{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:BBO3JUSOXFAUIBBVRCNM2OMZ7V","short_pith_number":"pith:BBO3JUSO","canonical_record":{"source":{"id":"2102.02400","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T03:59:37Z","cross_cats_sorted":[],"title_canon_sha256":"aceb4efe3d481cec464d6074d049ad1243585821aec5c49b710bcfa08c10d42b","abstract_canon_sha256":"4ca7632a12cae4834985a847f15f328f277f54022e21d891f1c8fce8d3b08fca"},"schema_version":"1.0"},"canonical_sha256":"085db4d24eb941440435889acd3999fd46f080babbf760fc30b9e8c658d3cc0d","source":{"kind":"arxiv","id":"2102.02400","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02400","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02400v4","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02400","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"BBO3JUSOXFAU","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"BBO3JUSOXFAUIBBV","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"BBO3JUSO","created_at":"2026-07-05T03:24:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:BBO3JUSOXFAUIBBVRCNM2OMZ7V","target":"record","payload":{"canonical_record":{"source":{"id":"2102.02400","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T03:59:37Z","cross_cats_sorted":[],"title_canon_sha256":"aceb4efe3d481cec464d6074d049ad1243585821aec5c49b710bcfa08c10d42b","abstract_canon_sha256":"4ca7632a12cae4834985a847f15f328f277f54022e21d891f1c8fce8d3b08fca"},"schema_version":"1.0"},"canonical_sha256":"085db4d24eb941440435889acd3999fd46f080babbf760fc30b9e8c658d3cc0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:28.168596Z","signature_b64":"hDfCAPWiA8ROFiVk9lWF2VH9gl4SV8rFq6L41yEIQ+K7eduO2qVpqAMntEWgsocy/b7hdDSy1wyRmc9WyYcbAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"085db4d24eb941440435889acd3999fd46f080babbf760fc30b9e8c658d3cc0d","last_reissued_at":"2026-07-05T03:24:28.168088Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:28.168088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.02400","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GloccQbpo4u3OZGSPlpsfnmTSJ1wp1bf0JdZTC10TYWzpyql8hRKGWqIghE3CaCFWGqgYlnno2pFCxDcPZVxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:24:48.922012Z"},"content_sha256":"829454106c3a31dd057854a96c23448eba8f0d3bc288fcf1023d656ee9f0042c","schema_version":"1.0","event_id":"sha256:829454106c3a31dd057854a96c23448eba8f0d3bc288fcf1023d656ee9f0042c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:BBO3JUSOXFAUIBBVRCNM2OMZ7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Provably End-to-end Label-Noise Learning without Anchor Points","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Han, Gang Niu, Masashi Sugiyama, Tongliang Liu, Xuefeng Li","submitted_at":"2021-02-04T03:59:37Z","abstract_excerpt":"In label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers. Existing consistent estimators for the transition matrix have been developed by exploiting anchor points. However, the anchor-point assumption is not always satisfied in real scenarios. In this paper, we propose an end-to-end framework for solving label-noise learning without anchor points, in which we simultaneously optimize two objectives: the cross entropy loss between the noisy label and the predicted probability by the neural network, and the volume of the simplex formed by th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02400","kind":"arxiv","version":4},"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/2102.02400/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":"2026-07-05T03:24:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NPM5/r2zmQHBRggs4rKOdXee+Sm6+99oCsVuOZOE5TEmt3WL6XK4BSMZZChFZLdwN4PLhPHJVYIBCb6DXXgbDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T12:24:48.922404Z"},"content_sha256":"27d55abad40b4a77adeddd113c31a4fe96902b829382024147d64bdac7175ba8","schema_version":"1.0","event_id":"sha256:27d55abad40b4a77adeddd113c31a4fe96902b829382024147d64bdac7175ba8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V/bundle.json","state_url":"https://pith.science/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V/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":"2026-07-06T12:24:48Z","links":{"resolver":"https://pith.science/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V","bundle":"https://pith.science/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V/bundle.json","state":"https://pith.science/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BBO3JUSOXFAUIBBVRCNM2OMZ7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:BBO3JUSOXFAUIBBVRCNM2OMZ7V","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":"4ca7632a12cae4834985a847f15f328f277f54022e21d891f1c8fce8d3b08fca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T03:59:37Z","title_canon_sha256":"aceb4efe3d481cec464d6074d049ad1243585821aec5c49b710bcfa08c10d42b"},"schema_version":"1.0","source":{"id":"2102.02400","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.02400","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"arxiv_version","alias_value":"2102.02400v4","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.02400","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_12","alias_value":"BBO3JUSOXFAU","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_16","alias_value":"BBO3JUSOXFAUIBBV","created_at":"2026-07-05T03:24:28Z"},{"alias_kind":"pith_short_8","alias_value":"BBO3JUSO","created_at":"2026-07-05T03:24:28Z"}],"graph_snapshots":[{"event_id":"sha256:27d55abad40b4a77adeddd113c31a4fe96902b829382024147d64bdac7175ba8","target":"graph","created_at":"2026-07-05T03:24:28Z","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/2102.02400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In label-noise learning, the transition matrix plays a key role in building statistically consistent classifiers. Existing consistent estimators for the transition matrix have been developed by exploiting anchor points. However, the anchor-point assumption is not always satisfied in real scenarios. In this paper, we propose an end-to-end framework for solving label-noise learning without anchor points, in which we simultaneously optimize two objectives: the cross entropy loss between the noisy label and the predicted probability by the neural network, and the volume of the simplex formed by th","authors_text":"Bo Han, Gang Niu, Masashi Sugiyama, Tongliang Liu, Xuefeng Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T03:59:37Z","title":"Provably End-to-end Label-Noise Learning without Anchor Points"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.02400","kind":"arxiv","version":4},"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":"sha256:829454106c3a31dd057854a96c23448eba8f0d3bc288fcf1023d656ee9f0042c","target":"record","created_at":"2026-07-05T03:24:28Z","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":"4ca7632a12cae4834985a847f15f328f277f54022e21d891f1c8fce8d3b08fca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-04T03:59:37Z","title_canon_sha256":"aceb4efe3d481cec464d6074d049ad1243585821aec5c49b710bcfa08c10d42b"},"schema_version":"1.0","source":{"id":"2102.02400","kind":"arxiv","version":4}},"canonical_sha256":"085db4d24eb941440435889acd3999fd46f080babbf760fc30b9e8c658d3cc0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"085db4d24eb941440435889acd3999fd46f080babbf760fc30b9e8c658d3cc0d","first_computed_at":"2026-07-05T03:24:28.168088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:28.168088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hDfCAPWiA8ROFiVk9lWF2VH9gl4SV8rFq6L41yEIQ+K7eduO2qVpqAMntEWgsocy/b7hdDSy1wyRmc9WyYcbAA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:28.168596Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.02400","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:829454106c3a31dd057854a96c23448eba8f0d3bc288fcf1023d656ee9f0042c","sha256:27d55abad40b4a77adeddd113c31a4fe96902b829382024147d64bdac7175ba8"],"state_sha256":"2686fabe7d83d16957a6790c4e1336736fe989938ab0ffed5dceef3b9f00da3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ET6W19oT9jXsWMHEQDRkigs6D1LJCSl3Qo11VpLbZj1z2+UaBift+sDZyb2JJvpZtOPSu/4GVnrZ/UqY0OKACw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T12:24:48.924341Z","bundle_sha256":"e6f732ff124139b56a9efa6180a03238affb66b48560ad7b9aaa4946899fa0cf"}}