{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BDGWJ273LEUBF4LI5IS7Z4ONXA","short_pith_number":"pith:BDGWJ273","canonical_record":{"source":{"id":"2103.12814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T20:00:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b9292dcb23925469ea2d758d11dfc0f6bc4a6d3f8d141bfd81fa5fa8dde4e68b","abstract_canon_sha256":"7f32969a90623f2fa0bb8a7a2ecba7c45c5b0a30c96d7303e06570166e5701d3"},"schema_version":"1.0"},"canonical_sha256":"08cd64ebfb592812f168ea25fcf1cdb802ec5af8f0c4f75afff1718f43f7c6ce","source":{"kind":"arxiv","id":"2103.12814","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12814","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12814v1","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12814","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"pith_short_12","alias_value":"BDGWJ273LEUB","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"pith_short_16","alias_value":"BDGWJ273LEUBF4LI","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"pith_short_8","alias_value":"BDGWJ273","created_at":"2026-07-05T02:25:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BDGWJ273LEUBF4LI5IS7Z4ONXA","target":"record","payload":{"canonical_record":{"source":{"id":"2103.12814","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T20:00:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b9292dcb23925469ea2d758d11dfc0f6bc4a6d3f8d141bfd81fa5fa8dde4e68b","abstract_canon_sha256":"7f32969a90623f2fa0bb8a7a2ecba7c45c5b0a30c96d7303e06570166e5701d3"},"schema_version":"1.0"},"canonical_sha256":"08cd64ebfb592812f168ea25fcf1cdb802ec5af8f0c4f75afff1718f43f7c6ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:25:52.078143Z","signature_b64":"e23ZwJfCRrY0hiqca4jJMs4PbvamakFqu7nM6zGBeyl6vmQIzXQ2F9m4IyWe0s4fHkjg97fxcqMpy01OByU3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08cd64ebfb592812f168ea25fcf1cdb802ec5af8f0c4f75afff1718f43f7c6ce","last_reissued_at":"2026-07-05T02:25:52.077642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:25:52.077642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.12814","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:25:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uRKaAWr+la3WkU4oI2TUOX2yPD1jNVn0kxSIZVvYznkwofCc42VtO/ZQiE1u3ewV05cb4I+g8Tac03qH4VP1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:26:09.698624Z"},"content_sha256":"50728dc286b4a985b58d1387f925e4b945a8bca423494dadc942752a4625956c","schema_version":"1.0","event_id":"sha256:50728dc286b4a985b58d1387f925e4b945a8bca423494dadc942752a4625956c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BDGWJ273LEUBF4LI5IS7Z4ONXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Co-matching: Combating Noisy Labels by Augmentation Anchoring","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Wenbo He, Yang Bo, Yangdi Lu","submitted_at":"2021-03-23T20:00:13Z","abstract_excerpt":"Deep learning with noisy labels is challenging as deep neural networks have the high capacity to memorize the noisy labels. In this paper, we propose a learning algorithm called Co-matching, which balances the consistency and divergence between two networks by augmentation anchoring. Specifically, we have one network generate anchoring label from its prediction on a weakly-augmented image. Meanwhile, we force its peer network, taking the strongly-augmented version of the same image as input, to generate prediction close to the anchoring label. We then update two networks simultaneously by sele"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12814","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/2103.12814/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":"2026-07-05T02:25:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"quw2+F8M/nmv1jOBtf3i8gbN5mhWR47DvTho2Anh3SQ4ThVBo2fOs3FPwBifqGN0SZBJpG2YE80ABDL+UMpJBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T14:26:09.699245Z"},"content_sha256":"5120561e1f3714595678ea78a1bae558b9c6866dc0fbfe1ba8a8b00f9020f411","schema_version":"1.0","event_id":"sha256:5120561e1f3714595678ea78a1bae558b9c6866dc0fbfe1ba8a8b00f9020f411"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA/bundle.json","state_url":"https://pith.science/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA/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":"2026-07-31T14:26:09Z","links":{"resolver":"https://pith.science/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA","bundle":"https://pith.science/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA/bundle.json","state":"https://pith.science/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BDGWJ273LEUBF4LI5IS7Z4ONXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BDGWJ273LEUBF4LI5IS7Z4ONXA","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":"7f32969a90623f2fa0bb8a7a2ecba7c45c5b0a30c96d7303e06570166e5701d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T20:00:13Z","title_canon_sha256":"b9292dcb23925469ea2d758d11dfc0f6bc4a6d3f8d141bfd81fa5fa8dde4e68b"},"schema_version":"1.0","source":{"id":"2103.12814","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.12814","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"arxiv_version","alias_value":"2103.12814v1","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.12814","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"pith_short_12","alias_value":"BDGWJ273LEUB","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"pith_short_16","alias_value":"BDGWJ273LEUBF4LI","created_at":"2026-07-05T02:25:52Z"},{"alias_kind":"pith_short_8","alias_value":"BDGWJ273","created_at":"2026-07-05T02:25:52Z"}],"graph_snapshots":[{"event_id":"sha256:5120561e1f3714595678ea78a1bae558b9c6866dc0fbfe1ba8a8b00f9020f411","target":"graph","created_at":"2026-07-05T02:25:52Z","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/2103.12814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep learning with noisy labels is challenging as deep neural networks have the high capacity to memorize the noisy labels. In this paper, we propose a learning algorithm called Co-matching, which balances the consistency and divergence between two networks by augmentation anchoring. Specifically, we have one network generate anchoring label from its prediction on a weakly-augmented image. Meanwhile, we force its peer network, taking the strongly-augmented version of the same image as input, to generate prediction close to the anchoring label. We then update two networks simultaneously by sele","authors_text":"Wenbo He, Yang Bo, Yangdi Lu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T20:00:13Z","title":"Co-matching: Combating Noisy Labels by Augmentation Anchoring"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.12814","kind":"arxiv","version":1},"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":"sha256:50728dc286b4a985b58d1387f925e4b945a8bca423494dadc942752a4625956c","target":"record","created_at":"2026-07-05T02:25:52Z","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":"7f32969a90623f2fa0bb8a7a2ecba7c45c5b0a30c96d7303e06570166e5701d3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-23T20:00:13Z","title_canon_sha256":"b9292dcb23925469ea2d758d11dfc0f6bc4a6d3f8d141bfd81fa5fa8dde4e68b"},"schema_version":"1.0","source":{"id":"2103.12814","kind":"arxiv","version":1}},"canonical_sha256":"08cd64ebfb592812f168ea25fcf1cdb802ec5af8f0c4f75afff1718f43f7c6ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08cd64ebfb592812f168ea25fcf1cdb802ec5af8f0c4f75afff1718f43f7c6ce","first_computed_at":"2026-07-05T02:25:52.077642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:25:52.077642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e23ZwJfCRrY0hiqca4jJMs4PbvamakFqu7nM6zGBeyl6vmQIzXQ2F9m4IyWe0s4fHkjg97fxcqMpy01OByU3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:25:52.078143Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.12814","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50728dc286b4a985b58d1387f925e4b945a8bca423494dadc942752a4625956c","sha256:5120561e1f3714595678ea78a1bae558b9c6866dc0fbfe1ba8a8b00f9020f411"],"state_sha256":"c3981e4bceecfa97084954668812d0a6365c287f81426fdbec07c3e876186a15"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ppS9Old0PRhEm59+cMQfdNAwYiwZutgi1fg1ihhi2f+ag9nW4Uov4v0YMhPHNSGDzZVQqRq3g0jgN5Oyppr0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T14:26:09.705209Z","bundle_sha256":"7b24db921e2263f84d61982372e5b218a8f818fbb9856f4391bd7e35a4ea9024"}}