{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZUNFIEIAQLZSYM56DPZKTM4XQO","short_pith_number":"pith:ZUNFIEIA","schema_version":"1.0","canonical_sha256":"cd1a54110082f32c33be1bf2a9b39783af3a0963335556dbef0c41d094f5c4a6","source":{"kind":"arxiv","id":"2402.03845","version":1},"attestation_state":"computed","paper":{"title":"On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Horvat, Jean-Pascal Pfister","submitted_at":"2024-02-06T09:41:43Z","abstract_excerpt":"Diffusion models are generative models that have recently demonstrated impressive performances in terms of sampling quality and density estimation in high dimensions. They rely on a forward continuous diffusion process and a backward continuous denoising process, which can be described by a time-dependent vector field and is used as a generative model. In the original formulation of the diffusion model, this vector field is assumed to be the score function (i.e. it is the gradient of the log-probability at a given time in the diffusion process). Curiously, on the practical side, most studies o"},"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":"2402.03845","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-06T09:41:43Z","cross_cats_sorted":[],"title_canon_sha256":"c522b32177d05709bed5019b5619d20cc668308b80a80e2df375cf00c48554e2","abstract_canon_sha256":"c6e681a5bf41d17225b60ddd29c88c89df6554a186c41593466b61c78eef7157"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:59.485836Z","signature_b64":"9+Wdiq2u6pSatb448LtrDw6l3fVxcA5ZUR2NGmmmWaVBr0LK8ZEWEvxBRUzTUARX2MLrWb7hscQeLHooltImDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cd1a54110082f32c33be1bf2a9b39783af3a0963335556dbef0c41d094f5c4a6","last_reissued_at":"2026-07-05T07:41:59.485400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:59.485400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Christian Horvat, Jean-Pascal Pfister","submitted_at":"2024-02-06T09:41:43Z","abstract_excerpt":"Diffusion models are generative models that have recently demonstrated impressive performances in terms of sampling quality and density estimation in high dimensions. They rely on a forward continuous diffusion process and a backward continuous denoising process, which can be described by a time-dependent vector field and is used as a generative model. In the original formulation of the diffusion model, this vector field is assumed to be the score function (i.e. it is the gradient of the log-probability at a given time in the diffusion process). Curiously, on the practical side, most studies o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03845","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/2402.03845/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":"2402.03845","created_at":"2026-07-05T07:41:59.485458+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03845v1","created_at":"2026-07-05T07:41:59.485458+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03845","created_at":"2026-07-05T07:41:59.485458+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZUNFIEIAQLZS","created_at":"2026-07-05T07:41:59.485458+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZUNFIEIAQLZSYM56","created_at":"2026-07-05T07:41:59.485458+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZUNFIEIA","created_at":"2026-07-05T07:41:59.485458+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.16768","citing_title":"On The Hidden Biases of Flow Matching Samplers","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07319","citing_title":"Generative Modeling with Flux Matching","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO","json":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO.json","graph_json":"https://pith.science/api/pith-number/ZUNFIEIAQLZSYM56DPZKTM4XQO/graph.json","events_json":"https://pith.science/api/pith-number/ZUNFIEIAQLZSYM56DPZKTM4XQO/events.json","paper":"https://pith.science/paper/ZUNFIEIA"},"agent_actions":{"view_html":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO","download_json":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO.json","view_paper":"https://pith.science/paper/ZUNFIEIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03845&json=true","fetch_graph":"https://pith.science/api/pith-number/ZUNFIEIAQLZSYM56DPZKTM4XQO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZUNFIEIAQLZSYM56DPZKTM4XQO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO/action/storage_attestation","attest_author":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO/action/author_attestation","sign_citation":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO/action/citation_signature","submit_replication":"https://pith.science/pith/ZUNFIEIAQLZSYM56DPZKTM4XQO/action/replication_record"}},"created_at":"2026-07-05T07:41:59.485458+00:00","updated_at":"2026-07-05T07:41:59.485458+00:00"}