{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ERFIK7CR5IX6SSFRTAIRM4VHAZ","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":"bd521403837ca8a3ad0ee3ab9e6ee44c7d34a59f04ef1b4210c8ee18cdf43807","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T15:31:22Z","title_canon_sha256":"0166b4a7018fe7969bff86d3ec69b260b4f507a65fc8c26e143a5d1548f5e1b3"},"schema_version":"1.0","source":{"id":"2310.18208","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.18208","created_at":"2026-07-05T08:56:45Z"},{"alias_kind":"arxiv_version","alias_value":"2310.18208v3","created_at":"2026-07-05T08:56:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18208","created_at":"2026-07-05T08:56:45Z"},{"alias_kind":"pith_short_12","alias_value":"ERFIK7CR5IX6","created_at":"2026-07-05T08:56:45Z"},{"alias_kind":"pith_short_16","alias_value":"ERFIK7CR5IX6SSFR","created_at":"2026-07-05T08:56:45Z"},{"alias_kind":"pith_short_8","alias_value":"ERFIK7CR","created_at":"2026-07-05T08:56:45Z"}],"graph_snapshots":[{"event_id":"sha256:b312d7b1288a7a7310e0a418124c01a56218ffda064a84c8d62c9c76664399eb","target":"graph","created_at":"2026-07-05T08:56:45Z","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/2310.18208/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benjamin Feuer, Chinmay Hegde, Juliana Freire, Yurong Liu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T15:31:22Z","title":"ArcheType: A Novel Framework for Open-Source Column Type Annotation using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18208","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":"sha256:56cc2fb07bfd722d7bed318b90dfef70e745711c8b79f4ca76edbda4d55f4921","target":"record","created_at":"2026-07-05T08:56:45Z","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":"bd521403837ca8a3ad0ee3ab9e6ee44c7d34a59f04ef1b4210c8ee18cdf43807","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-27T15:31:22Z","title_canon_sha256":"0166b4a7018fe7969bff86d3ec69b260b4f507a65fc8c26e143a5d1548f5e1b3"},"schema_version":"1.0","source":{"id":"2310.18208","kind":"arxiv","version":3}},"canonical_sha256":"244a857c51ea2fe948b198111672a70643298ede2601bdab53700e76f058b1a5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"244a857c51ea2fe948b198111672a70643298ede2601bdab53700e76f058b1a5","first_computed_at":"2026-07-05T08:56:45.875670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:45.875670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ERvJyr7+urjdAmrBSyasHr2kWQQjV4XxPXWFSEzohiuhoTA0dahDPVJ3vbyi9cy3Pq2FXVOdtuoYnw+V678rCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:45.876187Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.18208","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56cc2fb07bfd722d7bed318b90dfef70e745711c8b79f4ca76edbda4d55f4921","sha256:b312d7b1288a7a7310e0a418124c01a56218ffda064a84c8d62c9c76664399eb"],"state_sha256":"bb2c7d1febdcba5c9bd0522c8e8eb855819ea0c82ae07241fc9b9402e864cf98"}