{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YQFHCGJSERZUYIA6K6T5BJLUWY","short_pith_number":"pith:YQFHCGJS","canonical_record":{"source":{"id":"2109.09191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-19T18:50:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a0cfda89141413986c4cd75c7788f620ce1d095e6412b3e6664772d62b45ea7","abstract_canon_sha256":"092ae7fbde3f2a8c726423820398168dae74bbea569c4cbc765a2a190b34ae1a"},"schema_version":"1.0"},"canonical_sha256":"c40a71193224734c201e57a7d0a574b61ddf1a048924b659d5d6040a567c74f4","source":{"kind":"arxiv","id":"2109.09191","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09191","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09191v1","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09191","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"YQFHCGJSERZU","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"YQFHCGJSERZUYIA6","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"YQFHCGJS","created_at":"2026-07-05T03:15:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YQFHCGJSERZUYIA6K6T5BJLUWY","target":"record","payload":{"canonical_record":{"source":{"id":"2109.09191","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-19T18:50:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5a0cfda89141413986c4cd75c7788f620ce1d095e6412b3e6664772d62b45ea7","abstract_canon_sha256":"092ae7fbde3f2a8c726423820398168dae74bbea569c4cbc765a2a190b34ae1a"},"schema_version":"1.0"},"canonical_sha256":"c40a71193224734c201e57a7d0a574b61ddf1a048924b659d5d6040a567c74f4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:42.541043Z","signature_b64":"CV5gIL0E2S/ET8UpDCHZEeSm30CcFEGSgyPcPWuMux+FrEhNwSXGddMBQ7uwAtzHxcadSdsMhkzMAKALj2UyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c40a71193224734c201e57a7d0a574b61ddf1a048924b659d5d6040a567c74f4","last_reissued_at":"2026-07-05T03:15:42.540551Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:42.540551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.09191","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":"2026-07-05T03:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w4tNmq/va5JQnvsBAtQN6GSuzKijwi3WAgA0Xax/8BVsPgv48zs5tywwrQ6vrfesqPEs+NR/a3r3kJVB8+rwDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:42:40.629207Z"},"content_sha256":"2d0ea04930ce8518111541aec66248149d30513a1ad0d3bdbf8b68958f13ce28","schema_version":"1.0","event_id":"sha256:2d0ea04930ce8518111541aec66248149d30513a1ad0d3bdbf8b68958f13ce28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YQFHCGJSERZUYIA6K6T5BJLUWY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Dynamic based data filtering may not work for NLP datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Arka Talukdar, Monika Dagar, Prachi Gupta, Varun Menon","submitted_at":"2021-09-19T18:50:45Z","abstract_excerpt":"The recent increase in dataset size has brought about significant advances in natural language understanding. These large datasets are usually collected through automation (search engines or web crawlers) or crowdsourcing which inherently introduces incorrectly labeled data. Training on these datasets leads to memorization and poor generalization. Thus, it is pertinent to develop techniques that help in the identification and isolation of mislabelled data. In this paper, we study the applicability of the Area Under the Margin (AUM) metric to identify and remove/rectify mislabelled examples in "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09191","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/2109.09191/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":"2026-07-05T03:15:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dBIlzSbbt47K+Mpt09AYUP3ey/wTXCODQTaPUfy6dlOSztrfC8U1vQG22nvIJeLHrePQizfXQs5KdyaG0qqpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:42:40.629595Z"},"content_sha256":"94b740979b24703526fc94773e77d18aef266ce873170552b7d925bc31801575","schema_version":"1.0","event_id":"sha256:94b740979b24703526fc94773e77d18aef266ce873170552b7d925bc31801575"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YQFHCGJSERZUYIA6K6T5BJLUWY/bundle.json","state_url":"https://pith.science/pith/YQFHCGJSERZUYIA6K6T5BJLUWY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YQFHCGJSERZUYIA6K6T5BJLUWY/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":"2026-08-22T20:42:40Z","links":{"resolver":"https://pith.science/pith/YQFHCGJSERZUYIA6K6T5BJLUWY","bundle":"https://pith.science/pith/YQFHCGJSERZUYIA6K6T5BJLUWY/bundle.json","state":"https://pith.science/pith/YQFHCGJSERZUYIA6K6T5BJLUWY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YQFHCGJSERZUYIA6K6T5BJLUWY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YQFHCGJSERZUYIA6K6T5BJLUWY","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":"092ae7fbde3f2a8c726423820398168dae74bbea569c4cbc765a2a190b34ae1a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-19T18:50:45Z","title_canon_sha256":"5a0cfda89141413986c4cd75c7788f620ce1d095e6412b3e6664772d62b45ea7"},"schema_version":"1.0","source":{"id":"2109.09191","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09191","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09191v1","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09191","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"pith_short_12","alias_value":"YQFHCGJSERZU","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"pith_short_16","alias_value":"YQFHCGJSERZUYIA6","created_at":"2026-07-05T03:15:42Z"},{"alias_kind":"pith_short_8","alias_value":"YQFHCGJS","created_at":"2026-07-05T03:15:42Z"}],"graph_snapshots":[{"event_id":"sha256:94b740979b24703526fc94773e77d18aef266ce873170552b7d925bc31801575","target":"graph","created_at":"2026-07-05T03:15:42Z","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/2109.09191/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent increase in dataset size has brought about significant advances in natural language understanding. These large datasets are usually collected through automation (search engines or web crawlers) or crowdsourcing which inherently introduces incorrectly labeled data. Training on these datasets leads to memorization and poor generalization. Thus, it is pertinent to develop techniques that help in the identification and isolation of mislabelled data. In this paper, we study the applicability of the Area Under the Margin (AUM) metric to identify and remove/rectify mislabelled examples in ","authors_text":"Arka Talukdar, Monika Dagar, Prachi Gupta, Varun Menon","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-19T18:50:45Z","title":"Training Dynamic based data filtering may not work for NLP datasets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09191","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":"sha256:2d0ea04930ce8518111541aec66248149d30513a1ad0d3bdbf8b68958f13ce28","target":"record","created_at":"2026-07-05T03:15:42Z","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":"092ae7fbde3f2a8c726423820398168dae74bbea569c4cbc765a2a190b34ae1a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-19T18:50:45Z","title_canon_sha256":"5a0cfda89141413986c4cd75c7788f620ce1d095e6412b3e6664772d62b45ea7"},"schema_version":"1.0","source":{"id":"2109.09191","kind":"arxiv","version":1}},"canonical_sha256":"c40a71193224734c201e57a7d0a574b61ddf1a048924b659d5d6040a567c74f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c40a71193224734c201e57a7d0a574b61ddf1a048924b659d5d6040a567c74f4","first_computed_at":"2026-07-05T03:15:42.540551Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:42.540551Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CV5gIL0E2S/ET8UpDCHZEeSm30CcFEGSgyPcPWuMux+FrEhNwSXGddMBQ7uwAtzHxcadSdsMhkzMAKALj2UyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:42.541043Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09191","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d0ea04930ce8518111541aec66248149d30513a1ad0d3bdbf8b68958f13ce28","sha256:94b740979b24703526fc94773e77d18aef266ce873170552b7d925bc31801575"],"state_sha256":"ca631b3031b8561c11408fdd313ee3eed7c3d961c747e362cc63ccae4a351413"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpnJ1sI9mCPXTZiBycwPQblWGp4Nb3IcTXCjgsaeYVsvAIod49fmuhsQTmsDqM8abW6sEyzy/nKM7bdhruinCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T20:42:40.633251Z","bundle_sha256":"2c8597e5326509507f606cc84aec7773b30d51b7b38f2242f743231aa7a241a9"}}