{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FZE6CANWPAJ27NKLRZVM2LDOLO","short_pith_number":"pith:FZE6CANW","schema_version":"1.0","canonical_sha256":"2e49e101b67813afb54b8e6acd2c6e5b8247333eff86d4ce32379ffa215986ef","source":{"kind":"arxiv","id":"2303.02666","version":1},"attestation_state":"computed","paper":{"title":"Learned Lossless Compression for JPEG via Frequency-Domain Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chenglin Li, Hongkai Xiong, Jixiang Luo, Junni Zou, Shaohui Li, Wenrui Dai","submitted_at":"2023-03-05T13:15:28Z","abstract_excerpt":"JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels. In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients. To enable learning in the frequency domain, DCT coefficients are partitioned into groups to utilize implicit local redundancy. An auto"},"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":"2303.02666","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2023-03-05T13:15:28Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"7aecf6ac69653758dc546f08631f2ba7f846650dab73eecc773049681cf0ae8a","abstract_canon_sha256":"ddc2d2ea67aa90c6fa6a401fd15a9820a6410b357b29c41869fbcd3f09e62d83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:49:18.610211Z","signature_b64":"9LOcMm09cKsEmgL/0FvyocE+4BKptTIUSV/JKxyFIhd82b93zXEMH6ucLJsyfMRS5jatq5t5oVgNtaU84/kdDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e49e101b67813afb54b8e6acd2c6e5b8247333eff86d4ce32379ffa215986ef","last_reissued_at":"2026-07-05T05:49:18.609691Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:49:18.609691Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learned Lossless Compression for JPEG via Frequency-Domain Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Chenglin Li, Hongkai Xiong, Jixiang Luo, Junni Zou, Shaohui Li, Wenrui Dai","submitted_at":"2023-03-05T13:15:28Z","abstract_excerpt":"JPEG images can be further compressed to enhance the storage and transmission of large-scale image datasets. Existing learned lossless compressors for RGB images cannot be well transferred to JPEG images due to the distinguishing distribution of DCT coefficients and raw pixels. In this paper, we propose a novel framework for learned lossless compression of JPEG images that achieves end-to-end optimized prediction of the distribution of decoded DCT coefficients. To enable learning in the frequency domain, DCT coefficients are partitioned into groups to utilize implicit local redundancy. An auto"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02666","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/2303.02666/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":"2303.02666","created_at":"2026-07-05T05:49:18.609758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.02666v1","created_at":"2026-07-05T05:49:18.609758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02666","created_at":"2026-07-05T05:49:18.609758+00:00"},{"alias_kind":"pith_short_12","alias_value":"FZE6CANWPAJ2","created_at":"2026-07-05T05:49:18.609758+00:00"},{"alias_kind":"pith_short_16","alias_value":"FZE6CANWPAJ27NKL","created_at":"2026-07-05T05:49:18.609758+00:00"},{"alias_kind":"pith_short_8","alias_value":"FZE6CANW","created_at":"2026-07-05T05:49:18.609758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.05035","citing_title":"SMIC: Semantic Multi-Item Compression based on CLIP dictionary","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO","json":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO.json","graph_json":"https://pith.science/api/pith-number/FZE6CANWPAJ27NKLRZVM2LDOLO/graph.json","events_json":"https://pith.science/api/pith-number/FZE6CANWPAJ27NKLRZVM2LDOLO/events.json","paper":"https://pith.science/paper/FZE6CANW"},"agent_actions":{"view_html":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO","download_json":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO.json","view_paper":"https://pith.science/paper/FZE6CANW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.02666&json=true","fetch_graph":"https://pith.science/api/pith-number/FZE6CANWPAJ27NKLRZVM2LDOLO/graph.json","fetch_events":"https://pith.science/api/pith-number/FZE6CANWPAJ27NKLRZVM2LDOLO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO/action/storage_attestation","attest_author":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO/action/author_attestation","sign_citation":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO/action/citation_signature","submit_replication":"https://pith.science/pith/FZE6CANWPAJ27NKLRZVM2LDOLO/action/replication_record"}},"created_at":"2026-07-05T05:49:18.609758+00:00","updated_at":"2026-07-05T05:49:18.609758+00:00"}