{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P2TFLVQGYY7D5KICQFEH4WEW4U","short_pith_number":"pith:P2TFLVQG","schema_version":"1.0","canonical_sha256":"7ea655d606c63e3ea90281487e5896e51e7d3b7939dbd6a7ead5a8b53959c732","source":{"kind":"arxiv","id":"2606.04500","version":1},"attestation_state":"computed","paper":{"title":"SANE Schema-aware Natural-language Evaluation of Biological Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Markus Reischl, Martin Krueger, Rolf Gattung","submitted_at":"2026-06-03T06:31:28Z","abstract_excerpt":"High-throughput microscopy generates large, structured datasets capturing cellular responses to pharmacological perturbations, but accessing these datasets typically requires SQL expertise. Large language models offer a natural-language alternative, yet their tendency to hallucinate raises concerns about result reliability .\n  We present SANE Schema-Aware Natural-language Evaluation, a novel paradigm for domain-specific text-to-SQL evaluation: schema-grounded, automatically generated benchmarks tied to real and specific experimental structure. SANE makes evaluation more scalable, systematic, a"},"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":"2606.04500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-03T06:31:28Z","cross_cats_sorted":[],"title_canon_sha256":"778f0ada45957d266eb74f20ef9c22ea564b1bc068eb6fd91efe9357666a5b73","abstract_canon_sha256":"86b49071e9c60e628d3d80a07705de3be87e56bf2002f169a4a1cf3d63ca7ccb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:14.535343Z","signature_b64":"17bO9LmaIMBrF6fbkPM2zr+0F5QAcAdcM9pqk5V8r1yS8h811+mlg5DRoGRraQUdKW7WPa7UDWjmZTMbCmE3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea655d606c63e3ea90281487e5896e51e7d3b7939dbd6a7ead5a8b53959c732","last_reissued_at":"2026-06-04T01:09:14.534562Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:14.534562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SANE Schema-aware Natural-language Evaluation of Biological Data","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Markus Reischl, Martin Krueger, Rolf Gattung","submitted_at":"2026-06-03T06:31:28Z","abstract_excerpt":"High-throughput microscopy generates large, structured datasets capturing cellular responses to pharmacological perturbations, but accessing these datasets typically requires SQL expertise. Large language models offer a natural-language alternative, yet their tendency to hallucinate raises concerns about result reliability .\n  We present SANE Schema-Aware Natural-language Evaluation, a novel paradigm for domain-specific text-to-SQL evaluation: schema-grounded, automatically generated benchmarks tied to real and specific experimental structure. SANE makes evaluation more scalable, systematic, a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04500","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/2606.04500/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":"2606.04500","created_at":"2026-06-04T01:09:14.534675+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04500v1","created_at":"2026-06-04T01:09:14.534675+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04500","created_at":"2026-06-04T01:09:14.534675+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2TFLVQGYY7D","created_at":"2026-06-04T01:09:14.534675+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2TFLVQGYY7D5KIC","created_at":"2026-06-04T01:09:14.534675+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2TFLVQG","created_at":"2026-06-04T01:09:14.534675+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/P2TFLVQGYY7D5KICQFEH4WEW4U","json":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U.json","graph_json":"https://pith.science/api/pith-number/P2TFLVQGYY7D5KICQFEH4WEW4U/graph.json","events_json":"https://pith.science/api/pith-number/P2TFLVQGYY7D5KICQFEH4WEW4U/events.json","paper":"https://pith.science/paper/P2TFLVQG"},"agent_actions":{"view_html":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U","download_json":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U.json","view_paper":"https://pith.science/paper/P2TFLVQG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04500&json=true","fetch_graph":"https://pith.science/api/pith-number/P2TFLVQGYY7D5KICQFEH4WEW4U/graph.json","fetch_events":"https://pith.science/api/pith-number/P2TFLVQGYY7D5KICQFEH4WEW4U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U/action/storage_attestation","attest_author":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U/action/author_attestation","sign_citation":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U/action/citation_signature","submit_replication":"https://pith.science/pith/P2TFLVQGYY7D5KICQFEH4WEW4U/action/replication_record"}},"created_at":"2026-06-04T01:09:14.534675+00:00","updated_at":"2026-06-04T01:09:14.534675+00:00"}