{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J73RY33PTFZNWORQVOIAIJ5UFK","short_pith_number":"pith:J73RY33P","schema_version":"1.0","canonical_sha256":"4ff71c6f6f9972db3a30ab900427b42a833a7d5b45c814f190fcf4bf2df3acf6","source":{"kind":"arxiv","id":"2506.08662","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Detlev Marpe, Florian Borzechowski, Heiko Schwarz, Jonathan Pfaff, Michael Sch\\\"afer, Thomas Wiegand","submitted_at":"2025-06-10T10:22:22Z","abstract_excerpt":"The continuous improvements on image compression with variational autoencoders have lead to learned codecs competitive with conventional approaches in terms of rate-distortion efficiency. Nonetheless, taking the quantization into account during the training process remains a problem, since it produces zero derivatives almost everywhere and needs to be replaced with a differentiable approximation which allows end-to-end optimization. Though there are different methods for approximating the quantization, none of them model the quantization noise correctly and thus, result in suboptimal networks."},"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":"2506.08662","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T10:22:22Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"6d853770bc002b72a5d9c1e4fb70b00126305d20723d0a842c281f18ce3d6ffb","abstract_canon_sha256":"fa9a504846ad35e6f4dd9d6feacd693954b9c142824ef73a61458333a46585ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:11.372289Z","signature_b64":"p51RM4RVk0wNtDTw0ESb3ieGEDIMkRVlv38KEMcDJt9DBDC7iLgLCLZS5GBflxMu8crGuCQS/hSmew4NrdEeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ff71c6f6f9972db3a30ab900427b42a833a7d5b45c814f190fcf4bf2df3acf6","last_reissued_at":"2026-07-05T11:19:11.371771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:11.371771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Detlev Marpe, Florian Borzechowski, Heiko Schwarz, Jonathan Pfaff, Michael Sch\\\"afer, Thomas Wiegand","submitted_at":"2025-06-10T10:22:22Z","abstract_excerpt":"The continuous improvements on image compression with variational autoencoders have lead to learned codecs competitive with conventional approaches in terms of rate-distortion efficiency. Nonetheless, taking the quantization into account during the training process remains a problem, since it produces zero derivatives almost everywhere and needs to be replaced with a differentiable approximation which allows end-to-end optimization. Though there are different methods for approximating the quantization, none of them model the quantization noise correctly and thus, result in suboptimal networks."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.08662","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/2506.08662/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":"2506.08662","created_at":"2026-07-05T11:19:11.371832+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.08662v1","created_at":"2026-07-05T11:19:11.371832+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.08662","created_at":"2026-07-05T11:19:11.371832+00:00"},{"alias_kind":"pith_short_12","alias_value":"J73RY33PTFZN","created_at":"2026-07-05T11:19:11.371832+00:00"},{"alias_kind":"pith_short_16","alias_value":"J73RY33PTFZNWORQ","created_at":"2026-07-05T11:19:11.371832+00:00"},{"alias_kind":"pith_short_8","alias_value":"J73RY33P","created_at":"2026-07-05T11:19:11.371832+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.08662","citing_title":"Optimizing Learned Image Compression on Scalar and Entropy-Constraint Quantization","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK","json":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK.json","graph_json":"https://pith.science/api/pith-number/J73RY33PTFZNWORQVOIAIJ5UFK/graph.json","events_json":"https://pith.science/api/pith-number/J73RY33PTFZNWORQVOIAIJ5UFK/events.json","paper":"https://pith.science/paper/J73RY33P"},"agent_actions":{"view_html":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK","download_json":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK.json","view_paper":"https://pith.science/paper/J73RY33P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.08662&json=true","fetch_graph":"https://pith.science/api/pith-number/J73RY33PTFZNWORQVOIAIJ5UFK/graph.json","fetch_events":"https://pith.science/api/pith-number/J73RY33PTFZNWORQVOIAIJ5UFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK/action/storage_attestation","attest_author":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK/action/author_attestation","sign_citation":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK/action/citation_signature","submit_replication":"https://pith.science/pith/J73RY33PTFZNWORQVOIAIJ5UFK/action/replication_record"}},"created_at":"2026-07-05T11:19:11.371832+00:00","updated_at":"2026-07-05T11:19:11.371832+00:00"}