{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CS2IKY5NN56APJTGES6M5SWYWZ","short_pith_number":"pith:CS2IKY5N","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"},"canonical_sha256":"14b48563ad6f7c07a66624bccecad8b6444dc51d9355fc838b427936f3da94ef","source":{"kind":"arxiv","id":"2502.11262","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11262","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11262v1","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11262","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"CS2IKY5NN56A","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"pith_short_16","alias_value":"CS2IKY5NN56APJTG","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"pith_short_8","alias_value":"CS2IKY5N","created_at":"2026-07-05T10:31:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CS2IKY5NN56APJTGES6M5SWYWZ","target":"record","payload":{"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"},"canonical_sha256":"14b48563ad6f7c07a66624bccecad8b6444dc51d9355fc838b427936f3da94ef","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"},"source_kind":"arxiv","source_id":"2502.11262","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:31:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ON0iqqdgMQ4U278fv1lL9pxjxq0AsE47sdwfy6cHrmaQffw6XPN9e8Po4a2pLXZ9JUePlGp94PuF9vfe1TdJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:48:18.722602Z"},"content_sha256":"07823448f34e74f01e789d8f2904cd046cd6f51bda382aa983b49488b8c8556c","schema_version":"1.0","event_id":"sha256:07823448f34e74f01e789d8f2904cd046cd6f51bda382aa983b49488b8c8556c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CS2IKY5NN56APJTGES6M5SWYWZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:31:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ov2OQRFz9Rvl0/aOynlGvQRUtEmBk0NvMPaUEFmonKrIBjqX8hMZy4pQru7+WxX8aSMk7KaSUoROgxuArMWhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T22:48:18.723122Z"},"content_sha256":"4e1140b2198ee2b088e7403a243e9cacae8aed4c0a326035857f604f36f29be8","schema_version":"1.0","event_id":"sha256:4e1140b2198ee2b088e7403a243e9cacae8aed4c0a326035857f604f36f29be8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/bundle.json","state_url":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CS2IKY5NN56APJTGES6M5SWYWZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T22:48:18Z","links":{"resolver":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ","bundle":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/bundle.json","state":"https://pith.science/pith/CS2IKY5NN56APJTGES6M5SWYWZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CS2IKY5NN56APJTGES6M5SWYWZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CS2IKY5NN56APJTGES6M5SWYWZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"655ec2da57659a1d4b67800f49a321ba3391114e3231385a548ea6a0914c2083","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-16T20:33:59Z","title_canon_sha256":"d2fb2dc8594c392733209a91581eaef09b5e1cf4a1bc3cb1fcd44c06c0b23299"},"schema_version":"1.0","source":{"id":"2502.11262","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.11262","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"arxiv_version","alias_value":"2502.11262v1","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11262","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"pith_short_12","alias_value":"CS2IKY5NN56A","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"pith_short_16","alias_value":"CS2IKY5NN56APJTG","created_at":"2026-07-05T10:31:54Z"},{"alias_kind":"pith_short_8","alias_value":"CS2IKY5N","created_at":"2026-07-05T10:31:54Z"}],"graph_snapshots":[{"event_id":"sha256:4e1140b2198ee2b088e7403a243e9cacae8aed4c0a326035857f604f36f29be8","target":"graph","created_at":"2026-07-05T10:31:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.11262/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanchao Ma, Mengying Wang, Yangxin Fan, Yinghui Wu, Yiyang Bian","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-16T20:33:59Z","title":"Generating Skyline Datasets for Data Science Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11262","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:07823448f34e74f01e789d8f2904cd046cd6f51bda382aa983b49488b8c8556c","target":"record","created_at":"2026-07-05T10:31:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"655ec2da57659a1d4b67800f49a321ba3391114e3231385a548ea6a0914c2083","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-16T20:33:59Z","title_canon_sha256":"d2fb2dc8594c392733209a91581eaef09b5e1cf4a1bc3cb1fcd44c06c0b23299"},"schema_version":"1.0","source":{"id":"2502.11262","kind":"arxiv","version":1}},"canonical_sha256":"14b48563ad6f7c07a66624bccecad8b6444dc51d9355fc838b427936f3da94ef","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14b48563ad6f7c07a66624bccecad8b6444dc51d9355fc838b427936f3da94ef","first_computed_at":"2026-07-05T10:31:54.279690Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:54.279690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3qD7g/fcc/9XAQnnwhGjg8BeOGkquUv968tIct548LkDGMsQG961LvmnMpTc6GnXmkmsVG2Tb5p5zlgukWsrCg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:54.280636Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.11262","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:07823448f34e74f01e789d8f2904cd046cd6f51bda382aa983b49488b8c8556c","sha256:4e1140b2198ee2b088e7403a243e9cacae8aed4c0a326035857f604f36f29be8"],"state_sha256":"5a5fdad11caa99580da899bbe6b6030d65c7a789cf971f2044df804f5f45a715"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xdQYl8zAmI22Tw9i4k///Ri7ohHRyCYvlFsvul2AvJdSKfkTsrrSkwC/sXT4FW5vD+abdcHVu3Fb8lWRiCJRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T22:48:18.728393Z","bundle_sha256":"4b2ccf3afab317e17f6a35266ea70f40b708b09a118e9bac86b0f02fb798d801"}}