{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RZ36JKC4RCYF3FHAGMINTV7OEG","short_pith_number":"pith:RZ36JKC4","schema_version":"1.0","canonical_sha256":"8e77e4a85c88b05d94e03310d9d7ee21ab4b69c1b803e74202873c108bae4cd0","source":{"kind":"arxiv","id":"2402.17517","version":1},"attestation_state":"computed","paper":{"title":"Label-Noise Robust Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byeonghu Na, Heesun Bae, Il-Chul Moon, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, Yeongmin Kim","submitted_at":"2024-02-27T14:00:34Z","abstract_excerpt":"Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition mismatch and quality degradation of generated data. This paper proposes Transition-aware weighted Denoising Score Matching (TDSM) for training conditional diffusion models with noisy labels, which is the first study in the line of diffusion models. The TDSM objective contains a weighted sum of score networks, incorporating instance-wise and time-dependent lab"},"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":"2402.17517","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-27T14:00:34Z","cross_cats_sorted":[],"title_canon_sha256":"63564bdeb902843b4576dd5c5e283b7f1a431ab0c229df5a02c5e63ea6df760f","abstract_canon_sha256":"551e562d2456db502a8cd2ee026ada1a8dd0b142c57ce3c299e3543a543f6e5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:47.676809Z","signature_b64":"JKMfF75hpFnjDBffGapM7TzoF80afRBF8bVkLtxk22I8+NemUMcvhRDjX7AlRmojGhK5lga70x+iIrKBwVhUDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e77e4a85c88b05d94e03310d9d7ee21ab4b69c1b803e74202873c108bae4cd0","last_reissued_at":"2026-07-05T07:49:47.676311Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:47.676311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-Noise Robust Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byeonghu Na, Heesun Bae, Il-Chul Moon, Jung Hyun Lee, Se Jung Kwon, Wanmo Kang, Yeongmin Kim","submitted_at":"2024-02-27T14:00:34Z","abstract_excerpt":"Conditional diffusion models have shown remarkable performance in various generative tasks, but training them requires large-scale datasets that often contain noise in conditional inputs, a.k.a. noisy labels. This noise leads to condition mismatch and quality degradation of generated data. This paper proposes Transition-aware weighted Denoising Score Matching (TDSM) for training conditional diffusion models with noisy labels, which is the first study in the line of diffusion models. The TDSM objective contains a weighted sum of score networks, incorporating instance-wise and time-dependent lab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17517","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/2402.17517/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":"2402.17517","created_at":"2026-07-05T07:49:47.676382+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.17517v1","created_at":"2026-07-05T07:49:47.676382+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17517","created_at":"2026-07-05T07:49:47.676382+00:00"},{"alias_kind":"pith_short_12","alias_value":"RZ36JKC4RCYF","created_at":"2026-07-05T07:49:47.676382+00:00"},{"alias_kind":"pith_short_16","alias_value":"RZ36JKC4RCYF3FHA","created_at":"2026-07-05T07:49:47.676382+00:00"},{"alias_kind":"pith_short_8","alias_value":"RZ36JKC4","created_at":"2026-07-05T07:49:47.676382+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19629","citing_title":"RIVET: Robust Idempotent Voice Attribute Editing","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG","json":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG.json","graph_json":"https://pith.science/api/pith-number/RZ36JKC4RCYF3FHAGMINTV7OEG/graph.json","events_json":"https://pith.science/api/pith-number/RZ36JKC4RCYF3FHAGMINTV7OEG/events.json","paper":"https://pith.science/paper/RZ36JKC4"},"agent_actions":{"view_html":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG","download_json":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG.json","view_paper":"https://pith.science/paper/RZ36JKC4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.17517&json=true","fetch_graph":"https://pith.science/api/pith-number/RZ36JKC4RCYF3FHAGMINTV7OEG/graph.json","fetch_events":"https://pith.science/api/pith-number/RZ36JKC4RCYF3FHAGMINTV7OEG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG/action/storage_attestation","attest_author":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG/action/author_attestation","sign_citation":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG/action/citation_signature","submit_replication":"https://pith.science/pith/RZ36JKC4RCYF3FHAGMINTV7OEG/action/replication_record"}},"created_at":"2026-07-05T07:49:47.676382+00:00","updated_at":"2026-07-05T07:49:47.676382+00:00"}