{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VJFTMZMCYP6Y5CFFUALPCTLKEZ","short_pith_number":"pith:VJFTMZMC","canonical_record":{"source":{"id":"2102.02414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-04T05:09:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94231ea93209dd1af2e704fe2b9bc2fb93b68c80e3cd86a35f3de11a64392bde","abstract_canon_sha256":"aeccf800297a980ba54f3cb363f661f73e2707c174b52b11a7357b28d8ef9aba"},"schema_version":"1.0"},"canonical_sha256":"aa4b366582c3fd8e88a5a016f14d6a2646b1dacd85d1f25a4b0b50094f36b419","source":{"kind":"arxiv","id":"2102.02414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02414","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02414v2","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02414","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"VJFTMZMCYP6Y","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"VJFTMZMCYP6Y5CFF","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"VJFTMZMC","created_at":"2026-07-05T02:48:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VJFTMZMCYP6Y5CFFUALPCTLKEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-04T05:09:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"94231ea93209dd1af2e704fe2b9bc2fb93b68c80e3cd86a35f3de11a64392bde","abstract_canon_sha256":"aeccf800297a980ba54f3cb363f661f73e2707c174b52b11a7357b28d8ef9aba"},"schema_version":"1.0"},"canonical_sha256":"aa4b366582c3fd8e88a5a016f14d6a2646b1dacd85d1f25a4b0b50094f36b419","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:59.406637Z","signature_b64":"1HrYlH7afEONhY1CLZFvLzCAVPdCfAWgoMb+Eim/Kyc+mxNgSgtDeHw7qEhZztth0FWe3Bq3RiMvPykuGpkTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa4b366582c3fd8e88a5a016f14d6a2646b1dacd85d1f25a4b0b50094f36b419","last_reissued_at":"2026-07-05T02:48:59.406132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:59.406132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02414","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":"2026-07-05T02:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fre0EFOTxfLClv+VzKOlufe/rXXVT7RuI7sWFHNz54X/VVX8da8TC9VX466OHfbgGN6kTO+4r69ydQgcnZADCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:00:46.287741Z"},"content_sha256":"5b6544d22ebd09f3839ac0c1486e60a083faa4c1bc2c71741ea27d1115231d75","schema_version":"1.0","event_id":"sha256:5b6544d22ebd09f3839ac0c1486e60a083faa4c1bc2c71741ea27d1115231d75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VJFTMZMCYP6Y5CFFUALPCTLKEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gang Niu, Masashi Sugiyama, Yivan Zhang","submitted_at":"2021-02-04T05:09:18Z","abstract_excerpt":"Many weakly supervised classification methods employ a noise transition matrix to capture the class-conditional label corruption. To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks. In this work, we propose a theoretically grounded method that can estimate the noise transition matrix and learn a classifier simultaneously, without relying on the error-prone noisy class-posterior estimation. Concretely, inspired by the characteristics of the stochastic label c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02414","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/2102.02414/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":"2026-07-05T02:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knRqPX43FbLhGJmTeJxRLp/+9Z2RvENFjp/ShPo/+NqbnvsPtz0Mj6p5dmd+HXy413aTzJEVnvlfOgPBHauoBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:00:46.288383Z"},"content_sha256":"a4e6cf5b166d8083bf1d98d0ef99cacb88e9bc6e13d12795ea77c9560cc72c77","schema_version":"1.0","event_id":"sha256:a4e6cf5b166d8083bf1d98d0ef99cacb88e9bc6e13d12795ea77c9560cc72c77"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ/bundle.json","state_url":"https://pith.science/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ/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":"2026-07-07T13:00:46Z","links":{"resolver":"https://pith.science/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ","bundle":"https://pith.science/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ/bundle.json","state":"https://pith.science/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJFTMZMCYP6Y5CFFUALPCTLKEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VJFTMZMCYP6Y5CFFUALPCTLKEZ","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":"aeccf800297a980ba54f3cb363f661f73e2707c174b52b11a7357b28d8ef9aba","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-04T05:09:18Z","title_canon_sha256":"94231ea93209dd1af2e704fe2b9bc2fb93b68c80e3cd86a35f3de11a64392bde"},"schema_version":"1.0","source":{"id":"2102.02414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02414","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02414v2","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02414","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"VJFTMZMCYP6Y","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"pith_short_16","alias_value":"VJFTMZMCYP6Y5CFF","created_at":"2026-07-05T02:48:59Z"},{"alias_kind":"pith_short_8","alias_value":"VJFTMZMC","created_at":"2026-07-05T02:48:59Z"}],"graph_snapshots":[{"event_id":"sha256:a4e6cf5b166d8083bf1d98d0ef99cacb88e9bc6e13d12795ea77c9560cc72c77","target":"graph","created_at":"2026-07-05T02:48:59Z","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/2102.02414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many weakly supervised classification methods employ a noise transition matrix to capture the class-conditional label corruption. To estimate the transition matrix from noisy data, existing methods often need to estimate the noisy class-posterior, which could be unreliable due to the overconfidence of neural networks. In this work, we propose a theoretically grounded method that can estimate the noise transition matrix and learn a classifier simultaneously, without relying on the error-prone noisy class-posterior estimation. Concretely, inspired by the characteristics of the stochastic label c","authors_text":"Gang Niu, Masashi Sugiyama, Yivan Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-04T05:09:18Z","title":"Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02414","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":"sha256:5b6544d22ebd09f3839ac0c1486e60a083faa4c1bc2c71741ea27d1115231d75","target":"record","created_at":"2026-07-05T02:48:59Z","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":"aeccf800297a980ba54f3cb363f661f73e2707c174b52b11a7357b28d8ef9aba","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-02-04T05:09:18Z","title_canon_sha256":"94231ea93209dd1af2e704fe2b9bc2fb93b68c80e3cd86a35f3de11a64392bde"},"schema_version":"1.0","source":{"id":"2102.02414","kind":"arxiv","version":2}},"canonical_sha256":"aa4b366582c3fd8e88a5a016f14d6a2646b1dacd85d1f25a4b0b50094f36b419","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa4b366582c3fd8e88a5a016f14d6a2646b1dacd85d1f25a4b0b50094f36b419","first_computed_at":"2026-07-05T02:48:59.406132Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:48:59.406132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1HrYlH7afEONhY1CLZFvLzCAVPdCfAWgoMb+Eim/Kyc+mxNgSgtDeHw7qEhZztth0FWe3Bq3RiMvPykuGpkTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:48:59.406637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5b6544d22ebd09f3839ac0c1486e60a083faa4c1bc2c71741ea27d1115231d75","sha256:a4e6cf5b166d8083bf1d98d0ef99cacb88e9bc6e13d12795ea77c9560cc72c77"],"state_sha256":"fbd7ef3751854415c17a61b5b7e2c31a5b9a89321031062db3eb06e5fbafd852"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i426nwdfaFXsW5w/lOCKXibrhKvgdx7lLSlpum39WgsNfaBsAb8vXwFu64dZ+XKHrgi5mJetBihIwgX6ugdyAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:00:46.291052Z","bundle_sha256":"3b8ff6cd0305eba791b06b7c8a67880a616d9f30cd7d9ceeaa3a2b274d4f53dc"}}