/pith-number/RJSLWITTGKWHCXQIM2WRRR5CEM/graph.json","fetch_events":"https://pith.science/api/pith-number/RJSLWITTGKWHCXQIM2WRRR5CEM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM/action/storage_attestation","attest_author":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM/action/author_attestation","sign_citation":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM/action/citation_signature","submit_replication":"https://pith.science/pith/RJSLWITTGKWHCXQIM2WRRR5CEM/action/replication_record"}},"created_at":"2026-05-27T02:05:41.469338+00:00","updated_at":"2026-05-27T02:05:41.469338+00:00"}