{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DNPMXJWJ5B4HQ5C7UL2REKLMYE","short_pith_number":"pith:DNPMXJWJ","schema_version":"1.0","canonical_sha256":"1b5ecba6c9e87878745fa2f512296cc11ab0a7b8625259cda606bde222b8146b","source":{"kind":"arxiv","id":"2403.07320","version":2},"attestation_state":"computed","paper":{"title":"Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","math.IT"],"primary_cat":"cs.IT","authors_text":"Eric Lei, Hamed Hassani, Shirin Saeedi Bidokhti","submitted_at":"2024-03-12T05:09:25Z","abstract_excerpt":"Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which is then rounded to integers and entropy coded. While this approach has been shown to be optimal on a few specific sources, we show that it can be highly sub-optimal on synthetic sources whose intrinsic dimensionality is greater than one. With integer rounding in the latent space, the quantization regions induced by neural transformations, remain square-like a"},"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":"2403.07320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IT","submitted_at":"2024-03-12T05:09:25Z","cross_cats_sorted":["cs.LG","eess.SP","math.IT"],"title_canon_sha256":"584b4341a93fe73df028cd76770335c8a870dc5005bec9056488f1aeddeec6b7","abstract_canon_sha256":"4859eaf3c9b2422ee0cf146efd94718212b16245b9cc73ab896392ab8c8fd167"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:19.464416Z","signature_b64":"+MzqVv9xaxx5KT32QGkX/C8JA5+zYJBT4/RL5u+GCojVKyWQywBp7HK5KigEL1LSE5LMhpK4Sa4bEMibUOm6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b5ecba6c9e87878745fa2f512296cc11ab0a7b8625259cda606bde222b8146b","last_reissued_at":"2026-07-05T11:36:19.463891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:19.463891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Approaching Rate-Distortion Limits in Neural Compression with Lattice Transform Coding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.SP","math.IT"],"primary_cat":"cs.IT","authors_text":"Eric Lei, Hamed Hassani, Shirin Saeedi Bidokhti","submitted_at":"2024-03-12T05:09:25Z","abstract_excerpt":"Neural compression has brought tremendous progress in designing lossy compressors with good rate-distortion (RD) performance at low complexity. Thus far, neural compression design involves transforming the source to a latent vector, which is then rounded to integers and entropy coded. While this approach has been shown to be optimal on a few specific sources, we show that it can be highly sub-optimal on synthetic sources whose intrinsic dimensionality is greater than one. With integer rounding in the latent space, the quantization regions induced by neural transformations, remain square-like a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07320","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/2403.07320/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":"2403.07320","created_at":"2026-07-05T11:36:19.463949+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07320v2","created_at":"2026-07-05T11:36:19.463949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07320","created_at":"2026-07-05T11:36:19.463949+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNPMXJWJ5B4H","created_at":"2026-07-05T11:36:19.463949+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNPMXJWJ5B4HQ5C7","created_at":"2026-07-05T11:36:19.463949+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNPMXJWJ","created_at":"2026-07-05T11:36:19.463949+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.16119","citing_title":"Learning Optimal Lattice Vector Quantizers for End-to-end Neural Image Compression","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE","json":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE.json","graph_json":"https://pith.science/api/pith-number/DNPMXJWJ5B4HQ5C7UL2REKLMYE/graph.json","events_json":"https://pith.science/api/pith-number/DNPMXJWJ5B4HQ5C7UL2REKLMYE/events.json","paper":"https://pith.science/paper/DNPMXJWJ"},"agent_actions":{"view_html":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE","download_json":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE.json","view_paper":"https://pith.science/paper/DNPMXJWJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07320&json=true","fetch_graph":"https://pith.science/api/pith-number/DNPMXJWJ5B4HQ5C7UL2REKLMYE/graph.json","fetch_events":"https://pith.science/api/pith-number/DNPMXJWJ5B4HQ5C7UL2REKLMYE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE/action/storage_attestation","attest_author":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE/action/author_attestation","sign_citation":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE/action/citation_signature","submit_replication":"https://pith.science/pith/DNPMXJWJ5B4HQ5C7UL2REKLMYE/action/replication_record"}},"created_at":"2026-07-05T11:36:19.463949+00:00","updated_at":"2026-07-05T11:36:19.463949+00:00"}