{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:URF33DCEFPBAU7Y6PNIZUR6WLW","short_pith_number":"pith:URF33DCE","schema_version":"1.0","canonical_sha256":"a44bbd8c442bc20a7f1e7b519a47d65d867daf8c4a52939bb5f1683b10367685","source":{"kind":"arxiv","id":"2509.09684","version":1},"attestation_state":"computed","paper":{"title":"Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.IR","authors_text":"Bruno Yui Yamate, Marcelo Fantinato, Sarajane Marques Peres, Thais Rodrigues Neubauer","submitted_at":"2025-08-18T01:25:41Z","abstract_excerpt":"This paper introduces text-2-SQL-4-PM, a bilingual (Portuguese-English) benchmark dataset designed for the text-to-SQL task in the process mining domain. Text-to-SQL conversion facilitates natural language querying of databases, increasing accessibility for users without SQL expertise and productivity for those that are experts. The text-2-SQL-4-PM dataset is customized to address the unique challenges of process mining, including specialized vocabularies and single-table relational structures derived from event logs. The dataset comprises 1,655 natural language utterances, including human-gen"},"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":"2509.09684","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-08-18T01:25:41Z","cross_cats_sorted":["cs.AI","cs.CL","cs.DB"],"title_canon_sha256":"af2a69a9547c00fb4c3e59eda943255e5d811808e9d025841a1136fe7246867c","abstract_canon_sha256":"8cfd3d4d55be6d1bad4ff77a6c8198947ef97762cfadd40facc12b5e923f63c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:47.010827Z","signature_b64":"Idd8oflf70h5xhie9zQH17KWrX5VXlFglGt5XLKHb+OfbNQEU/7C2MePUisEPDSxswNtoWyq7QUBE2ghxfxSBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a44bbd8c442bc20a7f1e7b519a47d65d867daf8c4a52939bb5f1683b10367685","last_reissued_at":"2026-07-05T12:09:47.009736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:47.009736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Text-to-SQL Oriented to the Process Mining Domain: A PT-EN Dataset for Query Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.DB"],"primary_cat":"cs.IR","authors_text":"Bruno Yui Yamate, Marcelo Fantinato, Sarajane Marques Peres, Thais Rodrigues Neubauer","submitted_at":"2025-08-18T01:25:41Z","abstract_excerpt":"This paper introduces text-2-SQL-4-PM, a bilingual (Portuguese-English) benchmark dataset designed for the text-to-SQL task in the process mining domain. Text-to-SQL conversion facilitates natural language querying of databases, increasing accessibility for users without SQL expertise and productivity for those that are experts. The text-2-SQL-4-PM dataset is customized to address the unique challenges of process mining, including specialized vocabularies and single-table relational structures derived from event logs. The dataset comprises 1,655 natural language utterances, including human-gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09684","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/2509.09684/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":"2509.09684","created_at":"2026-07-05T12:09:47.010364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09684v1","created_at":"2026-07-05T12:09:47.010364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09684","created_at":"2026-07-05T12:09:47.010364+00:00"},{"alias_kind":"pith_short_12","alias_value":"URF33DCEFPBA","created_at":"2026-07-05T12:09:47.010364+00:00"},{"alias_kind":"pith_short_16","alias_value":"URF33DCEFPBAU7Y6","created_at":"2026-07-05T12:09:47.010364+00:00"},{"alias_kind":"pith_short_8","alias_value":"URF33DCE","created_at":"2026-07-05T12:09:47.010364+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/URF33DCEFPBAU7Y6PNIZUR6WLW","json":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW.json","graph_json":"https://pith.science/api/pith-number/URF33DCEFPBAU7Y6PNIZUR6WLW/graph.json","events_json":"https://pith.science/api/pith-number/URF33DCEFPBAU7Y6PNIZUR6WLW/events.json","paper":"https://pith.science/paper/URF33DCE"},"agent_actions":{"view_html":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW","download_json":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW.json","view_paper":"https://pith.science/paper/URF33DCE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09684&json=true","fetch_graph":"https://pith.science/api/pith-number/URF33DCEFPBAU7Y6PNIZUR6WLW/graph.json","fetch_events":"https://pith.science/api/pith-number/URF33DCEFPBAU7Y6PNIZUR6WLW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW/action/storage_attestation","attest_author":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW/action/author_attestation","sign_citation":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW/action/citation_signature","submit_replication":"https://pith.science/pith/URF33DCEFPBAU7Y6PNIZUR6WLW/action/replication_record"}},"created_at":"2026-07-05T12:09:47.010364+00:00","updated_at":"2026-07-05T12:09:47.010364+00:00"}