{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DC5ODXKSGCWWDRK7EP2R7NDS3O","short_pith_number":"pith:DC5ODXKS","schema_version":"1.0","canonical_sha256":"18bae1dd5230ad61c55f23f51fb472dba5e1ab559e22c08796a0541fef41686c","source":{"kind":"arxiv","id":"2312.11122","version":3},"attestation_state":"computed","paper":{"title":"Evaluation of Dataframe Libraries for Data Preparation on a Single Machine","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Adeel Aslam, Angelo Mozzillo, Giovanni Simonini, Luca Gagliardelli, Luca Zecchini, Sonia Bergamaschi","submitted_at":"2023-12-18T11:41:27Z","abstract_excerpt":"Data preparation is a trial-and-error process that typically involves countless iterations over the data to define the best pipeline of operators for a given task. With tabular data, practitioners often perform that burdensome activity on local machines by writing ad hoc scripts with libraries based on the Pandas dataframe API and testing them on samples of the entire dataset-the faster the library, the less idle time its users have.\n  In this paper, we evaluate the most popular Python dataframe libraries in general data preparation use cases to assess how they perform on a single machine. To "},"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":"2312.11122","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2023-12-18T11:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"b8700a6188bf94cd77c38c0c7879c548cb898636fd963b9d635ed2a1e2449a94","abstract_canon_sha256":"fcb6e71b16ca45609e559dfa64de6eb9a283fc969541bf37433e4b0a0b11effd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:23.192052Z","signature_b64":"vcbwI0B6vpJfb5F9EBpFOMIX8a4t8/9yVLsvay+eRW6uKW8oU+6ny8p9nNTI2QSQjeWqkl7soSqqG+viFTAECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18bae1dd5230ad61c55f23f51fb472dba5e1ab559e22c08796a0541fef41686c","last_reissued_at":"2026-07-05T09:38:23.191457Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:23.191457Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluation of Dataframe Libraries for Data Preparation on a Single Machine","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Adeel Aslam, Angelo Mozzillo, Giovanni Simonini, Luca Gagliardelli, Luca Zecchini, Sonia Bergamaschi","submitted_at":"2023-12-18T11:41:27Z","abstract_excerpt":"Data preparation is a trial-and-error process that typically involves countless iterations over the data to define the best pipeline of operators for a given task. With tabular data, practitioners often perform that burdensome activity on local machines by writing ad hoc scripts with libraries based on the Pandas dataframe API and testing them on samples of the entire dataset-the faster the library, the less idle time its users have.\n  In this paper, we evaluate the most popular Python dataframe libraries in general data preparation use cases to assess how they perform on a single machine. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11122","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2312.11122/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":"2312.11122","created_at":"2026-07-05T09:38:23.191531+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11122v3","created_at":"2026-07-05T09:38:23.191531+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11122","created_at":"2026-07-05T09:38:23.191531+00:00"},{"alias_kind":"pith_short_12","alias_value":"DC5ODXKSGCWW","created_at":"2026-07-05T09:38:23.191531+00:00"},{"alias_kind":"pith_short_16","alias_value":"DC5ODXKSGCWWDRK7","created_at":"2026-07-05T09:38:23.191531+00:00"},{"alias_kind":"pith_short_8","alias_value":"DC5ODXKS","created_at":"2026-07-05T09:38:23.191531+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24679","citing_title":"FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2511.08644","citing_title":"Energy Consumption of Dataframe Libraries for End-to-End Deep Learning Pipelines:A Comparative Analysis","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O","json":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O.json","graph_json":"https://pith.science/api/pith-number/DC5ODXKSGCWWDRK7EP2R7NDS3O/graph.json","events_json":"https://pith.science/api/pith-number/DC5ODXKSGCWWDRK7EP2R7NDS3O/events.json","paper":"https://pith.science/paper/DC5ODXKS"},"agent_actions":{"view_html":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O","download_json":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O.json","view_paper":"https://pith.science/paper/DC5ODXKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11122&json=true","fetch_graph":"https://pith.science/api/pith-number/DC5ODXKSGCWWDRK7EP2R7NDS3O/graph.json","fetch_events":"https://pith.science/api/pith-number/DC5ODXKSGCWWDRK7EP2R7NDS3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O/action/storage_attestation","attest_author":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O/action/author_attestation","sign_citation":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O/action/citation_signature","submit_replication":"https://pith.science/pith/DC5ODXKSGCWWDRK7EP2R7NDS3O/action/replication_record"}},"created_at":"2026-07-05T09:38:23.191531+00:00","updated_at":"2026-07-05T09:38:23.191531+00:00"}