{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C3UV5JNJFHEQVYAZX2YGPCMCUO","short_pith_number":"pith:C3UV5JNJ","schema_version":"1.0","canonical_sha256":"16e95ea5a929c90ae019beb0678982a38a48586c5c344017177fdf394a3ea872","source":{"kind":"arxiv","id":"2605.16376","version":1},"attestation_state":"computed","paper":{"title":"Kelvin v1.0: A Neural Pre-Encoder for H.264: A standards-compliant learned preprocessor with -27.62% BD-VMAF on UVG","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.DC","cs.LG","cs.MM"],"primary_cat":"eess.IV","authors_text":"Marco Graziano","submitted_at":"2026-05-10T22:05:24Z","abstract_excerpt":"Kelvin is a lightweight learned pre-encoder that sits in front of an unmodified libx264 encoder. It applies content-adaptive pixel adjustments, bounded at +/-1/255 per channel, so that the encoder allocates bits where they matter most perceptually, while emitting a standard H.264 bitstream compatible with every existing decoder, player, and CDN. On the seven-sequence 1080p UVG benchmark, Kelvin v1.0 achieves a mean BD-VMAF of -27.62% (7 of 7 wins) and BD-VMAF-NEG of -5.18% (6 of 7 wins) relative to baseline libx264 at preset medium. On the 30-sequence MCL-JCV public set (28 unseen by training)"},"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":"2605.16376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.IV","submitted_at":"2026-05-10T22:05:24Z","cross_cats_sorted":["cs.CV","cs.DC","cs.LG","cs.MM"],"title_canon_sha256":"3768c77b5460b0404a1af715dd851d0c9c6fcd26f10e4308283106cffc5ded0a","abstract_canon_sha256":"e95b66a142cda1132549e814f2da746d204b994bdd3d8f368342953a87cfccfb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:19.109512Z","signature_b64":"/7dA/bA3EX9pwB14aGI3W6HrykKEpURzZ8nxp+N7x53KaeX7oRa3fdpwDOPFeuFws63ZgnR6KrjyP1DuEFs9DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16e95ea5a929c90ae019beb0678982a38a48586c5c344017177fdf394a3ea872","last_reissued_at":"2026-05-20T00:02:19.108932Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:19.108932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Kelvin v1.0: A Neural Pre-Encoder for H.264: A standards-compliant learned preprocessor with -27.62% BD-VMAF on UVG","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV","cs.DC","cs.LG","cs.MM"],"primary_cat":"eess.IV","authors_text":"Marco Graziano","submitted_at":"2026-05-10T22:05:24Z","abstract_excerpt":"Kelvin is a lightweight learned pre-encoder that sits in front of an unmodified libx264 encoder. It applies content-adaptive pixel adjustments, bounded at +/-1/255 per channel, so that the encoder allocates bits where they matter most perceptually, while emitting a standard H.264 bitstream compatible with every existing decoder, player, and CDN. On the seven-sequence 1080p UVG benchmark, Kelvin v1.0 achieves a mean BD-VMAF of -27.62% (7 of 7 wins) and BD-VMAF-NEG of -5.18% (6 of 7 wins) relative to baseline libx264 at preset medium. On the 30-sequence MCL-JCV public set (28 unseen by training)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16376","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/2605.16376/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.616862Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"637fcb1b0aac0c41367bd113b3e01c31c425b356e4407dd6356e7002eb8419fc"},"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":"2605.16376","created_at":"2026-05-20T00:02:19.109042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16376v1","created_at":"2026-05-20T00:02:19.109042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16376","created_at":"2026-05-20T00:02:19.109042+00:00"},{"alias_kind":"pith_short_12","alias_value":"C3UV5JNJFHEQ","created_at":"2026-05-20T00:02:19.109042+00:00"},{"alias_kind":"pith_short_16","alias_value":"C3UV5JNJFHEQVYAZ","created_at":"2026-05-20T00:02:19.109042+00:00"},{"alias_kind":"pith_short_8","alias_value":"C3UV5JNJ","created_at":"2026-05-20T00:02:19.109042+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/C3UV5JNJFHEQVYAZX2YGPCMCUO","json":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO.json","graph_json":"https://pith.science/api/pith-number/C3UV5JNJFHEQVYAZX2YGPCMCUO/graph.json","events_json":"https://pith.science/api/pith-number/C3UV5JNJFHEQVYAZX2YGPCMCUO/events.json","paper":"https://pith.science/paper/C3UV5JNJ"},"agent_actions":{"view_html":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO","download_json":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO.json","view_paper":"https://pith.science/paper/C3UV5JNJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16376&json=true","fetch_graph":"https://pith.science/api/pith-number/C3UV5JNJFHEQVYAZX2YGPCMCUO/graph.json","fetch_events":"https://pith.science/api/pith-number/C3UV5JNJFHEQVYAZX2YGPCMCUO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO/action/storage_attestation","attest_author":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO/action/author_attestation","sign_citation":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO/action/citation_signature","submit_replication":"https://pith.science/pith/C3UV5JNJFHEQVYAZX2YGPCMCUO/action/replication_record"}},"created_at":"2026-05-20T00:02:19.109042+00:00","updated_at":"2026-05-20T00:02:19.109042+00:00"}