{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AGHTHD3Z5S4TQPREBIG3IEIDUU","short_pith_number":"pith:AGHTHD3Z","schema_version":"1.0","canonical_sha256":"018f338f79ecb9383e240a0db41103a520515f4ad0d463d74c766cd0cf32702b","source":{"kind":"arxiv","id":"2501.16085","version":2},"attestation_state":"computed","paper":{"title":"ARFlow: Autoregressive Flow with Hybrid Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Jason Eshraghian, Mude Hui, Rui-Jie Zhu, Songlin Yang, Yuyin Zhou, Yu Zhang, Zirui Wang","submitted_at":"2025-01-27T14:33:27Z","abstract_excerpt":"Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image. To address this limitation, we propose integrating autoregressive modeling -- known for its excellence in modeling complex, high-dimensional joint probability distributions -- into flow models. During training, at each step, we construct causally-ordered sequences by sampling multiple images from the same semantic category and applying diff"},"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":"2501.16085","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-27T14:33:27Z","cross_cats_sorted":[],"title_canon_sha256":"a5de825ef729aed2f9f382da2bd8ad513f2222574bb9d9a953a6f4a083b206e4","abstract_canon_sha256":"495dee9bce52b925f6c4b4df476123f983753c402b5601255d8d46fff3bd302c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:21:41.122469Z","signature_b64":"0hTcaZqengu6WiwfXBQlcc/KbWeRm14eiNYIOu60hZfU81/AQuqbFSbNAU5bfzZ4eRsZjDF6XWUBv3rJFgQcCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"018f338f79ecb9383e240a0db41103a520515f4ad0d463d74c766cd0cf32702b","last_reissued_at":"2026-07-05T11:21:41.121967Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:21:41.121967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ARFlow: Autoregressive Flow with Hybrid Linear Attention","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Jason Eshraghian, Mude Hui, Rui-Jie Zhu, Songlin Yang, Yuyin Zhou, Yu Zhang, Zirui Wang","submitted_at":"2025-01-27T14:33:27Z","abstract_excerpt":"Flow models are effective at progressively generating realistic images, but they generally struggle to capture long-range dependencies during the generation process as they compress all the information from previous time steps into a single corrupted image. To address this limitation, we propose integrating autoregressive modeling -- known for its excellence in modeling complex, high-dimensional joint probability distributions -- into flow models. During training, at each step, we construct causally-ordered sequences by sampling multiple images from the same semantic category and applying diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16085","kind":"arxiv","version":2},"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/2501.16085/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":"2501.16085","created_at":"2026-07-05T11:21:41.122027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16085v2","created_at":"2026-07-05T11:21:41.122027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16085","created_at":"2026-07-05T11:21:41.122027+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGHTHD3Z5S4T","created_at":"2026-07-05T11:21:41.122027+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGHTHD3Z5S4TQPRE","created_at":"2026-07-05T11:21:41.122027+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGHTHD3Z","created_at":"2026-07-05T11:21:41.122027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.15321","citing_title":"Next Patch Prediction for Autoregressive Visual Generation","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU","json":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU.json","graph_json":"https://pith.science/api/pith-number/AGHTHD3Z5S4TQPREBIG3IEIDUU/graph.json","events_json":"https://pith.science/api/pith-number/AGHTHD3Z5S4TQPREBIG3IEIDUU/events.json","paper":"https://pith.science/paper/AGHTHD3Z"},"agent_actions":{"view_html":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU","download_json":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU.json","view_paper":"https://pith.science/paper/AGHTHD3Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16085&json=true","fetch_graph":"https://pith.science/api/pith-number/AGHTHD3Z5S4TQPREBIG3IEIDUU/graph.json","fetch_events":"https://pith.science/api/pith-number/AGHTHD3Z5S4TQPREBIG3IEIDUU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU/action/storage_attestation","attest_author":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU/action/author_attestation","sign_citation":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU/action/citation_signature","submit_replication":"https://pith.science/pith/AGHTHD3Z5S4TQPREBIG3IEIDUU/action/replication_record"}},"created_at":"2026-07-05T11:21:41.122027+00:00","updated_at":"2026-07-05T11:21:41.122027+00:00"}