{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DSPWO4IHQY762ZDSNJQEDLPILN","short_pith_number":"pith:DSPWO4IH","schema_version":"1.0","canonical_sha256":"1c9f677107863fed64726a6041ade85b430340c7cf01ded4ebe0a9d5392b2d39","source":{"kind":"arxiv","id":"2304.13188","version":1},"attestation_state":"computed","paper":{"title":"TABLET: Learning From Instructions For Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dylan Slack, Sameer Singh","submitted_at":"2023-04-25T23:07:20Z","abstract_excerpt":"Acquiring high-quality data is often a significant challenge in training machine learning (ML) models for tabular prediction, particularly in privacy-sensitive and costly domains like medicine and finance. Providing natural language instructions to large language models (LLMs) offers an alternative solution. However, it is unclear how effectively instructions leverage the knowledge in LLMs for solving tabular prediction problems. To address this gap, we introduce TABLET, a benchmark of 20 diverse tabular datasets annotated with instructions that vary in their phrasing, granularity, and technic"},"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":"2304.13188","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-04-25T23:07:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"605190dd31ef74a49d14140c9d49b9b6adcb966f30669fad1e5381fa22d1b2a8","abstract_canon_sha256":"178fdd79745a03955fcfba382d44a0349bebdff2177456234beb74028e4d75bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:40.727198Z","signature_b64":"gVUP+OWfRFzFDrmdn7oM1hRLaqQUrN2H4lq5OCOeKfMTPt5G294ghTs4bAYN2ymcwy3WEEPCgL5p88XxvSYIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c9f677107863fed64726a6041ade85b430340c7cf01ded4ebe0a9d5392b2d39","last_reissued_at":"2026-07-05T06:04:40.726772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:40.726772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TABLET: Learning From Instructions For Tabular Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Dylan Slack, Sameer Singh","submitted_at":"2023-04-25T23:07:20Z","abstract_excerpt":"Acquiring high-quality data is often a significant challenge in training machine learning (ML) models for tabular prediction, particularly in privacy-sensitive and costly domains like medicine and finance. Providing natural language instructions to large language models (LLMs) offers an alternative solution. However, it is unclear how effectively instructions leverage the knowledge in LLMs for solving tabular prediction problems. To address this gap, we introduce TABLET, a benchmark of 20 diverse tabular datasets annotated with instructions that vary in their phrasing, granularity, and technic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.13188","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/2304.13188/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":"2304.13188","created_at":"2026-07-05T06:04:40.726831+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.13188v1","created_at":"2026-07-05T06:04:40.726831+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.13188","created_at":"2026-07-05T06:04:40.726831+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSPWO4IHQY76","created_at":"2026-07-05T06:04:40.726831+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSPWO4IHQY762ZDS","created_at":"2026-07-05T06:04:40.726831+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSPWO4IH","created_at":"2026-07-05T06:04:40.726831+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11640","citing_title":"TAROT: Task-Adaptive Refinement of LLM-prior Graphs for Few-shot Tabular Learning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24417","citing_title":"LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2403.20208","citing_title":"Unlock the Potential of Large Language Models for Predictive Tabular Tasks in Data Science with Table-Specific Pretraining","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13392","citing_title":"ReSS: Learning Reasoning Models for Tabular Data Prediction via Symbolic Scaffold","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN","json":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN.json","graph_json":"https://pith.science/api/pith-number/DSPWO4IHQY762ZDSNJQEDLPILN/graph.json","events_json":"https://pith.science/api/pith-number/DSPWO4IHQY762ZDSNJQEDLPILN/events.json","paper":"https://pith.science/paper/DSPWO4IH"},"agent_actions":{"view_html":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN","download_json":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN.json","view_paper":"https://pith.science/paper/DSPWO4IH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.13188&json=true","fetch_graph":"https://pith.science/api/pith-number/DSPWO4IHQY762ZDSNJQEDLPILN/graph.json","fetch_events":"https://pith.science/api/pith-number/DSPWO4IHQY762ZDSNJQEDLPILN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN/action/storage_attestation","attest_author":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN/action/author_attestation","sign_citation":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN/action/citation_signature","submit_replication":"https://pith.science/pith/DSPWO4IHQY762ZDSNJQEDLPILN/action/replication_record"}},"created_at":"2026-07-05T06:04:40.726831+00:00","updated_at":"2026-07-05T06:04:40.726831+00:00"}