{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5QL2JIKX6QUX2V4544QVIIMOW2","short_pith_number":"pith:5QL2JIKX","canonical_record":{"source":{"id":"2109.00574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-01T19:03:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fe0e8b77b51c7a8805d4395f8ca3ae6dbc97efcff5c5d90e4b7077af5e10a07","abstract_canon_sha256":"7508c3dcaaa3819053232f2792e50fa9374974557d5b7b086417f623d0df9c58"},"schema_version":"1.0"},"canonical_sha256":"ec17a4a157f4297d579de72154218eb6b1e7953388dd7032344e0ae99aaf0cba","source":{"kind":"arxiv","id":"2109.00574","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00574","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00574v2","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00574","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"5QL2JIKX6QUX","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"5QL2JIKX6QUX2V45","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"5QL2JIKX","created_at":"2026-07-05T04:16:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5QL2JIKX6QUX2V4544QVIIMOW2","target":"record","payload":{"canonical_record":{"source":{"id":"2109.00574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-01T19:03:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5fe0e8b77b51c7a8805d4395f8ca3ae6dbc97efcff5c5d90e4b7077af5e10a07","abstract_canon_sha256":"7508c3dcaaa3819053232f2792e50fa9374974557d5b7b086417f623d0df9c58"},"schema_version":"1.0"},"canonical_sha256":"ec17a4a157f4297d579de72154218eb6b1e7953388dd7032344e0ae99aaf0cba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:16:52.611690Z","signature_b64":"wcrphlZtWuBVhm0iqZWVh3uIdoq85vqB+AS+7Xv1YTntmV0q5jkDCglFznOwwQHQjs71cBUsBZl2HcRG6GK8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec17a4a157f4297d579de72154218eb6b1e7953388dd7032344e0ae99aaf0cba","last_reissued_at":"2026-07-05T04:16:52.611184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:16:52.611184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.00574","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":"2026-07-05T04:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SuCRYR/uEHsME3rGCNR0c8kaBlcXS96HIDp+bh1DMrg/1+QKxjzxs9f2X83B6U3kQs+e0cvMQIOPbM1F8WteBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:24:38.482213Z"},"content_sha256":"9258a6394998dade700ee034ffbf5ce372d0d93e33c56f6df50bb063a629daf4","schema_version":"1.0","event_id":"sha256:9258a6394998dade700ee034ffbf5ce372d0d93e33c56f6df50bb063a629daf4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5QL2JIKX6QUX2V4544QVIIMOW2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Active label cleaning for improved dataset quality under resource constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aditya Nori, Anton Schwaighofer, Ben Glocker, Daniel C. Castro, Javier Alvarez-Valle, Kerem C. Tezcan, Matthew Lungren, Melanie Bernhardt, Miguel Monteiro, Ozan Oktay, Ryutaro Tanno, Shruthi Bannur","submitted_at":"2021-09-01T19:03:57Z","abstract_excerpt":"Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to remove label noise by fully re-annotating large datasets is infeasible in resource-constrained settings, such as healthcare. This work advocates for a data-driven approach to prioritising samples for re-annotation - which we term \"active label cleaning\". We propose to rank instances according to estimated label correctness and labelling difficulty of each samp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00574","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/2109.00574/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":"2026-07-05T04:16:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U40ybv3tnoCeiFVBeYQkuC3j1+eCZb9QYusxoypvyU8evZj8Cjw+zKCEhNEX9WgrSa9oZoefe110xzcb2D9dBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T19:24:38.482837Z"},"content_sha256":"cc443419cb1f2da9a9dfab94b364d60ad02d232c1413777e74928339a7d8443d","schema_version":"1.0","event_id":"sha256:cc443419cb1f2da9a9dfab94b364d60ad02d232c1413777e74928339a7d8443d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5QL2JIKX6QUX2V4544QVIIMOW2/bundle.json","state_url":"https://pith.science/pith/5QL2JIKX6QUX2V4544QVIIMOW2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5QL2JIKX6QUX2V4544QVIIMOW2/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":"2026-08-18T19:24:38Z","links":{"resolver":"https://pith.science/pith/5QL2JIKX6QUX2V4544QVIIMOW2","bundle":"https://pith.science/pith/5QL2JIKX6QUX2V4544QVIIMOW2/bundle.json","state":"https://pith.science/pith/5QL2JIKX6QUX2V4544QVIIMOW2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5QL2JIKX6QUX2V4544QVIIMOW2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5QL2JIKX6QUX2V4544QVIIMOW2","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":"7508c3dcaaa3819053232f2792e50fa9374974557d5b7b086417f623d0df9c58","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-01T19:03:57Z","title_canon_sha256":"5fe0e8b77b51c7a8805d4395f8ca3ae6dbc97efcff5c5d90e4b7077af5e10a07"},"schema_version":"1.0","source":{"id":"2109.00574","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.00574","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"arxiv_version","alias_value":"2109.00574v2","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.00574","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"pith_short_12","alias_value":"5QL2JIKX6QUX","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"pith_short_16","alias_value":"5QL2JIKX6QUX2V45","created_at":"2026-07-05T04:16:52Z"},{"alias_kind":"pith_short_8","alias_value":"5QL2JIKX","created_at":"2026-07-05T04:16:52Z"}],"graph_snapshots":[{"event_id":"sha256:cc443419cb1f2da9a9dfab94b364d60ad02d232c1413777e74928339a7d8443d","target":"graph","created_at":"2026-07-05T04:16:52Z","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/2109.00574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Imperfections in data annotation, known as label noise, are detrimental to the training of machine learning models and have an often-overlooked confounding effect on the assessment of model performance. Nevertheless, employing experts to remove label noise by fully re-annotating large datasets is infeasible in resource-constrained settings, such as healthcare. This work advocates for a data-driven approach to prioritising samples for re-annotation - which we term \"active label cleaning\". We propose to rank instances according to estimated label correctness and labelling difficulty of each samp","authors_text":"Aditya Nori, Anton Schwaighofer, Ben Glocker, Daniel C. Castro, Javier Alvarez-Valle, Kerem C. Tezcan, Matthew Lungren, Melanie Bernhardt, Miguel Monteiro, Ozan Oktay, Ryutaro Tanno, Shruthi Bannur","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-01T19:03:57Z","title":"Active label cleaning for improved dataset quality under resource constraints"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.00574","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":"sha256:9258a6394998dade700ee034ffbf5ce372d0d93e33c56f6df50bb063a629daf4","target":"record","created_at":"2026-07-05T04:16:52Z","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":"7508c3dcaaa3819053232f2792e50fa9374974557d5b7b086417f623d0df9c58","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-09-01T19:03:57Z","title_canon_sha256":"5fe0e8b77b51c7a8805d4395f8ca3ae6dbc97efcff5c5d90e4b7077af5e10a07"},"schema_version":"1.0","source":{"id":"2109.00574","kind":"arxiv","version":2}},"canonical_sha256":"ec17a4a157f4297d579de72154218eb6b1e7953388dd7032344e0ae99aaf0cba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec17a4a157f4297d579de72154218eb6b1e7953388dd7032344e0ae99aaf0cba","first_computed_at":"2026-07-05T04:16:52.611184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:16:52.611184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wcrphlZtWuBVhm0iqZWVh3uIdoq85vqB+AS+7Xv1YTntmV0q5jkDCglFznOwwQHQjs71cBUsBZl2HcRG6GK8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:16:52.611690Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.00574","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9258a6394998dade700ee034ffbf5ce372d0d93e33c56f6df50bb063a629daf4","sha256:cc443419cb1f2da9a9dfab94b364d60ad02d232c1413777e74928339a7d8443d"],"state_sha256":"22ba7d9ad111dab0bb5d33611f347d37b884158c61373546e8e459b10d0ee2b1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xG8Sm3lz0q8z9h4Oet/JP8MCyFS0OdyfTm+uEEcG+LCPJg824JKOMGFbyrTpNndIZ8HUwOh+0oRY3k79X1GRCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T19:24:38.488472Z","bundle_sha256":"3d4b99e8acb92294236f1f6f4ff2950ac0308ec275c316e168ad768a92f97372"}}