{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:APYB5ZRVH3VBMR67J4E3C4WKUH","short_pith_number":"pith:APYB5ZRV","schema_version":"1.0","canonical_sha256":"03f01ee6353eea1647df4f09b172caa1d25aabea7957e8c3cd4e8e3dfae98f91","source":{"kind":"arxiv","id":"2603.07841","version":2},"attestation_state":"computed","paper":{"title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen, Trinh Pham, Viet Huynh","submitted_at":"2026-03-08T23:14:18Z","abstract_excerpt":"Recent advances in large language models have strengthened Text2SQL systems that translate natural language questions into database queries. A persistent deployment challenge is to assess a newly trained Text2SQL system on an unseen and unlabeled dataset when no verified answers are available. This situation arises frequently because database content and structure evolve, privacy policies slow manual review, and carefully written SQL labels are costly and time-consuming. Without timely evaluation, organizations cannot approve releases or detect failures early. FusionSQL addresses this gap by w"},"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":"2603.07841","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-08T23:14:18Z","cross_cats_sorted":[],"title_canon_sha256":"9f228cd1b868f28c88fc985e4f9115542a1681454765e72b79d8dd17e277cdd3","abstract_canon_sha256":"a33ab310f43be842f569a809a33fbaf2d843482400cdece2746d7785adb4ab85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:31.132132Z","signature_b64":"YtAAnTI8qVFF0ixVaS8AfpEiAY9Xv5VJj8c+pFicvBLSlvplAEytoqyyD4gF2v8EOIo+Y9vjIPkO6Tw7E0PuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"03f01ee6353eea1647df4f09b172caa1d25aabea7957e8c3cd4e8e3dfae98f91","last_reissued_at":"2026-07-28T01:22:31.131159Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:31.131159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Efficient and Effective Evaluator for Text2SQL Models on Unseen and Unlabeled Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongzhi Yin, Quoc Viet Hung Nguyen, Thanh Tam Nguyen, Trinh Pham, Viet Huynh","submitted_at":"2026-03-08T23:14:18Z","abstract_excerpt":"Recent advances in large language models have strengthened Text2SQL systems that translate natural language questions into database queries. A persistent deployment challenge is to assess a newly trained Text2SQL system on an unseen and unlabeled dataset when no verified answers are available. This situation arises frequently because database content and structure evolve, privacy policies slow manual review, and carefully written SQL labels are costly and time-consuming. Without timely evaluation, organizations cannot approve releases or detect failures early. FusionSQL addresses this gap by w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.07841","kind":"arxiv","version":2},"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/2603.07841/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":"2603.07841","created_at":"2026-07-28T01:22:31.131625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.07841v2","created_at":"2026-07-28T01:22:31.131625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.07841","created_at":"2026-07-28T01:22:31.131625+00:00"},{"alias_kind":"pith_short_12","alias_value":"APYB5ZRVH3VB","created_at":"2026-07-28T01:22:31.131625+00:00"},{"alias_kind":"pith_short_16","alias_value":"APYB5ZRVH3VBMR67","created_at":"2026-07-28T01:22:31.131625+00:00"},{"alias_kind":"pith_short_8","alias_value":"APYB5ZRV","created_at":"2026-07-28T01:22:31.131625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.23595","citing_title":"Learning to Evaluate: Cost-Effective Model Evaluation on Unlabeled Data with Meta-Learning","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH","json":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH.json","graph_json":"https://pith.science/api/pith-number/APYB5ZRVH3VBMR67J4E3C4WKUH/graph.json","events_json":"https://pith.science/api/pith-number/APYB5ZRVH3VBMR67J4E3C4WKUH/events.json","paper":"https://pith.science/paper/APYB5ZRV"},"agent_actions":{"view_html":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH","download_json":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH.json","view_paper":"https://pith.science/paper/APYB5ZRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.07841&json=true","fetch_graph":"https://pith.science/api/pith-number/APYB5ZRVH3VBMR67J4E3C4WKUH/graph.json","fetch_events":"https://pith.science/api/pith-number/APYB5ZRVH3VBMR67J4E3C4WKUH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH/action/storage_attestation","attest_author":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH/action/author_attestation","sign_citation":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH/action/citation_signature","submit_replication":"https://pith.science/pith/APYB5ZRVH3VBMR67J4E3C4WKUH/action/replication_record"}},"created_at":"2026-07-28T01:22:31.131625+00:00","updated_at":"2026-07-28T01:22:31.131625+00:00"}