{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XTQNTHZZVMRP3EM5GB6X5BQZKF","short_pith_number":"pith:XTQNTHZZ","schema_version":"1.0","canonical_sha256":"bce0d99f39ab22fd919d307d7e86195170597329c263e3e215faf3effb1f20bc","source":{"kind":"arxiv","id":"2310.08337","version":3},"attestation_state":"computed","paper":{"title":"Neural Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian A. Naesseth, Dmitry Vetrov, Grigory Bartosh","submitted_at":"2023-10-12T13:54:55Z","abstract_excerpt":"Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of transformations can potentially help train generative distributions more efficiently, simplifying the reverse process and closing the gap between the true negative log-likelihood and the variational approximation. In this paper, we present Neural Diffusion Models (NDMs), a generalization of conventional diffusion models that enables defining and learning ti"},"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":"2310.08337","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-12T13:54:55Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e026006e543ff4095921aeb34add4dd19d172e90f86d2722d51bfaf47600a0f8","abstract_canon_sha256":"309cd0b588e3377a01607b8b694f58c64dd3f1a76c702edc63b5e77f0cf27534"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:50.214495Z","signature_b64":"PoFOLgLXC9SSISOJQB3fAqUmydWizvfwj7H/bVurW7mr67gl/Hixf5KGvQtN6HHfiUALFF3UIYc671eeBwcvAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce0d99f39ab22fd919d307d7e86195170597329c263e3e215faf3effb1f20bc","last_reissued_at":"2026-07-05T08:25:50.214011Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:50.214011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christian A. Naesseth, Dmitry Vetrov, Grigory Bartosh","submitted_at":"2023-10-12T13:54:55Z","abstract_excerpt":"Diffusion models have shown remarkable performance on many generative tasks. Despite recent success, most diffusion models are restricted in that they only allow linear transformation of the data distribution. In contrast, broader family of transformations can potentially help train generative distributions more efficiently, simplifying the reverse process and closing the gap between the true negative log-likelihood and the variational approximation. In this paper, we present Neural Diffusion Models (NDMs), a generalization of conventional diffusion models that enables defining and learning ti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08337","kind":"arxiv","version":3},"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/2310.08337/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":"2310.08337","created_at":"2026-07-05T08:25:50.214075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08337v3","created_at":"2026-07-05T08:25:50.214075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08337","created_at":"2026-07-05T08:25:50.214075+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTQNTHZZVMRP","created_at":"2026-07-05T08:25:50.214075+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTQNTHZZVMRP3EM5","created_at":"2026-07-05T08:25:50.214075+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTQNTHZZ","created_at":"2026-07-05T08:25:50.214075+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.23748","citing_title":"A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF","json":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF.json","graph_json":"https://pith.science/api/pith-number/XTQNTHZZVMRP3EM5GB6X5BQZKF/graph.json","events_json":"https://pith.science/api/pith-number/XTQNTHZZVMRP3EM5GB6X5BQZKF/events.json","paper":"https://pith.science/paper/XTQNTHZZ"},"agent_actions":{"view_html":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF","download_json":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF.json","view_paper":"https://pith.science/paper/XTQNTHZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08337&json=true","fetch_graph":"https://pith.science/api/pith-number/XTQNTHZZVMRP3EM5GB6X5BQZKF/graph.json","fetch_events":"https://pith.science/api/pith-number/XTQNTHZZVMRP3EM5GB6X5BQZKF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF/action/storage_attestation","attest_author":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF/action/author_attestation","sign_citation":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF/action/citation_signature","submit_replication":"https://pith.science/pith/XTQNTHZZVMRP3EM5GB6X5BQZKF/action/replication_record"}},"created_at":"2026-07-05T08:25:50.214075+00:00","updated_at":"2026-07-05T08:25:50.214075+00:00"}