{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RJSLWITTGKWHCXQIM2WRRR5CEM","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":"da18d78a400eefd665125d748e26b43d3f14fd089e357fdb66b29c67f5dde3d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:38:03Z","title_canon_sha256":"b6422b433d567dbfae64d151efdf69d4c52becdc64690e86b4d8f9f947826194"},"schema_version":"1.0","source":{"id":"2605.27095","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27095","created_at":"2026-05-27T02:05:41Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27095v1","created_at":"2026-05-27T02:05:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27095","created_at":"2026-05-27T02:05:41Z"},{"alias_kind":"pith_short_12","alias_value":"RJSLWITTGKWH","created_at":"2026-05-27T02:05:41Z"},{"alias_kind":"pith_short_16","alias_value":"RJSLWITTGKWHCXQI","created_at":"2026-05-27T02:05:41Z"},{"alias_kind":"pith_short_8","alias_value":"RJSLWITT","created_at":"2026-05-27T02:05:41Z"}],"graph_snapshots":[{"event_id":"sha256:f4c1cbc00c8ae0f8cd59a2d40d800d10d902fbad088d01679ded79e9b5d70c3b","target":"graph","created_at":"2026-05-27T02:05:41Z","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/2605.27095/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo An, Chubin Zhang, Ivor W. Tsang, Jingxuan Wu, Mingcong Lei, Xingrui Yu, Yang You, Zhenglin Wan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:38:03Z","title":"Adversarial Dual On-Policy Distillation from Expressive Flow-based Teacher"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27095","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":"sha256:79aed5b53ab2c920db1d0dc7c23743f90858c5731f361bdad6b5e4b6987fff7c","target":"record","created_at":"2026-05-27T02:05:41Z","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":"da18d78a400eefd665125d748e26b43d3f14fd089e357fdb66b29c67f5dde3d0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T14:38:03Z","title_canon_sha256":"b6422b433d567dbfae64d151efdf69d4c52becdc64690e86b4d8f9f947826194"},"schema_version":"1.0","source":{"id":"2605.27095","kind":"arxiv","version":1}},"canonical_sha256":"8a64bb227332ac715e0866ad18c7a22329454deb335d2175224cfc3465f123d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a64bb227332ac715e0866ad18c7a22329454deb335d2175224cfc3465f123d8","first_computed_at":"2026-05-27T02:05:41.469176Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:05:41.469176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GBsjNSnHOfjywnTmoNkbLtuG2uqxOqBJ+5S+blK9qn8MxU3S3GKW8RPk0T9bc2M+/4QREYRGruedSOZKJOfHCA==","signature_status":"signed_v1","signed_at":"2026-05-27T02:05:41.470224Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27095","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79aed5b53ab2c920db1d0dc7c23743f90858c5731f361bdad6b5e4b6987fff7c","sha256:f4c1cbc00c8ae0f8cd59a2d40d800d10d902fbad088d01679ded79e9b5d70c3b"],"state_sha256":"a7fd199666b7a01bddaa509dc2204c24fba33980b96db3b6df9bca1f42d4774b"}