{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:B37EBAFUQ3UYNWTX6G642ZY4ZS","short_pith_number":"pith:B37EBAFU","canonical_record":{"source":{"id":"2305.19518","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T03:01:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1094baf270551c92ebb74a1967df7f3d5fb3da965288157ef0f49e8d88e74205","abstract_canon_sha256":"3281066da4d4626f3ac37584b7e2c8a2c70a73d5223a97d5b50ca368590f4048"},"schema_version":"1.0"},"canonical_sha256":"0efe4080b486e986da77f1bdcd671ccc81b68bfd8cc84c09d311b4743746618a","source":{"kind":"arxiv","id":"2305.19518","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19518","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19518v2","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19518","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"B37EBAFUQ3UY","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"B37EBAFUQ3UYNWTX","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"B37EBAFU","created_at":"2026-07-05T07:19:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:B37EBAFUQ3UYNWTX6G642ZY4ZS","target":"record","payload":{"canonical_record":{"source":{"id":"2305.19518","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T03:01:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1094baf270551c92ebb74a1967df7f3d5fb3da965288157ef0f49e8d88e74205","abstract_canon_sha256":"3281066da4d4626f3ac37584b7e2c8a2c70a73d5223a97d5b50ca368590f4048"},"schema_version":"1.0"},"canonical_sha256":"0efe4080b486e986da77f1bdcd671ccc81b68bfd8cc84c09d311b4743746618a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:20.178155Z","signature_b64":"PGrnS4phiJNWWcL1PEHQbFcVixES/OPyfHU3utN8zdwJKarAYXd43Ll/1Bsh0J7W/nboYdJoCjDA7nfErnnACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0efe4080b486e986da77f1bdcd671ccc81b68bfd8cc84c09d311b4743746618a","last_reissued_at":"2026-07-05T07:19:20.177616Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:20.177616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.19518","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YD2o90yCQaxziVgrBM6ifMt+0rq2MENGfya5kJFp+Q9HsTqpVasv2SJL4QOXA55ff9AQEJ5Ewl9Ih+ep2srDAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:20:17.988471Z"},"content_sha256":"cc25d9c0871a6552032af802124490a6f92fd80c4648d5aa6ee3eabc7915d394","schema_version":"1.0","event_id":"sha256:cc25d9c0871a6552032af802124490a6f92fd80c4648d5aa6ee3eabc7915d394"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:B37EBAFUQ3UYNWTX6G642ZY4ZS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Changyou Chen, Jian Chen, Rohan Sharma, Ruiyi Zhang, Tong Sun, Tong Yu, Zhiqiang Xu","submitted_at":"2023-05-31T03:01:36Z","abstract_excerpt":"Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, $\\textit{i.e.}$, labels are generated by gradually refining an initial random guess. This new perspective immediately enables existing powerful diffusion models to seamlessly learn the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19518","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/2305.19518/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:19:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lBxxOqwT10x2z8yDA4cieNZJKRlVxsI+/L3fPuPOnjRVm83m8DtcyclWS3Mo3fWE8he607vjX71SYd4wklCGBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T23:20:17.989430Z"},"content_sha256":"71afce1a7b2e86048f43ffe2e51936343ee755fffa6ece1a9cb38d5418043e1e","schema_version":"1.0","event_id":"sha256:71afce1a7b2e86048f43ffe2e51936343ee755fffa6ece1a9cb38d5418043e1e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS/bundle.json","state_url":"https://pith.science/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T23:20:17Z","links":{"resolver":"https://pith.science/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS","bundle":"https://pith.science/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS/bundle.json","state":"https://pith.science/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B37EBAFUQ3UYNWTX6G642ZY4ZS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:B37EBAFUQ3UYNWTX6G642ZY4ZS","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"3281066da4d4626f3ac37584b7e2c8a2c70a73d5223a97d5b50ca368590f4048","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T03:01:36Z","title_canon_sha256":"1094baf270551c92ebb74a1967df7f3d5fb3da965288157ef0f49e8d88e74205"},"schema_version":"1.0","source":{"id":"2305.19518","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.19518","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"arxiv_version","alias_value":"2305.19518v2","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.19518","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"pith_short_12","alias_value":"B37EBAFUQ3UY","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"pith_short_16","alias_value":"B37EBAFUQ3UYNWTX","created_at":"2026-07-05T07:19:20Z"},{"alias_kind":"pith_short_8","alias_value":"B37EBAFU","created_at":"2026-07-05T07:19:20Z"}],"graph_snapshots":[{"event_id":"sha256:71afce1a7b2e86048f43ffe2e51936343ee755fffa6ece1a9cb38d5418043e1e","target":"graph","created_at":"2026-07-05T07:19:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.19518/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning from noisy labels is an important and long-standing problem in machine learning for real applications. One of the main research lines focuses on learning a label corrector to purify potential noisy labels. However, these methods typically rely on strict assumptions and are limited to certain types of label noise. In this paper, we reformulate the label-noise problem from a generative-model perspective, $\\textit{i.e.}$, labels are generated by gradually refining an initial random guess. This new perspective immediately enables existing powerful diffusion models to seamlessly learn the ","authors_text":"Changyou Chen, Jian Chen, Rohan Sharma, Ruiyi Zhang, Tong Sun, Tong Yu, Zhiqiang Xu","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T03:01:36Z","title":"Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.19518","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:cc25d9c0871a6552032af802124490a6f92fd80c4648d5aa6ee3eabc7915d394","target":"record","created_at":"2026-07-05T07:19:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"3281066da4d4626f3ac37584b7e2c8a2c70a73d5223a97d5b50ca368590f4048","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-31T03:01:36Z","title_canon_sha256":"1094baf270551c92ebb74a1967df7f3d5fb3da965288157ef0f49e8d88e74205"},"schema_version":"1.0","source":{"id":"2305.19518","kind":"arxiv","version":2}},"canonical_sha256":"0efe4080b486e986da77f1bdcd671ccc81b68bfd8cc84c09d311b4743746618a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0efe4080b486e986da77f1bdcd671ccc81b68bfd8cc84c09d311b4743746618a","first_computed_at":"2026-07-05T07:19:20.177616Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:19:20.177616Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PGrnS4phiJNWWcL1PEHQbFcVixES/OPyfHU3utN8zdwJKarAYXd43Ll/1Bsh0J7W/nboYdJoCjDA7nfErnnACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:19:20.178155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.19518","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cc25d9c0871a6552032af802124490a6f92fd80c4648d5aa6ee3eabc7915d394","sha256:71afce1a7b2e86048f43ffe2e51936343ee755fffa6ece1a9cb38d5418043e1e"],"state_sha256":"11635df1b78bc432a19aad57e69e5c63fee1edbf191e9afe5dc77d36fdabcd18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5noEvqLL2ATufwhU851Gcrekj4yzCKOXSsAR8WFQxUrDS4jHgTT+Vj03xb94b5FX2Kb6af8kfkudqarLWBJ/Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T23:20:17.995262Z","bundle_sha256":"e7455a49b8741b74da4640cecb32fffc8b2b82cc07d9534483f4b60b65fe8459"}}