{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YCA4X7754PP5YI6BLLI53KYGVB","short_pith_number":"pith:YCA4X775","schema_version":"1.0","canonical_sha256":"c081cbfffde3dfdc23c15ad1ddab06a85df3d8532211c52e96fcca9b6c652daf","source":{"kind":"arxiv","id":"2304.05364","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Models for Constrained Domains","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emile Mathieu, Leo Klarner, Michael Hutchinson, Nic Fishman, Valentin De Bortoli","submitted_at":"2023-04-11T17:19:45Z","abstract_excerpt":"Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-image tasks. Building on this success, diffusion models have recently been extended to the Riemannian manifold setting, broadening their applicability to a range of problems from the natural and engineering sciences. However, these Riemannian diffusion models are built on the assumption that their forward and backward processes are well-defined for all times, preventing them from being applied to an important set of ta"},"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":"2304.05364","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-11T17:19:45Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a3f9915fd80a0cce244d39bb3651e92f1045955835e443a06d8873e9f5a31b1c","abstract_canon_sha256":"519fd4c57f83c887e646bcf2181d6a2c638491398311eeb4737f18ab614ae5f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:07.948167Z","signature_b64":"xXcBEDJCn66jEnasuBfT9BDtzfetKKT0ZTVGsyshTZ0I1MtLoaI1omtBr9ZefeCOIPIASdbQwiF6yglgxoNeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c081cbfffde3dfdc23c15ad1ddab06a85df3d8532211c52e96fcca9b6c652daf","last_reissued_at":"2026-07-05T07:53:07.947721Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:07.947721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Models for Constrained Domains","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Emile Mathieu, Leo Klarner, Michael Hutchinson, Nic Fishman, Valentin De Bortoli","submitted_at":"2023-04-11T17:19:45Z","abstract_excerpt":"Denoising diffusion models are a novel class of generative algorithms that achieve state-of-the-art performance across a range of domains, including image generation and text-to-image tasks. Building on this success, diffusion models have recently been extended to the Riemannian manifold setting, broadening their applicability to a range of problems from the natural and engineering sciences. However, these Riemannian diffusion models are built on the assumption that their forward and backward processes are well-defined for all times, preventing them from being applied to an important set of ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.05364","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/2304.05364/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":"2304.05364","created_at":"2026-07-05T07:53:07.947780+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.05364v2","created_at":"2026-07-05T07:53:07.947780+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.05364","created_at":"2026-07-05T07:53:07.947780+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCA4X7754PP5","created_at":"2026-07-05T07:53:07.947780+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCA4X7754PP5YI6B","created_at":"2026-07-05T07:53:07.947780+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCA4X775","created_at":"2026-07-05T07:53:07.947780+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07232","citing_title":"DiPhon: Diffusion on Graphons for Scalable Graph Generation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08058","citing_title":"Picasso: Holistic Scene Reconstruction with Physics-Constrained Sampling","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12813","citing_title":"REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations","ref_index":162,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB","json":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB.json","graph_json":"https://pith.science/api/pith-number/YCA4X7754PP5YI6BLLI53KYGVB/graph.json","events_json":"https://pith.science/api/pith-number/YCA4X7754PP5YI6BLLI53KYGVB/events.json","paper":"https://pith.science/paper/YCA4X775"},"agent_actions":{"view_html":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB","download_json":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB.json","view_paper":"https://pith.science/paper/YCA4X775","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.05364&json=true","fetch_graph":"https://pith.science/api/pith-number/YCA4X7754PP5YI6BLLI53KYGVB/graph.json","fetch_events":"https://pith.science/api/pith-number/YCA4X7754PP5YI6BLLI53KYGVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB/action/storage_attestation","attest_author":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB/action/author_attestation","sign_citation":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB/action/citation_signature","submit_replication":"https://pith.science/pith/YCA4X7754PP5YI6BLLI53KYGVB/action/replication_record"}},"created_at":"2026-07-05T07:53:07.947780+00:00","updated_at":"2026-07-05T07:53:07.947780+00:00"}