{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JHGLDS3QT3OFD73S2XRO3GOFNY","short_pith_number":"pith:JHGLDS3Q","schema_version":"1.0","canonical_sha256":"49ccb1cb709edc51ff72d5e2ed99c56e3e6cdd011232e76462f589a7b6cb0899","source":{"kind":"arxiv","id":"2605.26105","version":1},"attestation_state":"computed","paper":{"title":"On-Policy Adversarial Flow Distillation for Autoregressive Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shengju Qian, Xiaohang Tang, Xin Wang, Yang Luo, Yang You, Yong Liu, Zirui Zhu","submitted_at":"2026-05-25T17:58:12Z","abstract_excerpt":"Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains difficult. The student must learn under its own rollout distribution, whereas practical teachers may expose only prompt-conditioned completed videos and may differ in architecture, capacity, temporal design, and sampling schedule. This interface makes supervised fine-tuning off-policy, score-based distillation inapplicable, and direct adversarial imitation too sparse for denoising-time credit assignment. We propose Adver"},"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":"2605.26105","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-25T17:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"9bcb213ccd352b8e40f43ab580981fb5e157deb7e98a3be40833f04a8c41203f","abstract_canon_sha256":"f229cc230f131caaab2a8d95e9640fac4f2335152a7662227ceb3ca40fc9d022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T03:05:24.302152Z","signature_b64":"71mIGISFtRI00r/uVf5XU6pDTdbf7iQPlW7/8JxYXN+roaZiwoZj2SZ8je72VI07pyAo1xFT3SmxKrEXlJKeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"49ccb1cb709edc51ff72d5e2ed99c56e3e6cdd011232e76462f589a7b6cb0899","last_reissued_at":"2026-05-26T03:05:24.301160Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T03:05:24.301160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-Policy Adversarial Flow Distillation for Autoregressive Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Shengju Qian, Xiaohang Tang, Xin Wang, Yang Luo, Yang You, Yong Liu, Zirui Zhu","submitted_at":"2026-05-25T17:58:12Z","abstract_excerpt":"Autoregressive video generators are attractive for streaming, long-horizon, and interactive applications, but distilling strong black-box teachers into causal students remains difficult. The student must learn under its own rollout distribution, whereas practical teachers may expose only prompt-conditioned completed videos and may differ in architecture, capacity, temporal design, and sampling schedule. This interface makes supervised fine-tuning off-policy, score-based distillation inapplicable, and direct adversarial imitation too sparse for denoising-time credit assignment. We propose Adver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26105","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/2605.26105/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":"2605.26105","created_at":"2026-05-26T03:05:24.301324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26105v1","created_at":"2026-05-26T03:05:24.301324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26105","created_at":"2026-05-26T03:05:24.301324+00:00"},{"alias_kind":"pith_short_12","alias_value":"JHGLDS3QT3OF","created_at":"2026-05-26T03:05:24.301324+00:00"},{"alias_kind":"pith_short_16","alias_value":"JHGLDS3QT3OFD73S","created_at":"2026-05-26T03:05:24.301324+00:00"},{"alias_kind":"pith_short_8","alias_value":"JHGLDS3Q","created_at":"2026-05-26T03:05:24.301324+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/JHGLDS3QT3OFD73S2XRO3GOFNY","json":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY.json","graph_json":"https://pith.science/api/pith-number/JHGLDS3QT3OFD73S2XRO3GOFNY/graph.json","events_json":"https://pith.science/api/pith-number/JHGLDS3QT3OFD73S2XRO3GOFNY/events.json","paper":"https://pith.science/paper/JHGLDS3Q"},"agent_actions":{"view_html":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY","download_json":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY.json","view_paper":"https://pith.science/paper/JHGLDS3Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26105&json=true","fetch_graph":"https://pith.science/api/pith-number/JHGLDS3QT3OFD73S2XRO3GOFNY/graph.json","fetch_events":"https://pith.science/api/pith-number/JHGLDS3QT3OFD73S2XRO3GOFNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY/action/storage_attestation","attest_author":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY/action/author_attestation","sign_citation":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY/action/citation_signature","submit_replication":"https://pith.science/pith/JHGLDS3QT3OFD73S2XRO3GOFNY/action/replication_record"}},"created_at":"2026-05-26T03:05:24.301324+00:00","updated_at":"2026-05-26T03:05:24.301324+00:00"}