{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:3S4ECBYSRGGXXDUNHC5CPUBJ32","short_pith_number":"pith:3S4ECBYS","schema_version":"1.0","canonical_sha256":"dcb8410712898d7b8e8d38ba27d029dea76c9db271155abb42eee6386d1ac3a4","source":{"kind":"arxiv","id":"2112.07844","version":1},"attestation_state":"computed","paper":{"title":"Fix your Models by Fixing your Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Corletti, Atindriyo Sanyal, Ben Epstein, Nidhi Vyas, Nikita Demir, Vikram Chatterji","submitted_at":"2021-12-15T02:41:50Z","abstract_excerpt":"The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So, getting data quality insights and iteratively pruning the errors to obtain a dataset which is most representative of downstream use cases is still an ad-hoc manual process. Our work addresses this data tooling gap, required to build improved ML workflows purely through data-centric techniques. More specifically, we introduce a systematic framework for (1) fi"},"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":"2112.07844","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-12-15T02:41:50Z","cross_cats_sorted":[],"title_canon_sha256":"0f63b35b00c9ca84fefadafa928a1a8fa7ece85735fdcb6d22f8e7acf4e2a8fa","abstract_canon_sha256":"944fea545c74ef59577332891256dd7d86c259eaa2167448ac7e1b1a818b77e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:41:07.608123Z","signature_b64":"7VpFnRjpkC9y3FXQz2jaJBvhOsTntC8yjJrKsnkZ5zwkD/Bzha1vbmz6Dode0JRN10iLoKesngpi79OHsnMeBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dcb8410712898d7b8e8d38ba27d029dea76c9db271155abb42eee6386d1ac3a4","last_reissued_at":"2026-07-05T03:41:07.607688Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:41:07.607688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fix your Models by Fixing your Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anthony Corletti, Atindriyo Sanyal, Ben Epstein, Nidhi Vyas, Nikita Demir, Vikram Chatterji","submitted_at":"2021-12-15T02:41:50Z","abstract_excerpt":"The quality of underlying training data is very crucial for building performant machine learning models with wider generalizabilty. However, current machine learning (ML) tools lack streamlined processes for improving the data quality. So, getting data quality insights and iteratively pruning the errors to obtain a dataset which is most representative of downstream use cases is still an ad-hoc manual process. Our work addresses this data tooling gap, required to build improved ML workflows purely through data-centric techniques. More specifically, we introduce a systematic framework for (1) fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07844","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/2112.07844/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":"2112.07844","created_at":"2026-07-05T03:41:07.607746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.07844v1","created_at":"2026-07-05T03:41:07.607746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07844","created_at":"2026-07-05T03:41:07.607746+00:00"},{"alias_kind":"pith_short_12","alias_value":"3S4ECBYSRGGX","created_at":"2026-07-05T03:41:07.607746+00:00"},{"alias_kind":"pith_short_16","alias_value":"3S4ECBYSRGGXXDUN","created_at":"2026-07-05T03:41:07.607746+00:00"},{"alias_kind":"pith_short_8","alias_value":"3S4ECBYS","created_at":"2026-07-05T03:41:07.607746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02922","citing_title":"Domain Knowledge in Artificial Intelligence: Using Conceptual Modeling to Increase Machine Learning Accuracy and Explainability","ref_index":69,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32","json":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32.json","graph_json":"https://pith.science/api/pith-number/3S4ECBYSRGGXXDUNHC5CPUBJ32/graph.json","events_json":"https://pith.science/api/pith-number/3S4ECBYSRGGXXDUNHC5CPUBJ32/events.json","paper":"https://pith.science/paper/3S4ECBYS"},"agent_actions":{"view_html":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32","download_json":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32.json","view_paper":"https://pith.science/paper/3S4ECBYS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.07844&json=true","fetch_graph":"https://pith.science/api/pith-number/3S4ECBYSRGGXXDUNHC5CPUBJ32/graph.json","fetch_events":"https://pith.science/api/pith-number/3S4ECBYSRGGXXDUNHC5CPUBJ32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32/action/storage_attestation","attest_author":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32/action/author_attestation","sign_citation":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32/action/citation_signature","submit_replication":"https://pith.science/pith/3S4ECBYSRGGXXDUNHC5CPUBJ32/action/replication_record"}},"created_at":"2026-07-05T03:41:07.607746+00:00","updated_at":"2026-07-05T03:41:07.607746+00:00"}