{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:5YOAFYQPLKIXMHVF2IBKBGUDZL","short_pith_number":"pith:5YOAFYQP","schema_version":"1.0","canonical_sha256":"ee1c02e20f5a91761ea5d202a09a83cad913b78e25178a1d1bbc305a1da87995","source":{"kind":"arxiv","id":"2312.12464","version":2},"attestation_state":"computed","paper":{"title":"Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ashish Shugani, Razik Singh Grewal, Sukriti Jaitly, Tanay Shah","submitted_at":"2023-12-18T21:11:17Z","abstract_excerpt":"We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization techniques, including the standout LaTeX serialization method. This method significantly boosts the performance of LLMs in processing domain-specific datasets, Our method stands out for its memory efficiency and ability to fully utilize complex data structures. Through extensive experimentation, including various serialization approaches like feature combina"},"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":"2312.12464","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-18T21:11:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"7baf6f98be51bf1b2ad6c58a9ae15bd5046832f22c331360a8a104381eb58d3a","abstract_canon_sha256":"4191441492a82bfa088060d9d0498a9545a12caf3131c32a97185237382a4aba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:26:42.548981Z","signature_b64":"hOmDjdvEFrjC+h2jJapRWZSQyyPVZNrbq0U8xZFZNLmRrtVfg4T2tkOOGcdNw3C7VOShM+BqRH+YVZUsCIn4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee1c02e20f5a91761ea5d202a09a83cad913b78e25178a1d1bbc305a1da87995","last_reissued_at":"2026-07-05T07:26:42.548482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:26:42.548482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Better Serialization of Tabular Data for Few-shot Classification with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ashish Shugani, Razik Singh Grewal, Sukriti Jaitly, Tanay Shah","submitted_at":"2023-12-18T21:11:17Z","abstract_excerpt":"We present a study on the integration of Large Language Models (LLMs) in tabular data classification, emphasizing an efficient framework. Building upon existing work done in TabLLM (arXiv:2210.10723), we introduce three novel serialization techniques, including the standout LaTeX serialization method. This method significantly boosts the performance of LLMs in processing domain-specific datasets, Our method stands out for its memory efficiency and ability to fully utilize complex data structures. Through extensive experimentation, including various serialization approaches like feature combina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12464","kind":"arxiv","version":2},"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/2312.12464/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":"2312.12464","created_at":"2026-07-05T07:26:42.548545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.12464v2","created_at":"2026-07-05T07:26:42.548545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12464","created_at":"2026-07-05T07:26:42.548545+00:00"},{"alias_kind":"pith_short_12","alias_value":"5YOAFYQPLKIX","created_at":"2026-07-05T07:26:42.548545+00:00"},{"alias_kind":"pith_short_16","alias_value":"5YOAFYQPLKIXMHVF","created_at":"2026-07-05T07:26:42.548545+00:00"},{"alias_kind":"pith_short_8","alias_value":"5YOAFYQP","created_at":"2026-07-05T07:26:42.548545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24417","citing_title":"LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04323","citing_title":"LUCAS-MEGA: A Large-Scale Multimodal Dataset for Representation Learning in Soil-Environment Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04323","citing_title":"LUCAS-MEGA: A Large-Scale Multimodal Dataset for Representation Learning in Soil-Environment Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18305","citing_title":"CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL","json":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL.json","graph_json":"https://pith.science/api/pith-number/5YOAFYQPLKIXMHVF2IBKBGUDZL/graph.json","events_json":"https://pith.science/api/pith-number/5YOAFYQPLKIXMHVF2IBKBGUDZL/events.json","paper":"https://pith.science/paper/5YOAFYQP"},"agent_actions":{"view_html":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL","download_json":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL.json","view_paper":"https://pith.science/paper/5YOAFYQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.12464&json=true","fetch_graph":"https://pith.science/api/pith-number/5YOAFYQPLKIXMHVF2IBKBGUDZL/graph.json","fetch_events":"https://pith.science/api/pith-number/5YOAFYQPLKIXMHVF2IBKBGUDZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL/action/storage_attestation","attest_author":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL/action/author_attestation","sign_citation":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL/action/citation_signature","submit_replication":"https://pith.science/pith/5YOAFYQPLKIXMHVF2IBKBGUDZL/action/replication_record"}},"created_at":"2026-07-05T07:26:42.548545+00:00","updated_at":"2026-07-05T07:26:42.548545+00:00"}