{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CS2IKY5NN56APJTGES6M5SWYWZ","short_pith_number":"pith:CS2IKY5N","schema_version":"1.0","canonical_sha256":"14b48563ad6f7c07a66624bccecad8b6444dc51d9355fc838b427936f3da94ef","source":{"kind":"arxiv","id":"2502.11262","version":1},"attestation_state":"computed","paper":{"title":"Generating Skyline Datasets for Data Science Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Hanchao Ma, Mengying Wang, Yangxin Fan, Yinghui Wu, Yiyang Bian","submitted_at":"2025-02-16T20:33:59Z","abstract_excerpt":"Preparing high-quality datasets required by various data-driven AI and machine learning models has become a cornerstone task in data-driven analysis. Conventional data discovery methods typically integrate datasets towards a single pre-defined quality measure that may lead to bias for downstream tasks. This paper introduces MODis, a framework that discovers datasets by optimizing multiple user-defined, model-performance measures. Given a set of data sources and a model, MODis selects and integrates data sources into a skyline dataset, over which the model is expected to have the desired perfor"},"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":"2502.11262","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-16T20:33:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d2fb2dc8594c392733209a91581eaef09b5e1cf4a1bc3cb1fcd44c06c0b23299","abstract_canon_sha256":"655ec2da57659a1d4b67800f49a321ba3391114e3231385a548ea6a0914c2083"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:54.280636Z","signature_b64":"3qD7g/fcc/9XAQnnwhGjg8BeOGkquUv968tIct548LkDGMsQG961LvmnMpTc6GnXmkmsVG2Tb5p5zlgukWsrCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14b48563ad6f7c07a66624bccecad8b6444dc51d9355fc838b427936f3da94ef","last_reissued_at":"2026-07-05T10:31:54.279690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:54.279690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Skyline Datasets for Data Science Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Hanchao Ma, Mengying Wang, Yangxin Fan, Yinghui Wu, Yiyang Bian","submitted_at":"2025-02-16T20:33:59Z","abstract_excerpt":"Preparing high-quality datasets required by various data-driven AI and machine learning models has become a cornerstone task in data-driven analysis. Conventional data discovery methods typically integrate datasets towards a single pre-defined quality measure that may lead to bias for downstream tasks. This paper introduces MODis, a framework that discovers datasets by optimizing multiple user-defined, model-performance measures. Given a set of data sources and a model, MODis selects and integrates data sources into a skyline dataset, over which the model is expected to have the desired perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11262","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/2502.11262/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":"2502.11262","created_at":"2026-07-05T10:31:54.279793+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11262v1","created_at":"2026-07-05T10:31:54.279793+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11262","created_at":"2026-07-05T10:31:54.279793+00:00"},{"alias_kind":"pith_short_12","alias_value":"CS2IKY5NN56A","created_at":"2026-07-05T10:31:54.279793+00:00"},{"alias_kind":"pith_short_16","alias_value":"CS2IKY5NN56APJTG","created_at":"2026-07-05T10:31:54.279793+00:00"},{"alias_kind":"pith_short_8","alias_value":"CS2IKY5N","created_at":"2026-07-05T10:31:54.279793+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ","json":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ.json","graph_json":"https://pith.science/api/pith-number/CS2IKY5NN56APJTGES6M5SWYWZ/graph.json","events_json":"https://pith.science/api/pith-number/CS2IKY5NN56APJTGES6M5SWYWZ/events.json","paper":"https://pith.science/paper/CS2IKY5N"},"agent_actions":{"view_html":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ","download_json":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ.json","view_paper":"https://pith.science/paper/CS2IKY5N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11262&json=true","fetch_graph":"https://pith.science/api/pith-number/CS2IKY5NN56APJTGES6M5SWYWZ/graph.json","fetch_events":"https://pith.science/api/pith-number/CS2IKY5NN56APJTGES6M5SWYWZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/action/storage_attestation","attest_author":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/action/author_attestation","sign_citation":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/action/citation_signature","submit_replication":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/action/replication_record"}},"created_at":"2026-07-05T10:31:54.279793+00:00","updated_at":"2026-07-05T10:31:54.279793+00:00"}