{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ESZEUUKYM2IHDNYNEBQT35ESD4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"459becd59277e315394295bfcdc86e1f83c7ef52b1289c35712f2205b9b73f6c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T22:35:40Z","title_canon_sha256":"7706777c501852355228f218824076905b433647220349190c844a43463dc8ed"},"schema_version":"1.0","source":{"id":"2402.08100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.08100","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"arxiv_version","alias_value":"2402.08100v1","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.08100","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"pith_short_12","alias_value":"ESZEUUKYM2IH","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"pith_short_16","alias_value":"ESZEUUKYM2IHDNYN","created_at":"2026-07-05T09:45:44Z"},{"alias_kind":"pith_short_8","alias_value":"ESZEUUKY","created_at":"2026-07-05T09:45:44Z"}],"graph_snapshots":[{"event_id":"sha256:4119ef48d9cad8d71bd1241dba55b04079263eb3c442df9e95c96904dace6e5c","target":"graph","created_at":"2026-07-05T09:45:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2402.08100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding textual description to generate code seems to be an achieved capability of instruction-following Large Language Models (LLMs) in zero-shot scenario. However, there is a severe possibility that this translation ability may be influenced by having seen target textual descriptions and the related code. This effect is known as Data Contamination.\n  In this study, we investigate the impact of Data Contamination on the performance of GPT-3.5 in the Text-to-SQL code-generating tasks. Hence, we introduce a novel method to detect Data Contamination in GPTs and examine GPT-3.5's Text-to-SQ","authors_text":"Andrea Favalli, Cristina Giannone, Dario Onorati, Elena Sofia Ruzzetti, Fabio Massimo Zanzotto, Federico Ranaldi, Leonardo Ranaldi, Raniero Romagnoli","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T22:35:40Z","title":"Investigating the Impact of Data Contamination of Large Language Models in Text-to-SQL Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.08100","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a390847d394c465e815fa10ee16d5aeb7b30ca6c1bc4b90ba611a6c94a3e7458","target":"record","created_at":"2026-07-05T09:45:44Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"459becd59277e315394295bfcdc86e1f83c7ef52b1289c35712f2205b9b73f6c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-12T22:35:40Z","title_canon_sha256":"7706777c501852355228f218824076905b433647220349190c844a43463dc8ed"},"schema_version":"1.0","source":{"id":"2402.08100","kind":"arxiv","version":1}},"canonical_sha256":"24b24a5158669071b70d20613df4921f27e76a2be670f490c676494e87c8f012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24b24a5158669071b70d20613df4921f27e76a2be670f490c676494e87c8f012","first_computed_at":"2026-07-05T09:45:44.273728Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:45:44.273728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HgE/59Q1cyyWX78Qbn7GkAP+zHj5mG33czldXPEs108obaOHecdZWpCqS0cr9Y4mCkF5E9pIIgc5Wkm72cidAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:45:44.274199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.08100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a390847d394c465e815fa10ee16d5aeb7b30ca6c1bc4b90ba611a6c94a3e7458","sha256:4119ef48d9cad8d71bd1241dba55b04079263eb3c442df9e95c96904dace6e5c"],"state_sha256":"2e860592688a6dfc2c3bcd07d9f53877f7c90dcba08978eafc9b483046b14cea"}