{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7HPIKPP3FDBRS7LKW5O7GXFJUT","short_pith_number":"pith:7HPIKPP3","schema_version":"1.0","canonical_sha256":"f9de853dfb28c3197d6ab75df35ca9a4e3abe3797f56f2db5b6726b4db7669d6","source":{"kind":"arxiv","id":"2310.03004","version":1},"attestation_state":"computed","paper":{"title":"Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","math.OC"],"primary_cat":"cs.LG","authors_text":"Chenguang Zhu, Reid Pryzant, Somayeh Sojoudi, Tanmay Gautam, Ziyi Yang","submitted_at":"2023-10-04T17:45:14Z","abstract_excerpt":"Vector Quantization (VQ) is a well-known technique in deep learning for extracting informative discrete latent representations. VQ-embedded models have shown impressive results in a range of applications including image and speech generation. VQ operates as a parametric K-means algorithm that quantizes inputs using a single codebook vector in the forward pass. While powerful, this technique faces practical challenges including codebook collapse, non-differentiability and lossy compression. To mitigate the aforementioned issues, we propose Soft Convex Quantization (SCQ) as a direct substitute f"},"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":"2310.03004","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T17:45:14Z","cross_cats_sorted":["cs.AI","cs.CV","cs.MM","math.OC"],"title_canon_sha256":"4e09a2acab73f7e55a7f63060586fc81cf39e31e20a1e003b7d392de2b99368f","abstract_canon_sha256":"01446a33ef9e2df3b5d6805a66d1d820749d87ece34365741184c831d9e53d26"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:16.444725Z","signature_b64":"WjjTt+NVLEIhkUR8CGyE1ceAUoAkrr/se1jxC0/c3tKkstqS3fC0BdpHRPsBq+WXH4jDE8FkMWpTpwlQJ2umAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9de853dfb28c3197d6ab75df35ca9a4e3abe3797f56f2db5b6726b4db7669d6","last_reissued_at":"2026-07-05T06:57:16.444235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:16.444235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Soft Convex Quantization: Revisiting Vector Quantization with Convex Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.MM","math.OC"],"primary_cat":"cs.LG","authors_text":"Chenguang Zhu, Reid Pryzant, Somayeh Sojoudi, Tanmay Gautam, Ziyi Yang","submitted_at":"2023-10-04T17:45:14Z","abstract_excerpt":"Vector Quantization (VQ) is a well-known technique in deep learning for extracting informative discrete latent representations. VQ-embedded models have shown impressive results in a range of applications including image and speech generation. VQ operates as a parametric K-means algorithm that quantizes inputs using a single codebook vector in the forward pass. While powerful, this technique faces practical challenges including codebook collapse, non-differentiability and lossy compression. To mitigate the aforementioned issues, we propose Soft Convex Quantization (SCQ) as a direct substitute f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03004","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/2310.03004/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":"2310.03004","created_at":"2026-07-05T06:57:16.444291+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03004v1","created_at":"2026-07-05T06:57:16.444291+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03004","created_at":"2026-07-05T06:57:16.444291+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HPIKPP3FDBR","created_at":"2026-07-05T06:57:16.444291+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HPIKPP3FDBRS7LK","created_at":"2026-07-05T06:57:16.444291+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HPIKPP3","created_at":"2026-07-05T06:57:16.444291+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT","json":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT.json","graph_json":"https://pith.science/api/pith-number/7HPIKPP3FDBRS7LKW5O7GXFJUT/graph.json","events_json":"https://pith.science/api/pith-number/7HPIKPP3FDBRS7LKW5O7GXFJUT/events.json","paper":"https://pith.science/paper/7HPIKPP3"},"agent_actions":{"view_html":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT","download_json":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT.json","view_paper":"https://pith.science/paper/7HPIKPP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03004&json=true","fetch_graph":"https://pith.science/api/pith-number/7HPIKPP3FDBRS7LKW5O7GXFJUT/graph.json","fetch_events":"https://pith.science/api/pith-number/7HPIKPP3FDBRS7LKW5O7GXFJUT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT/action/storage_attestation","attest_author":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT/action/author_attestation","sign_citation":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT/action/citation_signature","submit_replication":"https://pith.science/pith/7HPIKPP3FDBRS7LKW5O7GXFJUT/action/replication_record"}},"created_at":"2026-07-05T06:57:16.444291+00:00","updated_at":"2026-07-05T06:57:16.444291+00:00"}