{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7IF7AMXO62DYBDSDXNF3QRKV74","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":"5a36df6347a0586f5c82cde02130ee0c7591cae1f6db318e17fa862ea780f274","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T10:58:21Z","title_canon_sha256":"1e6c41fc9714eb0dcdeb03ec9d320a39f03ca82219961c8e51be0f52a66861c4"},"schema_version":"1.0","source":{"id":"2404.06209","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.06209","created_at":"2026-07-05T09:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2404.06209v3","created_at":"2026-07-05T09:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.06209","created_at":"2026-07-05T09:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"7IF7AMXO62DY","created_at":"2026-07-05T09:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"7IF7AMXO62DYBDSD","created_at":"2026-07-05T09:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"7IF7AMXO","created_at":"2026-07-05T09:44:08Z"}],"graph_snapshots":[{"event_id":"sha256:935d47ba51ca79be29f7a4c4a3240f53a1719ab26a5fcd8587916c948807bf58","target":"graph","created_at":"2026-07-05T09:44:08Z","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/2404.06209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While many have shown how Large Language Models (LLMs) can be applied to a diverse set of tasks, the critical issues of data contamination and memorization are often glossed over. In this work, we address this concern for tabular data. Specifically, we introduce a variety of different techniques to assess whether a language model has seen a tabular dataset during training. This investigation reveals that LLMs have memorized many popular tabular datasets verbatim. We then compare the few-shot learning performance of LLMs on datasets that were seen during training to the performance on datasets ","authors_text":"Besmira Nushi, Harsha Nori, Rich Caruana, Sebastian Bordt, Vanessa Rodrigues","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T10:58:21Z","title":"Elephants Never Forget: Memorization and Learning of Tabular Data in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.06209","kind":"arxiv","version":3},"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:f70005c673bf76e47566793af53d72868535a6c02ef3a5c3ffc12fcae7ca5dc3","target":"record","created_at":"2026-07-05T09:44:08Z","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":"5a36df6347a0586f5c82cde02130ee0c7591cae1f6db318e17fa862ea780f274","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T10:58:21Z","title_canon_sha256":"1e6c41fc9714eb0dcdeb03ec9d320a39f03ca82219961c8e51be0f52a66861c4"},"schema_version":"1.0","source":{"id":"2404.06209","kind":"arxiv","version":3}},"canonical_sha256":"fa0bf032eef687808e43bb4bb84555ff06189bd92e6ed13bc89ecc9f287c15ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa0bf032eef687808e43bb4bb84555ff06189bd92e6ed13bc89ecc9f287c15ab","first_computed_at":"2026-07-05T09:44:08.590605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:44:08.590605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"62eSZW0BRiMQPbcvMlLTI4y/ggbtq2G9s3bl9Ui7iGtogIt3vVKtfcklaGS2pcYI/mLGdcfHGm4CUNbD23vODg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:44:08.591096Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.06209","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f70005c673bf76e47566793af53d72868535a6c02ef3a5c3ffc12fcae7ca5dc3","sha256:935d47ba51ca79be29f7a4c4a3240f53a1719ab26a5fcd8587916c948807bf58"],"state_sha256":"0695180b7f91d512fbf1ec9cda3092610f6330b1db2816c2909afbde32acda69"}