{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AKVAT3NLUKLBTMK2I3CHGMKAWG","short_pith_number":"pith:AKVAT3NL","schema_version":"1.0","canonical_sha256":"02aa09edaba29619b15a46c4733140b18f31de30905933f1c533d1d8283361e8","source":{"kind":"arxiv","id":"2605.24417","version":1},"attestation_state":"computed","paper":{"title":"LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alina Kostromina, Aziz Temirkhanov, Daria Grushina, Dmitry Simakov, Kseniia Kuvshinova, Mile Mitrovic","submitted_at":"2026-05-23T06:05:20Z","abstract_excerpt":"Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data-scarce domains. For such few-shot scenarios, specialized methods like TabPFN - a state-of-the-art Prior-Data Fitted Network - have set a high standard by leveraging large-scale synthetic pretraining, though they still require a context of labeled examples to function. In contrast, Large Language Models (LLMs) could offer a more flexible alternative via zero- and few-shot in-context learning directly from task descriptions, but their performanc"},"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":"2605.24417","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-23T06:05:20Z","cross_cats_sorted":[],"title_canon_sha256":"3b6a05edd9914b173b0bb5ee5cc4189f9ec17dea4e77eeed6ce232ff613044ed","abstract_canon_sha256":"6e8be907c6e8c7744668f089550d4c95f6669adacae3385911a5e1ed6bfb296c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:38.702255Z","signature_b64":"N4+Emr//6zkbQgFcvKq28t63Q4jP/9gWsePifDBkDy4Wqx9Jho8aVeE4iCYn+oxx8LxnruwWNGr4M/fkVEaoCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02aa09edaba29619b15a46c4733140b18f31de30905933f1c533d1d8283361e8","last_reissued_at":"2026-05-26T01:03:38.701444Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:38.701444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alina Kostromina, Aziz Temirkhanov, Daria Grushina, Dmitry Simakov, Kseniia Kuvshinova, Mile Mitrovic","submitted_at":"2026-05-23T06:05:20Z","abstract_excerpt":"Supervised classification for tabular data remains a core machine learning task, yet its reliance on large labeled datasets limits applicability in data-scarce domains. For such few-shot scenarios, specialized methods like TabPFN - a state-of-the-art Prior-Data Fitted Network - have set a high standard by leveraging large-scale synthetic pretraining, though they still require a context of labeled examples to function. In contrast, Large Language Models (LLMs) could offer a more flexible alternative via zero- and few-shot in-context learning directly from task descriptions, but their performanc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24417","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/2605.24417/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":"2605.24417","created_at":"2026-05-26T01:03:38.701570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24417v1","created_at":"2026-05-26T01:03:38.701570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24417","created_at":"2026-05-26T01:03:38.701570+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKVAT3NLUKLB","created_at":"2026-05-26T01:03:38.701570+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKVAT3NLUKLBTMK2","created_at":"2026-05-26T01:03:38.701570+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKVAT3NL","created_at":"2026-05-26T01:03:38.701570+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/AKVAT3NLUKLBTMK2I3CHGMKAWG","json":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG.json","graph_json":"https://pith.science/api/pith-number/AKVAT3NLUKLBTMK2I3CHGMKAWG/graph.json","events_json":"https://pith.science/api/pith-number/AKVAT3NLUKLBTMK2I3CHGMKAWG/events.json","paper":"https://pith.science/paper/AKVAT3NL"},"agent_actions":{"view_html":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG","download_json":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG.json","view_paper":"https://pith.science/paper/AKVAT3NL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24417&json=true","fetch_graph":"https://pith.science/api/pith-number/AKVAT3NLUKLBTMK2I3CHGMKAWG/graph.json","fetch_events":"https://pith.science/api/pith-number/AKVAT3NLUKLBTMK2I3CHGMKAWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG/action/storage_attestation","attest_author":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG/action/author_attestation","sign_citation":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG/action/citation_signature","submit_replication":"https://pith.science/pith/AKVAT3NLUKLBTMK2I3CHGMKAWG/action/replication_record"}},"created_at":"2026-05-26T01:03:38.701570+00:00","updated_at":"2026-05-26T01:03:38.701570+00:00"}