{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZKSW5F6I7Z5RS7ZOUGDPS3A7XX","short_pith_number":"pith:ZKSW5F6I","schema_version":"1.0","canonical_sha256":"caa56e97c8fe7b197f2ea186f96c1fbdd05002de8aee4ad1bee21555268e7d72","source":{"kind":"arxiv","id":"2410.14758","version":2},"attestation_state":"computed","paper":{"title":"Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bac Nguyen, Chieh-Hsin Lai, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2024-10-18T09:12:33Z","abstract_excerpt":"By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion methods rely on fixed pretrained embeddings, limiting the benefits of joint training with the diffusion model. While jointly learning the embedding (via reconstruction loss) and the latent diffusion model (via score matching loss) could enhance performance, end-to-end training risks embedding collapse, degrading generation quality. To mitigate this issue, we in"},"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":"2410.14758","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-18T09:12:33Z","cross_cats_sorted":[],"title_canon_sha256":"d61d4c0d29292d8bf8c1ee9576bacc174bc1c0ca7c39147236483e022a36dbaa","abstract_canon_sha256":"b6835c3077da383e99993b00de5eea1a40744b0bb75cae18d468c176af3191f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:42:38.457389Z","signature_b64":"4FbBC7hJdiUwdFT2uMZu++0qdC0p/krlxok6YsPhHk2dufzYD8nZOct/bReoeDug+xDCjAF+BeXYD6zo0FOGAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"caa56e97c8fe7b197f2ea186f96c1fbdd05002de8aee4ad1bee21555268e7d72","last_reissued_at":"2026-07-05T10:42:38.456911Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:42:38.456911Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Vector-Quantized Image Modeling with Latent Consistency-Matching Diffusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bac Nguyen, Chieh-Hsin Lai, Naoki Murata, Stefano Ermon, Toshimitsu Uesaka, Yuhta Takida, Yuki Mitsufuji","submitted_at":"2024-10-18T09:12:33Z","abstract_excerpt":"By embedding discrete representations into a continuous latent space, we can leverage continuous-space latent diffusion models to handle generative modeling of discrete data. However, despite their initial success, most latent diffusion methods rely on fixed pretrained embeddings, limiting the benefits of joint training with the diffusion model. While jointly learning the embedding (via reconstruction loss) and the latent diffusion model (via score matching loss) could enhance performance, end-to-end training risks embedding collapse, degrading generation quality. To mitigate this issue, we in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14758","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/2410.14758/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":"2410.14758","created_at":"2026-07-05T10:42:38.456967+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.14758v2","created_at":"2026-07-05T10:42:38.456967+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14758","created_at":"2026-07-05T10:42:38.456967+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZKSW5F6I7Z5R","created_at":"2026-07-05T10:42:38.456967+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZKSW5F6I7Z5RS7ZO","created_at":"2026-07-05T10:42:38.456967+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZKSW5F6I","created_at":"2026-07-05T10:42:38.456967+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/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX","json":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX.json","graph_json":"https://pith.science/api/pith-number/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/graph.json","events_json":"https://pith.science/api/pith-number/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/events.json","paper":"https://pith.science/paper/ZKSW5F6I"},"agent_actions":{"view_html":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX","download_json":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX.json","view_paper":"https://pith.science/paper/ZKSW5F6I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.14758&json=true","fetch_graph":"https://pith.science/api/pith-number/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/graph.json","fetch_events":"https://pith.science/api/pith-number/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/action/storage_attestation","attest_author":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/action/author_attestation","sign_citation":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/action/citation_signature","submit_replication":"https://pith.science/pith/ZKSW5F6I7Z5RS7ZOUGDPS3A7XX/action/replication_record"}},"created_at":"2026-07-05T10:42:38.456967+00:00","updated_at":"2026-07-05T10:42:38.456967+00:00"}