{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F33E7IG7PTFTLCY5XTGZEGN7K5","short_pith_number":"pith:F33E7IG7","schema_version":"1.0","canonical_sha256":"2ef64fa0df7ccb358b1dbccd9219bf57676939257ce353d1218d2e1621ec6c01","source":{"kind":"arxiv","id":"2510.00948","version":2},"attestation_state":"computed","paper":{"title":"InfVSR: Breaking Length Limits of Generic Video Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingnan Duan, Kai Liu, Linghe Kong, Xi Li, Yucong Chen, Yulun Zhang, Zheng Chen, Ziqing Zhang","submitted_at":"2025-10-01T14:21:45Z","abstract_excerpt":"Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent challenges when processing long sequences: (1) inefficiency due to the heavy cost of multi-step denoising for full-length sequences; and (2) poor consistency is hindered by temporal decomposition that causes artifacts and discontinuities. To break these limits, we propose InfVSR, which reformulates VSR as an autoregressive-one-step-diffusion paradigm, and enables streaming inference with video diffusion priors. First, we adapt the pretrained DiT int"},"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":"2510.00948","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T14:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"70dcf1c80b4cbe9d6f4a6d069a82ebf4059a050ed37365c5b3e06da5082da5ed","abstract_canon_sha256":"f998e584900976c025a50badb7770b96d970010657237814d7f64debc4a12ec6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:47.548310Z","signature_b64":"SirWOyCoDuDZZoScYEj0DB04sFNyzjurPoUcDS/fLUAT4MSMhEUth+njw0OxO4AwT0cLQH1ARuHYxOonUKUXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef64fa0df7ccb358b1dbccd9219bf57676939257ce353d1218d2e1621ec6c01","last_reissued_at":"2026-05-22T01:03:47.547458Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:47.547458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfVSR: Breaking Length Limits of Generic Video Super-Resolution","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingnan Duan, Kai Liu, Linghe Kong, Xi Li, Yucong Chen, Yulun Zhang, Zheng Chen, Ziqing Zhang","submitted_at":"2025-10-01T14:21:45Z","abstract_excerpt":"Real-world videos often extend over thousands of frames. Existing generative video super-resolution (VSR) approaches, however, face two persistent challenges when processing long sequences: (1) inefficiency due to the heavy cost of multi-step denoising for full-length sequences; and (2) poor consistency is hindered by temporal decomposition that causes artifacts and discontinuities. To break these limits, we propose InfVSR, which reformulates VSR as an autoregressive-one-step-diffusion paradigm, and enables streaming inference with video diffusion priors. First, we adapt the pretrained DiT int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00948","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/2510.00948/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":"2510.00948","created_at":"2026-05-22T01:03:47.547564+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.00948v2","created_at":"2026-05-22T01:03:47.547564+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00948","created_at":"2026-05-22T01:03:47.547564+00:00"},{"alias_kind":"pith_short_12","alias_value":"F33E7IG7PTFT","created_at":"2026-05-22T01:03:47.547564+00:00"},{"alias_kind":"pith_short_16","alias_value":"F33E7IG7PTFTLCY5","created_at":"2026-05-22T01:03:47.547564+00:00"},{"alias_kind":"pith_short_8","alias_value":"F33E7IG7","created_at":"2026-05-22T01:03:47.547564+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2512.23709","citing_title":"Stream-DiffVSR: Low-Latency Streamable Video Super-Resolution via Auto-Regressive Diffusion","ref_index":101,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13182","citing_title":"DiffST: Spatiotemporal-Aware Diffusion for Real-World Space-Time Video Super-Resolution","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18047","citing_title":"GS-STVSR: Ultra-Efficient Continuous Spatio-Temporal Video Super-Resolution via 2D Gaussian Splatting","ref_index":159,"is_internal_anchor":true},{"citing_arxiv_id":"2604.14560","citing_title":"DVFace: Spatio-Temporal Dual-Prior Diffusion for Video Face Restoration","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5","json":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5.json","graph_json":"https://pith.science/api/pith-number/F33E7IG7PTFTLCY5XTGZEGN7K5/graph.json","events_json":"https://pith.science/api/pith-number/F33E7IG7PTFTLCY5XTGZEGN7K5/events.json","paper":"https://pith.science/paper/F33E7IG7"},"agent_actions":{"view_html":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5","download_json":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5.json","view_paper":"https://pith.science/paper/F33E7IG7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.00948&json=true","fetch_graph":"https://pith.science/api/pith-number/F33E7IG7PTFTLCY5XTGZEGN7K5/graph.json","fetch_events":"https://pith.science/api/pith-number/F33E7IG7PTFTLCY5XTGZEGN7K5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5/action/storage_attestation","attest_author":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5/action/author_attestation","sign_citation":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5/action/citation_signature","submit_replication":"https://pith.science/pith/F33E7IG7PTFTLCY5XTGZEGN7K5/action/replication_record"}},"created_at":"2026-05-22T01:03:47.547564+00:00","updated_at":"2026-05-22T01:03:47.547564+00:00"}