{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NPRNPWOYEMX7YOTBPVRYHNXOE4","short_pith_number":"pith:NPRNPWOY","schema_version":"1.0","canonical_sha256":"6be2d7d9d8232ffc3a617d6383b6ee27319e0655fd3fe6185eb9a2d1d4fe2e5a","source":{"kind":"arxiv","id":"2502.11729","version":1},"attestation_state":"computed","paper":{"title":"On Quantizing Neural Representation for Variable-Rate Video Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Hanfei Li, Junqi Shi, Ming Lu, Qi Zhao, Tong Chen, Zhan Ma, Zhujia Chen","submitted_at":"2025-02-17T12:13:21Z","abstract_excerpt":"This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight retraining for each target bitrate, we hypothesize that variable-rate coding can be achieved by adjusting quantization parameters (QPs) of pre-trained weights. Our study reveals that traditional quantization methods, which assume inter-layer independence, are ineffective for non-generalized INR-VC models due to significant dependencies across layers. To addres"},"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":"2502.11729","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2025-02-17T12:13:21Z","cross_cats_sorted":[],"title_canon_sha256":"7b26b68621a44950d5720d89a3e40c0fa6dcf959b4e129744ed44b314b5d13f4","abstract_canon_sha256":"0a67bd048cc8a5c8354556a545253cf5f67dfe7a163c43a2945e02427f963a29"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:33.358521Z","signature_b64":"PhJt8RPWJKbq5vA+ZSbUUSQwUh5pXcQW59xQQta8InT3xaSnC5GUmDpoQdrVGf3/t0IM9C6gR1hmBHIXfNVcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6be2d7d9d8232ffc3a617d6383b6ee27319e0655fd3fe6185eb9a2d1d4fe2e5a","last_reissued_at":"2026-07-05T10:15:33.358026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:33.358026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Quantizing Neural Representation for Variable-Rate Video Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.IV","authors_text":"Hanfei Li, Junqi Shi, Ming Lu, Qi Zhao, Tong Chen, Zhan Ma, Zhujia Chen","submitted_at":"2025-02-17T12:13:21Z","abstract_excerpt":"This work introduces NeuroQuant, a novel post-training quantization (PTQ) approach tailored to non-generalized Implicit Neural Representations for variable-rate Video Coding (INR-VC). Unlike existing methods that require extensive weight retraining for each target bitrate, we hypothesize that variable-rate coding can be achieved by adjusting quantization parameters (QPs) of pre-trained weights. Our study reveals that traditional quantization methods, which assume inter-layer independence, are ineffective for non-generalized INR-VC models due to significant dependencies across layers. To addres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11729","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/2502.11729/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":"2502.11729","created_at":"2026-07-05T10:15:33.358098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11729v1","created_at":"2026-07-05T10:15:33.358098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11729","created_at":"2026-07-05T10:15:33.358098+00:00"},{"alias_kind":"pith_short_12","alias_value":"NPRNPWOYEMX7","created_at":"2026-07-05T10:15:33.358098+00:00"},{"alias_kind":"pith_short_16","alias_value":"NPRNPWOYEMX7YOTB","created_at":"2026-07-05T10:15:33.358098+00:00"},{"alias_kind":"pith_short_8","alias_value":"NPRNPWOY","created_at":"2026-07-05T10:15:33.358098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.01653","citing_title":"Hadamard-Domain Model Quantization for Learned Image Coding","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4","json":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4.json","graph_json":"https://pith.science/api/pith-number/NPRNPWOYEMX7YOTBPVRYHNXOE4/graph.json","events_json":"https://pith.science/api/pith-number/NPRNPWOYEMX7YOTBPVRYHNXOE4/events.json","paper":"https://pith.science/paper/NPRNPWOY"},"agent_actions":{"view_html":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4","download_json":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4.json","view_paper":"https://pith.science/paper/NPRNPWOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11729&json=true","fetch_graph":"https://pith.science/api/pith-number/NPRNPWOYEMX7YOTBPVRYHNXOE4/graph.json","fetch_events":"https://pith.science/api/pith-number/NPRNPWOYEMX7YOTBPVRYHNXOE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4/action/storage_attestation","attest_author":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4/action/author_attestation","sign_citation":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4/action/citation_signature","submit_replication":"https://pith.science/pith/NPRNPWOYEMX7YOTBPVRYHNXOE4/action/replication_record"}},"created_at":"2026-07-05T10:15:33.358098+00:00","updated_at":"2026-07-05T10:15:33.358098+00:00"}