{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6NJHI2JVSAAHBQKFV6SKEKB762","short_pith_number":"pith:6NJHI2JV","schema_version":"1.0","canonical_sha256":"f352746935900070c145afa4a2283ff6afcfd3f390ed30a6f16c223f2ac465d2","source":{"kind":"arxiv","id":"1807.06068","version":3},"attestation_state":"computed","paper":{"title":"Automated Data Slicing for Model Validation:A Big data - AI Integration Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Ki Hyun Tae, Neoklis Polyzotis, Steven Euijong Whang, Tim Kraska, Yeounoh Chung","submitted_at":"2018-07-16T19:21:24Z","abstract_excerpt":"As machine learning systems become democratized, it becomes increasingly important to help users easily debug their models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly. This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets, and slicing allows users to analyze the model performance on a more granular"},"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":"1807.06068","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-07-16T19:21:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"01e2a1772d34868c36576e6d9085fa3438e9eda46e039f8c5a5abdf0392ef60e","abstract_canon_sha256":"84312ad1f71b556e9b40279e0f26dcb0ebff11186b5d2ee63027e228b9c7c784"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:56:53.152595Z","signature_b64":"K8T4iKLfWKvoSsHRaEqIJFjb3tktpsJVFM+3d8AoO/M2V8c7WKj++6UvWO4gqDcZ3JwcnsS6wgbDUp8EduT3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f352746935900070c145afa4a2283ff6afcfd3f390ed30a6f16c223f2ac465d2","last_reissued_at":"2026-05-17T23:56:53.152187Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:56:53.152187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automated Data Slicing for Model Validation:A Big data - AI Integration Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DB","authors_text":"Ki Hyun Tae, Neoklis Polyzotis, Steven Euijong Whang, Tim Kraska, Yeounoh Chung","submitted_at":"2018-07-16T19:21:24Z","abstract_excerpt":"As machine learning systems become democratized, it becomes increasingly important to help users easily debug their models. However, current data tools are still primitive when it comes to helping users trace model performance problems all the way to the data. We focus on the particular problem of slicing data to identify subsets of the validation data where the model performs poorly. This is an important problem in model validation because the overall model performance can fail to reflect that of the smaller subsets, and slicing allows users to analyze the model performance on a more granular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.06068","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1807.06068","created_at":"2026-05-17T23:56:53.152251+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.06068v3","created_at":"2026-05-17T23:56:53.152251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.06068","created_at":"2026-05-17T23:56:53.152251+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NJHI2JVSAAH","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NJHI2JVSAAHBQKF","created_at":"2026-05-18T12:32:11.075285+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NJHI2JV","created_at":"2026-05-18T12:32:11.075285+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19357","citing_title":"FairTree: Subgroup Fairness Auditing of Machine Learning Models with Bias-Variance Decomposition","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762","json":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762.json","graph_json":"https://pith.science/api/pith-number/6NJHI2JVSAAHBQKFV6SKEKB762/graph.json","events_json":"https://pith.science/api/pith-number/6NJHI2JVSAAHBQKFV6SKEKB762/events.json","paper":"https://pith.science/paper/6NJHI2JV"},"agent_actions":{"view_html":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762","download_json":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762.json","view_paper":"https://pith.science/paper/6NJHI2JV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.06068&json=true","fetch_graph":"https://pith.science/api/pith-number/6NJHI2JVSAAHBQKFV6SKEKB762/graph.json","fetch_events":"https://pith.science/api/pith-number/6NJHI2JVSAAHBQKFV6SKEKB762/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762/action/storage_attestation","attest_author":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762/action/author_attestation","sign_citation":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762/action/citation_signature","submit_replication":"https://pith.science/pith/6NJHI2JVSAAHBQKFV6SKEKB762/action/replication_record"}},"created_at":"2026-05-17T23:56:53.152251+00:00","updated_at":"2026-05-17T23:56:53.152251+00:00"}