{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YUAEN4NTCDCQQVKQARSWJFDKFJ","short_pith_number":"pith:YUAEN4NT","schema_version":"1.0","canonical_sha256":"c50046f1b310c5085550046564946a2a63e9fc91211557f89a22b53460a66c1d","source":{"kind":"arxiv","id":"2402.05887","version":2},"attestation_state":"computed","paper":{"title":"Sandwiched Compression: Repurposing Standard Codecs with Neural Network Wrappers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"eess.IV","authors_text":"Berivan Isik, Danhang Tang, Hugues Hoppe, Jonathan Taylor, Onur G. Guleryuz, Philip A. Chou, Philip Davidson, Ruofei Du, Sean Fanello","submitted_at":"2024-02-08T18:23:50Z","abstract_excerpt":"We propose sandwiching standard image and video codecs between pre- and post-processing neural networks. The networks are jointly trained through a differentiable codec proxy to minimize a given rate-distortion loss. This sandwich architecture not only improves the standard codec's performance on its intended content, but more importantly, adapts the codec to other types of image/video content and to other distortion measures. The sandwich learns to transmit ``neural code images'' that optimize and improve overall rate-distortion performance, with the improvements becoming significant especial"},"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":"2402.05887","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2024-02-08T18:23:50Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"aaa9be9e2e2a153a90fb3bab4233d266099990ab44f8d1061b30355733ab5e2e","abstract_canon_sha256":"7d743f84d90cecf289c67c100b4714547681f0cb255b00d270af131bc80381ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:46.059786Z","signature_b64":"DX+t+Gk8YWJJsXcyONJrU5Iq6AwBwJiBWbQ+tI45D/lRzmb3dI7iN02uoygGCCZM0qio6j2cnBIfFYeZWC8uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c50046f1b310c5085550046564946a2a63e9fc91211557f89a22b53460a66c1d","last_reissued_at":"2026-07-05T10:17:46.059299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:46.059299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sandwiched Compression: Repurposing Standard Codecs with Neural Network Wrappers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"eess.IV","authors_text":"Berivan Isik, Danhang Tang, Hugues Hoppe, Jonathan Taylor, Onur G. Guleryuz, Philip A. Chou, Philip Davidson, Ruofei Du, Sean Fanello","submitted_at":"2024-02-08T18:23:50Z","abstract_excerpt":"We propose sandwiching standard image and video codecs between pre- and post-processing neural networks. The networks are jointly trained through a differentiable codec proxy to minimize a given rate-distortion loss. This sandwich architecture not only improves the standard codec's performance on its intended content, but more importantly, adapts the codec to other types of image/video content and to other distortion measures. The sandwich learns to transmit ``neural code images'' that optimize and improve overall rate-distortion performance, with the improvements becoming significant especial"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05887","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/2402.05887/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":"2402.05887","created_at":"2026-07-05T10:17:46.059363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.05887v2","created_at":"2026-07-05T10:17:46.059363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05887","created_at":"2026-07-05T10:17:46.059363+00:00"},{"alias_kind":"pith_short_12","alias_value":"YUAEN4NTCDCQ","created_at":"2026-07-05T10:17:46.059363+00:00"},{"alias_kind":"pith_short_16","alias_value":"YUAEN4NTCDCQQVKQ","created_at":"2026-07-05T10:17:46.059363+00:00"},{"alias_kind":"pith_short_8","alias_value":"YUAEN4NT","created_at":"2026-07-05T10:17:46.059363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20671","citing_title":"A Projection-Based Surrogate Gradient Interpretation for Neural Codec Wrappers","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03940","citing_title":"SEAOTTER: Sensor Embedded Autoencoding with One-Time Transcode for Efficient Reconstruction","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ","json":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ.json","graph_json":"https://pith.science/api/pith-number/YUAEN4NTCDCQQVKQARSWJFDKFJ/graph.json","events_json":"https://pith.science/api/pith-number/YUAEN4NTCDCQQVKQARSWJFDKFJ/events.json","paper":"https://pith.science/paper/YUAEN4NT"},"agent_actions":{"view_html":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ","download_json":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ.json","view_paper":"https://pith.science/paper/YUAEN4NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.05887&json=true","fetch_graph":"https://pith.science/api/pith-number/YUAEN4NTCDCQQVKQARSWJFDKFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/YUAEN4NTCDCQQVKQARSWJFDKFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ/action/storage_attestation","attest_author":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ/action/author_attestation","sign_citation":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ/action/citation_signature","submit_replication":"https://pith.science/pith/YUAEN4NTCDCQQVKQARSWJFDKFJ/action/replication_record"}},"created_at":"2026-07-05T10:17:46.059363+00:00","updated_at":"2026-07-05T10:17:46.059363+00:00"}