{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NYDUCQGIL2VYJHT35O7RSKOZN3","short_pith_number":"pith:NYDUCQGI","schema_version":"1.0","canonical_sha256":"6e074140c85eab849e7bebbf1929d96ed897e8ed41b47923fc4414414d21c633","source":{"kind":"arxiv","id":"2307.05080","version":1},"attestation_state":"computed","paper":{"title":"Estimating label quality and errors in semantic segmentation data via any model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jonas Mueller, Vedang Lad","submitted_at":"2023-07-11T07:29:09Z","abstract_excerpt":"The labor-intensive annotation process of semantic segmentation datasets is often prone to errors, since humans struggle to label every pixel correctly. We study algorithms to automatically detect such annotation errors, in particular methods to score label quality, such that the images with the lowest scores are least likely to be correctly labeled. This helps prioritize what data to review in order to ensure a high-quality training/evaluation dataset, which is critical in sensitive applications such as medical imaging and autonomous vehicles. Widely applicable, our label quality scores rely "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.05080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-11T07:29:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"31b129e6589711f2e64ec38c0c37eecf37648ac8bb6361640568c0f590f222a4","abstract_canon_sha256":"09fe021ece591e7bb4ffbfb8407301f92005199cd598bc7ce68d7896da9cb253"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:29:26.108503Z","signature_b64":"ImmYX8zG6kssNJBxb8/mpzlCBkeA9LBZk37j+DjKfHJ5y6KPQVr+foWnR44y73TW/hwSrLZML6uXUXgAKQVVDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e074140c85eab849e7bebbf1929d96ed897e8ed41b47923fc4414414d21c633","last_reissued_at":"2026-07-05T06:29:26.108058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:29:26.108058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Estimating label quality and errors in semantic segmentation data via any model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Jonas Mueller, Vedang Lad","submitted_at":"2023-07-11T07:29:09Z","abstract_excerpt":"The labor-intensive annotation process of semantic segmentation datasets is often prone to errors, since humans struggle to label every pixel correctly. We study algorithms to automatically detect such annotation errors, in particular methods to score label quality, such that the images with the lowest scores are least likely to be correctly labeled. This helps prioritize what data to review in order to ensure a high-quality training/evaluation dataset, which is critical in sensitive applications such as medical imaging and autonomous vehicles. Widely applicable, our label quality scores rely "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05080","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/2307.05080/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.05080","created_at":"2026-07-05T06:29:26.108114+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05080v1","created_at":"2026-07-05T06:29:26.108114+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05080","created_at":"2026-07-05T06:29:26.108114+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYDUCQGIL2VY","created_at":"2026-07-05T06:29:26.108114+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYDUCQGIL2VYJHT3","created_at":"2026-07-05T06:29:26.108114+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYDUCQGI","created_at":"2026-07-05T06:29:26.108114+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.02351","citing_title":"Ordinal Adaptive Correction: A Data-Centric Approach to Ordinal Image Classification with Noisy Labels","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06891","citing_title":"Towards Fairness under Label Bias in Image Segmentation: Impact, Measurement and Mitigation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3","json":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3.json","graph_json":"https://pith.science/api/pith-number/NYDUCQGIL2VYJHT35O7RSKOZN3/graph.json","events_json":"https://pith.science/api/pith-number/NYDUCQGIL2VYJHT35O7RSKOZN3/events.json","paper":"https://pith.science/paper/NYDUCQGI"},"agent_actions":{"view_html":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3","download_json":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3.json","view_paper":"https://pith.science/paper/NYDUCQGI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05080&json=true","fetch_graph":"https://pith.science/api/pith-number/NYDUCQGIL2VYJHT35O7RSKOZN3/graph.json","fetch_events":"https://pith.science/api/pith-number/NYDUCQGIL2VYJHT35O7RSKOZN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3/action/storage_attestation","attest_author":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3/action/author_attestation","sign_citation":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3/action/citation_signature","submit_replication":"https://pith.science/pith/NYDUCQGIL2VYJHT35O7RSKOZN3/action/replication_record"}},"created_at":"2026-07-05T06:29:26.108114+00:00","updated_at":"2026-07-05T06:29:26.108114+00:00"}