{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:E6VAGMEAMCHMOSDMWDO2XOETLL","short_pith_number":"pith:E6VAGMEA","schema_version":"1.0","canonical_sha256":"27aa033080608ec7486cb0ddabb8935af6a4b48b824b1a81b000d382f7ca02a1","source":{"kind":"arxiv","id":"2210.11717","version":2},"attestation_state":"computed","paper":{"title":"A Survey of Dataset Refinement for Problems in Computer Vision Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"CheukTing Chung, Zheng Wang, Zhijing Wan, Zhixiang Wang","submitted_at":"2022-10-21T03:58:43Z","abstract_excerpt":"Large-scale datasets have played a crucial role in the advancement of computer vision. However, they often suffer from problems such as class imbalance, noisy labels, dataset bias, or high resource costs, which can inhibit model performance and reduce trustworthiness. With the advocacy of data-centric research, various data-centric solutions have been proposed to solve the dataset problems mentioned above. They improve the quality of datasets by re-organizing them, which we call dataset refinement. In this survey, we provide a comprehensive and structured overview of recent advances in dataset"},"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":"2210.11717","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-10-21T03:58:43Z","cross_cats_sorted":[],"title_canon_sha256":"e0608d9803a229bbd8c3e268af03c61621235d91be1b63ae55c9a0418b0d151e","abstract_canon_sha256":"8f718faa90476a37f50c54ebdff6fda621f686cda0261a5df5e302b4c766c320"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:50.917628Z","signature_b64":"U7jkeNGEtH/YZ7MdB34xjuAujLwtqC0Y9vIpLm1j9rcxkwm4EQDmjRWZUhZW/WfZbnGs0hCTwL8D8AErRP3XBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27aa033080608ec7486cb0ddabb8935af6a4b48b824b1a81b000d382f7ca02a1","last_reissued_at":"2026-07-05T06:57:50.917070Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:50.917070Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Dataset Refinement for Problems in Computer Vision Datasets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"CheukTing Chung, Zheng Wang, Zhijing Wan, Zhixiang Wang","submitted_at":"2022-10-21T03:58:43Z","abstract_excerpt":"Large-scale datasets have played a crucial role in the advancement of computer vision. However, they often suffer from problems such as class imbalance, noisy labels, dataset bias, or high resource costs, which can inhibit model performance and reduce trustworthiness. With the advocacy of data-centric research, various data-centric solutions have been proposed to solve the dataset problems mentioned above. They improve the quality of datasets by re-organizing them, which we call dataset refinement. In this survey, we provide a comprehensive and structured overview of recent advances in dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.11717","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/2210.11717/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":"2210.11717","created_at":"2026-07-05T06:57:50.917152+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.11717v2","created_at":"2026-07-05T06:57:50.917152+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.11717","created_at":"2026-07-05T06:57:50.917152+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6VAGMEAMCHM","created_at":"2026-07-05T06:57:50.917152+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6VAGMEAMCHMOSDM","created_at":"2026-07-05T06:57:50.917152+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6VAGMEA","created_at":"2026-07-05T06:57:50.917152+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2504.15796","citing_title":"Locating and Mitigating Gradient Conflicts in Point Cloud Domain Adaptation via Saliency Map Skewness","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL","json":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL.json","graph_json":"https://pith.science/api/pith-number/E6VAGMEAMCHMOSDMWDO2XOETLL/graph.json","events_json":"https://pith.science/api/pith-number/E6VAGMEAMCHMOSDMWDO2XOETLL/events.json","paper":"https://pith.science/paper/E6VAGMEA"},"agent_actions":{"view_html":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL","download_json":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL.json","view_paper":"https://pith.science/paper/E6VAGMEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.11717&json=true","fetch_graph":"https://pith.science/api/pith-number/E6VAGMEAMCHMOSDMWDO2XOETLL/graph.json","fetch_events":"https://pith.science/api/pith-number/E6VAGMEAMCHMOSDMWDO2XOETLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL/action/storage_attestation","attest_author":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL/action/author_attestation","sign_citation":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL/action/citation_signature","submit_replication":"https://pith.science/pith/E6VAGMEAMCHMOSDMWDO2XOETLL/action/replication_record"}},"created_at":"2026-07-05T06:57:50.917152+00:00","updated_at":"2026-07-05T06:57:50.917152+00:00"}