{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GSXCQ6TF2FVQV56EFUBI6OU5MN","short_pith_number":"pith:GSXCQ6TF","schema_version":"1.0","canonical_sha256":"34ae287a65d16b0af7c42d028f3a9d635d8c5bf460ff1369cebed97478bbf56e","source":{"kind":"arxiv","id":"2502.15718","version":1},"attestation_state":"computed","paper":{"title":"Making Sense of Data in the Wild: Data Analysis Automation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Irina Espejo Morales, Joris Cadow-Gossweiler, Malina Molnar, Mara Graziani, Teodoro Laino","submitted_at":"2025-01-27T10:04:10Z","abstract_excerpt":"As the volume of publicly available data continues to grow, researchers face the challenge of limited diversity in benchmarking machine learning tasks. Although thousands of datasets are available in public repositories, the sheer abundance often complicates the search for suitable data, leaving many valuable datasets underexplored. This situation is further amplified by the fact that, despite longstanding advocacy for improving data curation quality, current solutions remain prohibitively time-consuming and resource-intensive. In this paper, we propose a novel approach that combines intellige"},"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":"2502.15718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-01-27T10:04:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6335ebe840170f67a66a180d58d62dfdf0a54e41ab22fef20a67d84055143ffc","abstract_canon_sha256":"879db745c68d552bcc28ba84fa358f72349da1cde9e1dad3d83df5a4b293e2d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:15.337844Z","signature_b64":"b+aUcnnsPUZHHlYehbJ7hUrUaZIsUiGWONPWhH+Wn0HEY02Aol9jF/xCjyUU30J1a+8yTL1iw7bAiArDgG4LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34ae287a65d16b0af7c42d028f3a9d635d8c5bf460ff1369cebed97478bbf56e","last_reissued_at":"2026-07-05T10:18:15.337132Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:15.337132Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Making Sense of Data in the Wild: Data Analysis Automation at Scale","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Irina Espejo Morales, Joris Cadow-Gossweiler, Malina Molnar, Mara Graziani, Teodoro Laino","submitted_at":"2025-01-27T10:04:10Z","abstract_excerpt":"As the volume of publicly available data continues to grow, researchers face the challenge of limited diversity in benchmarking machine learning tasks. Although thousands of datasets are available in public repositories, the sheer abundance often complicates the search for suitable data, leaving many valuable datasets underexplored. This situation is further amplified by the fact that, despite longstanding advocacy for improving data curation quality, current solutions remain prohibitively time-consuming and resource-intensive. In this paper, we propose a novel approach that combines intellige"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.15718","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/2502.15718/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":"2502.15718","created_at":"2026-07-05T10:18:15.337207+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.15718v1","created_at":"2026-07-05T10:18:15.337207+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.15718","created_at":"2026-07-05T10:18:15.337207+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSXCQ6TF2FVQ","created_at":"2026-07-05T10:18:15.337207+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSXCQ6TF2FVQV56E","created_at":"2026-07-05T10:18:15.337207+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSXCQ6TF","created_at":"2026-07-05T10:18:15.337207+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/GSXCQ6TF2FVQV56EFUBI6OU5MN","json":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN.json","graph_json":"https://pith.science/api/pith-number/GSXCQ6TF2FVQV56EFUBI6OU5MN/graph.json","events_json":"https://pith.science/api/pith-number/GSXCQ6TF2FVQV56EFUBI6OU5MN/events.json","paper":"https://pith.science/paper/GSXCQ6TF"},"agent_actions":{"view_html":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN","download_json":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN.json","view_paper":"https://pith.science/paper/GSXCQ6TF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.15718&json=true","fetch_graph":"https://pith.science/api/pith-number/GSXCQ6TF2FVQV56EFUBI6OU5MN/graph.json","fetch_events":"https://pith.science/api/pith-number/GSXCQ6TF2FVQV56EFUBI6OU5MN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN/action/storage_attestation","attest_author":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN/action/author_attestation","sign_citation":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN/action/citation_signature","submit_replication":"https://pith.science/pith/GSXCQ6TF2FVQV56EFUBI6OU5MN/action/replication_record"}},"created_at":"2026-07-05T10:18:15.337207+00:00","updated_at":"2026-07-05T10:18:15.337207+00:00"}