{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ERFIK7CR5IX6SSFRTAIRM4VHAZ","short_pith_number":"pith:ERFIK7CR","schema_version":"1.0","canonical_sha256":"244a857c51ea2fe948b198111672a70643298ede2601bdab53700e76f058b1a5","source":{"kind":"arxiv","id":"2310.18208","version":3},"attestation_state":"computed","paper":{"title":"ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Feuer, Chinmay Hegde, Juliana Freire, Yurong Liu","submitted_at":"2023-10-27T15:31:22Z","abstract_excerpt":"Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a large number of training samples per type and incur large run-time inference costs; and their performance can degrade when evaluated on novel datasets, even when types remain constant. Large language models have exhibited strong zero-shot classification performance on a wide range of tasks and in this paper we explore their use for CTA. We introduce ArcheType, a simple, practical method for context sampling, prompt seria"},"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":"2310.18208","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T15:31:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0166b4a7018fe7969bff86d3ec69b260b4f507a65fc8c26e143a5d1548f5e1b3","abstract_canon_sha256":"bd521403837ca8a3ad0ee3ab9e6ee44c7d34a59f04ef1b4210c8ee18cdf43807"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:45.876187Z","signature_b64":"ERvJyr7+urjdAmrBSyasHr2kWQQjV4XxPXWFSEzohiuhoTA0dahDPVJ3vbyi9cy3Pq2FXVOdtuoYnw+V678rCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"244a857c51ea2fe948b198111672a70643298ede2601bdab53700e76f058b1a5","last_reissued_at":"2026-07-05T08:56:45.875670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:45.875670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Benjamin Feuer, Chinmay Hegde, Juliana Freire, Yurong Liu","submitted_at":"2023-10-27T15:31:22Z","abstract_excerpt":"Existing deep-learning approaches to semantic column type annotation (CTA) have important shortcomings: they rely on semantic types which are fixed at training time; require a large number of training samples per type and incur large run-time inference costs; and their performance can degrade when evaluated on novel datasets, even when types remain constant. Large language models have exhibited strong zero-shot classification performance on a wide range of tasks and in this paper we explore their use for CTA. We introduce ArcheType, a simple, practical method for context sampling, prompt seria"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18208","kind":"arxiv","version":3},"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/2310.18208/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":"2310.18208","created_at":"2026-07-05T08:56:45.875734+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18208v3","created_at":"2026-07-05T08:56:45.875734+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18208","created_at":"2026-07-05T08:56:45.875734+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERFIK7CR5IX6","created_at":"2026-07-05T08:56:45.875734+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERFIK7CR5IX6SSFR","created_at":"2026-07-05T08:56:45.875734+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERFIK7CR","created_at":"2026-07-05T08:56:45.875734+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.19314","citing_title":"LiveBench: A Challenging, Contamination-Limited LLM Benchmark","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ","json":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ.json","graph_json":"https://pith.science/api/pith-number/ERFIK7CR5IX6SSFRTAIRM4VHAZ/graph.json","events_json":"https://pith.science/api/pith-number/ERFIK7CR5IX6SSFRTAIRM4VHAZ/events.json","paper":"https://pith.science/paper/ERFIK7CR"},"agent_actions":{"view_html":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ","download_json":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ.json","view_paper":"https://pith.science/paper/ERFIK7CR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18208&json=true","fetch_graph":"https://pith.science/api/pith-number/ERFIK7CR5IX6SSFRTAIRM4VHAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/ERFIK7CR5IX6SSFRTAIRM4VHAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ/action/storage_attestation","attest_author":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ/action/author_attestation","sign_citation":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ/action/citation_signature","submit_replication":"https://pith.science/pith/ERFIK7CR5IX6SSFRTAIRM4VHAZ/action/replication_record"}},"created_at":"2026-07-05T08:56:45.875734+00:00","updated_at":"2026-07-05T08:56:45.875734+00:00"}