{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SGOPC4ZW5DKT2AB7NDC5YWYAPI","short_pith_number":"pith:SGOPC4ZW","schema_version":"1.0","canonical_sha256":"919cf17336e8d53d003f68c5dc5b007a17d53170549384a8211bc4f6fbe6e5f4","source":{"kind":"arxiv","id":"2509.09512","version":1},"attestation_state":"computed","paper":{"title":"PIPES: A Meta-dataset of Machine Learning Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cynthia Moreira Maia, George D. C. Cavalcanti, Lucas B. V. de Amorim, Rafael M. O. Cruz","submitted_at":"2025-09-11T14:52:58Z","abstract_excerpt":"Solutions to the Algorithm Selection Problem (ASP) in machine learning face the challenge of high computational costs associated with evaluating various algorithms' performances on a given dataset. To mitigate this cost, the meta-learning field can leverage previously executed experiments shared in online repositories such as OpenML. OpenML provides an extensive collection of machine learning experiments. However, an analysis of OpenML's records reveals limitations. It lacks diversity in pipelines, specifically when exploring data preprocessing steps/blocks, such as scaling or imputation, resu"},"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":"2509.09512","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-11T14:52:58Z","cross_cats_sorted":[],"title_canon_sha256":"65cf92bdd0c16ec500b47104ee723fdf512add10039591074c818feafc84dbc6","abstract_canon_sha256":"815eae79e3275a61e25f2ecc80c80db79918d69bf9da6629204b2c6666b00791"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:37.301548Z","signature_b64":"Mlt6vkHVcjaD+ZlXxrx0fTmB46BpxpjghYxwCjSCVXuz1ZhwhdBGts5AuW6O5OZ7XTy+L20nvuuqMVg9P4DMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"919cf17336e8d53d003f68c5dc5b007a17d53170549384a8211bc4f6fbe6e5f4","last_reissued_at":"2026-07-05T12:09:37.301093Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:37.301093Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PIPES: A Meta-dataset of Machine Learning Pipelines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Cynthia Moreira Maia, George D. C. Cavalcanti, Lucas B. V. de Amorim, Rafael M. O. Cruz","submitted_at":"2025-09-11T14:52:58Z","abstract_excerpt":"Solutions to the Algorithm Selection Problem (ASP) in machine learning face the challenge of high computational costs associated with evaluating various algorithms' performances on a given dataset. To mitigate this cost, the meta-learning field can leverage previously executed experiments shared in online repositories such as OpenML. OpenML provides an extensive collection of machine learning experiments. However, an analysis of OpenML's records reveals limitations. It lacks diversity in pipelines, specifically when exploring data preprocessing steps/blocks, such as scaling or imputation, resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09512","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/2509.09512/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":"2509.09512","created_at":"2026-07-05T12:09:37.301155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09512v1","created_at":"2026-07-05T12:09:37.301155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09512","created_at":"2026-07-05T12:09:37.301155+00:00"},{"alias_kind":"pith_short_12","alias_value":"SGOPC4ZW5DKT","created_at":"2026-07-05T12:09:37.301155+00:00"},{"alias_kind":"pith_short_16","alias_value":"SGOPC4ZW5DKT2AB7","created_at":"2026-07-05T12:09:37.301155+00:00"},{"alias_kind":"pith_short_8","alias_value":"SGOPC4ZW","created_at":"2026-07-05T12:09:37.301155+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/SGOPC4ZW5DKT2AB7NDC5YWYAPI","json":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI.json","graph_json":"https://pith.science/api/pith-number/SGOPC4ZW5DKT2AB7NDC5YWYAPI/graph.json","events_json":"https://pith.science/api/pith-number/SGOPC4ZW5DKT2AB7NDC5YWYAPI/events.json","paper":"https://pith.science/paper/SGOPC4ZW"},"agent_actions":{"view_html":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI","download_json":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI.json","view_paper":"https://pith.science/paper/SGOPC4ZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09512&json=true","fetch_graph":"https://pith.science/api/pith-number/SGOPC4ZW5DKT2AB7NDC5YWYAPI/graph.json","fetch_events":"https://pith.science/api/pith-number/SGOPC4ZW5DKT2AB7NDC5YWYAPI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI/action/storage_attestation","attest_author":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI/action/author_attestation","sign_citation":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI/action/citation_signature","submit_replication":"https://pith.science/pith/SGOPC4ZW5DKT2AB7NDC5YWYAPI/action/replication_record"}},"created_at":"2026-07-05T12:09:37.301155+00:00","updated_at":"2026-07-05T12:09:37.301155+00:00"}