{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:DQ5QWMHWYEITKTPQYAPUMEBNPG","short_pith_number":"pith:DQ5QWMHW","canonical_record":{"source":{"id":"2001.10528","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-28T18:59:03Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"12536308ac43596bb1bcb89fe50e6e2aa74ebeb3000f79602870dc44518f632d","abstract_canon_sha256":"347f459654b1ee396491adb9bf2c6e6f35422066e232a3fd0a568121093efbd1"},"schema_version":"1.0"},"canonical_sha256":"1c3b0b30f6c111354df0c01f46102d79af0269c5272f3743c4279ddf4650de1c","source":{"kind":"arxiv","id":"2001.10528","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.10528","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2001.10528v4","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10528","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"DQ5QWMHWYEIT","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"DQ5QWMHWYEITKTPQ","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"DQ5QWMHW","created_at":"2026-07-05T02:01:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:DQ5QWMHWYEITKTPQYAPUMEBNPG","target":"record","payload":{"canonical_record":{"source":{"id":"2001.10528","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-28T18:59:03Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"12536308ac43596bb1bcb89fe50e6e2aa74ebeb3000f79602870dc44518f632d","abstract_canon_sha256":"347f459654b1ee396491adb9bf2c6e6f35422066e232a3fd0a568121093efbd1"},"schema_version":"1.0"},"canonical_sha256":"1c3b0b30f6c111354df0c01f46102d79af0269c5272f3743c4279ddf4650de1c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:01:28.888578Z","signature_b64":"Ipwj0Pifql4FbUDxQBeW/owC0u6EwkKEwJj4fCNhCIhcs3q8H8zaj45jUnPnoNafWybk7IKErzNsDzqKNmE/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c3b0b30f6c111354df0c01f46102d79af0269c5272f3743c4279ddf4650de1c","last_reissued_at":"2026-07-05T02:01:28.888096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:01:28.888096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.10528","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":"2026-07-05T02:01:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aBvcoxd2IWfFmNTv9EgrffK7z1Yas1uED3d7qXj7+32p7NLYFFP+9NYNO3Kspq3lUfajKTCXI2vHjZ1zXAsaCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:14:29.053126Z"},"content_sha256":"745fdcf251d73b9476fffcc3b00b92533d7596bed191298e1e9d64dc52174fec","schema_version":"1.0","event_id":"sha256:745fdcf251d73b9476fffcc3b00b92533d7596bed191298e1e9d64dc52174fec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:DQ5QWMHWYEITKTPQYAPUMEBNPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Identifying Mislabeled Data using the Area Under the Margin Ranking","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ethan R. Elenberg, Geoff Pleiss, Kilian Q. Weinberger, Tianyi Zhang","submitted_at":"2020-01-28T18:59:03Z","abstract_excerpt":"Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural networks. At the heart of our algorithm is the Area Under the Margin (AUM) statistic, which exploits differences in the training dynamics of clean and mislabeled samples. A simple procedure - adding an extra class populated with purposefully mislabeled threshold samples - learns a AUM upper bound that isolates mislabeled data. This approach consistently improves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10528","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/2001.10528/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":"2026-07-05T02:01:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Vty/VXpgiFRHxY7R9i/al7LOrN1Ei1VQdQEGSdR0Qu1fLyf+5C5RAIMacJW+sZm7cxHWN6DkAlv1CAPrkhSAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T01:14:29.053662Z"},"content_sha256":"302067501421c6a57ee900dff565f58a688c50ee691e001d20e305758e481f55","schema_version":"1.0","event_id":"sha256:302067501421c6a57ee900dff565f58a688c50ee691e001d20e305758e481f55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG/bundle.json","state_url":"https://pith.science/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG/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":"2026-08-10T01:14:29Z","links":{"resolver":"https://pith.science/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG","bundle":"https://pith.science/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG/bundle.json","state":"https://pith.science/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DQ5QWMHWYEITKTPQYAPUMEBNPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:DQ5QWMHWYEITKTPQYAPUMEBNPG","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":"347f459654b1ee396491adb9bf2c6e6f35422066e232a3fd0a568121093efbd1","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-28T18:59:03Z","title_canon_sha256":"12536308ac43596bb1bcb89fe50e6e2aa74ebeb3000f79602870dc44518f632d"},"schema_version":"1.0","source":{"id":"2001.10528","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.10528","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2001.10528v4","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.10528","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"DQ5QWMHWYEIT","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"DQ5QWMHWYEITKTPQ","created_at":"2026-07-05T02:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"DQ5QWMHW","created_at":"2026-07-05T02:01:28Z"}],"graph_snapshots":[{"event_id":"sha256:302067501421c6a57ee900dff565f58a688c50ee691e001d20e305758e481f55","target":"graph","created_at":"2026-07-05T02:01:28Z","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/2001.10528/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Not all data in a typical training set help with generalization; some samples can be overly ambiguous or outrightly mislabeled. This paper introduces a new method to identify such samples and mitigate their impact when training neural networks. At the heart of our algorithm is the Area Under the Margin (AUM) statistic, which exploits differences in the training dynamics of clean and mislabeled samples. A simple procedure - adding an extra class populated with purposefully mislabeled threshold samples - learns a AUM upper bound that isolates mislabeled data. This approach consistently improves ","authors_text":"Ethan R. Elenberg, Geoff Pleiss, Kilian Q. Weinberger, Tianyi Zhang","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-28T18:59:03Z","title":"Identifying Mislabeled Data using the Area Under the Margin Ranking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.10528","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":"sha256:745fdcf251d73b9476fffcc3b00b92533d7596bed191298e1e9d64dc52174fec","target":"record","created_at":"2026-07-05T02:01:28Z","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":"347f459654b1ee396491adb9bf2c6e6f35422066e232a3fd0a568121093efbd1","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-01-28T18:59:03Z","title_canon_sha256":"12536308ac43596bb1bcb89fe50e6e2aa74ebeb3000f79602870dc44518f632d"},"schema_version":"1.0","source":{"id":"2001.10528","kind":"arxiv","version":4}},"canonical_sha256":"1c3b0b30f6c111354df0c01f46102d79af0269c5272f3743c4279ddf4650de1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c3b0b30f6c111354df0c01f46102d79af0269c5272f3743c4279ddf4650de1c","first_computed_at":"2026-07-05T02:01:28.888096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:01:28.888096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ipwj0Pifql4FbUDxQBeW/owC0u6EwkKEwJj4fCNhCIhcs3q8H8zaj45jUnPnoNafWybk7IKErzNsDzqKNmE/Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:01:28.888578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.10528","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:745fdcf251d73b9476fffcc3b00b92533d7596bed191298e1e9d64dc52174fec","sha256:302067501421c6a57ee900dff565f58a688c50ee691e001d20e305758e481f55"],"state_sha256":"09903f22a9794e2ef9c1e5726d9ad4022529af88114e2b497fae1d70103a1732"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5n9NGR0RagrlzEr5n7uysd1OqYRp5sBmQnqnvPEb+r2TV6IjIPsCinP+5wtM76Dq5z9gdtZ2nCAiFjC1P+yqDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T01:14:29.059412Z","bundle_sha256":"a1d1325111c9f66dbcce6c721fc91827d0cb62c6f1263de79821058112286890"}}