{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FXUVWOO3WXDSSTRJ7JUJOQKOJB","short_pith_number":"pith:FXUVWOO3","schema_version":"1.0","canonical_sha256":"2de95b39dbb5c7294e29fa6897414e485ae4ca9192d9c4424059e9671b1cbf5e","source":{"kind":"arxiv","id":"2310.15578","version":4},"attestation_state":"computed","paper":{"title":"VMAF Re-implementation on PyTorch: Some Experimental Results","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Kirill Aistov, Maxim Koroteev","submitted_at":"2023-10-24T07:42:04Z","abstract_excerpt":"Based on the standard VMAF implementation we propose an implementation of VMAF using PyTorch framework. For this implementation comparisons with the standard (libvmaf) show the discrepancy $\\lesssim 10^{-2}$ in VMAF units. We investigate gradients computation when using VMAF as an objective function and demonstrate that training using this function does not result in ill-behaving gradients. The implementation is then used to train a preprocessing filter. It is demonstrated that its performance is superior to the unsharp masking filter. The resulting filter is also easy for implementation and c"},"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":"2310.15578","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-24T07:42:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ab528eceff9ac94a13e6f73a506480a1b16ebf68b4de6c1c62583c3c120316f6","abstract_canon_sha256":"f159e52da61152fcb448fdec8969e32d0146f865fe64bc4d5d535cb537bb8b78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:10.354523Z","signature_b64":"xAeDhUzJilaaxE8mQYv3v/OclWX432CAehJaA96TpKUqB2AMVh5R/xDvbAN4uKinbdET0ss/jS2rlj9RwUH+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2de95b39dbb5c7294e29fa6897414e485ae4ca9192d9c4424059e9671b1cbf5e","last_reissued_at":"2026-07-05T08:44:10.354013Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:10.354013Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VMAF Re-implementation on PyTorch: Some Experimental Results","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Kirill Aistov, Maxim Koroteev","submitted_at":"2023-10-24T07:42:04Z","abstract_excerpt":"Based on the standard VMAF implementation we propose an implementation of VMAF using PyTorch framework. For this implementation comparisons with the standard (libvmaf) show the discrepancy $\\lesssim 10^{-2}$ in VMAF units. We investigate gradients computation when using VMAF as an objective function and demonstrate that training using this function does not result in ill-behaving gradients. The implementation is then used to train a preprocessing filter. It is demonstrated that its performance is superior to the unsharp masking filter. The resulting filter is also easy for implementation and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15578","kind":"arxiv","version":4},"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/2310.15578/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":"2310.15578","created_at":"2026-07-05T08:44:10.354076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15578v4","created_at":"2026-07-05T08:44:10.354076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15578","created_at":"2026-07-05T08:44:10.354076+00:00"},{"alias_kind":"pith_short_12","alias_value":"FXUVWOO3WXDS","created_at":"2026-07-05T08:44:10.354076+00:00"},{"alias_kind":"pith_short_16","alias_value":"FXUVWOO3WXDSSTRJ","created_at":"2026-07-05T08:44:10.354076+00:00"},{"alias_kind":"pith_short_8","alias_value":"FXUVWOO3","created_at":"2026-07-05T08:44:10.354076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.23382","citing_title":"SIEDD: Shared-Implicit Encoder with Discrete Decoders","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB","json":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB.json","graph_json":"https://pith.science/api/pith-number/FXUVWOO3WXDSSTRJ7JUJOQKOJB/graph.json","events_json":"https://pith.science/api/pith-number/FXUVWOO3WXDSSTRJ7JUJOQKOJB/events.json","paper":"https://pith.science/paper/FXUVWOO3"},"agent_actions":{"view_html":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB","download_json":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB.json","view_paper":"https://pith.science/paper/FXUVWOO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15578&json=true","fetch_graph":"https://pith.science/api/pith-number/FXUVWOO3WXDSSTRJ7JUJOQKOJB/graph.json","fetch_events":"https://pith.science/api/pith-number/FXUVWOO3WXDSSTRJ7JUJOQKOJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB/action/storage_attestation","attest_author":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB/action/author_attestation","sign_citation":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB/action/citation_signature","submit_replication":"https://pith.science/pith/FXUVWOO3WXDSSTRJ7JUJOQKOJB/action/replication_record"}},"created_at":"2026-07-05T08:44:10.354076+00:00","updated_at":"2026-07-05T08:44:10.354076+00:00"}