{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:HEH3OCENNF67KPZHAJ2TXSWZ6T","short_pith_number":"pith:HEH3OCEN","canonical_record":{"source":{"id":"2409.14556","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-22T18:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7d19005af52e275acbd749818c9e69df371c854aaae2b81c5f67c44f5cb92bc","abstract_canon_sha256":"c1409ed03ddfe0c321a7a134675a11b60c39dd31453251148721fb45fb9be507"},"schema_version":"1.0"},"canonical_sha256":"390fb7088d697df53f2702753bcad9f4d9d7935f7eaac538750ea175a87fb0a4","source":{"kind":"arxiv","id":"2409.14556","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14556","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14556v2","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14556","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"HEH3OCENNF67","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"HEH3OCENNF67KPZH","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"HEH3OCEN","created_at":"2026-07-05T09:29:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:HEH3OCENNF67KPZHAJ2TXSWZ6T","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14556","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-22T18:39:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7d19005af52e275acbd749818c9e69df371c854aaae2b81c5f67c44f5cb92bc","abstract_canon_sha256":"c1409ed03ddfe0c321a7a134675a11b60c39dd31453251148721fb45fb9be507"},"schema_version":"1.0"},"canonical_sha256":"390fb7088d697df53f2702753bcad9f4d9d7935f7eaac538750ea175a87fb0a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:33.482436Z","signature_b64":"snQFO2EOvuFWvGZ+osQER5wqZKHdDcaGLLiO8GuXTC+tXlg1xrjcWSRtq+nvk8kGL62HfO4bHG5redT5pP0bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"390fb7088d697df53f2702753bcad9f4d9d7935f7eaac538750ea175a87fb0a4","last_reissued_at":"2026-07-05T09:29:33.481990Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:33.481990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14556","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8BMWPZnHyeJuBaJD5tyzAIu4JlRo3mrcemVhc1++Rn4lL5NOwpaZKpJkum2kIA9dALbkBjutENAHGtQJCXySBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T06:37:24.231209Z"},"content_sha256":"eb7294dcbf20d4d764a2b733295b0e7e471d61e4872ca277a3e7d1e00d378e28","schema_version":"1.0","event_id":"sha256:eb7294dcbf20d4d764a2b733295b0e7e471d61e4872ca277a3e7d1e00d378e28"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:HEH3OCENNF67KPZHAJ2TXSWZ6T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Guorui Xiao, Lindsey Linxi Wei, Magdalena Balazinska","submitted_at":"2024-09-22T18:39:27Z","abstract_excerpt":"As an important component of data exploration and integration, Column Type Annotation (CTA) aims to label columns of a table with one or more semantic types. With the recent development of Large Language Models (LLMs), researchers have started to explore the possibility of using LLMs for CTA, leveraging their strong zero-shot capabilities. In this paper, we build on this promising work and improve on LLM-based methods for CTA by showing how to use a Knowledge Graph (KG) to augment the context information provided to the LLM. Our approach, called RACOON, combines both pre-trained parametric and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14556","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/2409.14556/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6/IS8SjhvJi7wzIjR0+JhUBNT2bSyhZm5oi77R4sp/fdSsuw0A9j52KRRbxKiHHAlaBUb80p4FUgvjr1r9aEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-26T06:37:24.231619Z"},"content_sha256":"cabe24ff01b2f161e6b835f61ef1c2d27d0eb4cac016c524937df2fe73943bb0","schema_version":"1.0","event_id":"sha256:cabe24ff01b2f161e6b835f61ef1c2d27d0eb4cac016c524937df2fe73943bb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T/bundle.json","state_url":"https://pith.science/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-26T06:37:24Z","links":{"resolver":"https://pith.science/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T","bundle":"https://pith.science/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T/bundle.json","state":"https://pith.science/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HEH3OCENNF67KPZHAJ2TXSWZ6T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:HEH3OCENNF67KPZHAJ2TXSWZ6T","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":"c1409ed03ddfe0c321a7a134675a11b60c39dd31453251148721fb45fb9be507","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-22T18:39:27Z","title_canon_sha256":"d7d19005af52e275acbd749818c9e69df371c854aaae2b81c5f67c44f5cb92bc"},"schema_version":"1.0","source":{"id":"2409.14556","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14556","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14556v2","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14556","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"HEH3OCENNF67","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"HEH3OCENNF67KPZH","created_at":"2026-07-05T09:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"HEH3OCEN","created_at":"2026-07-05T09:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:cabe24ff01b2f161e6b835f61ef1c2d27d0eb4cac016c524937df2fe73943bb0","target":"graph","created_at":"2026-07-05T09:29:33Z","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/2409.14556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As an important component of data exploration and integration, Column Type Annotation (CTA) aims to label columns of a table with one or more semantic types. With the recent development of Large Language Models (LLMs), researchers have started to explore the possibility of using LLMs for CTA, leveraging their strong zero-shot capabilities. In this paper, we build on this promising work and improve on LLM-based methods for CTA by showing how to use a Knowledge Graph (KG) to augment the context information provided to the LLM. Our approach, called RACOON, combines both pre-trained parametric and","authors_text":"Guorui Xiao, Lindsey Linxi Wei, Magdalena Balazinska","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-22T18:39:27Z","title":"RACOON: An LLM-based Framework for Retrieval-Augmented Column Type Annotation with a Knowledge Graph"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14556","kind":"arxiv","version":2},"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:eb7294dcbf20d4d764a2b733295b0e7e471d61e4872ca277a3e7d1e00d378e28","target":"record","created_at":"2026-07-05T09:29:33Z","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":"c1409ed03ddfe0c321a7a134675a11b60c39dd31453251148721fb45fb9be507","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-09-22T18:39:27Z","title_canon_sha256":"d7d19005af52e275acbd749818c9e69df371c854aaae2b81c5f67c44f5cb92bc"},"schema_version":"1.0","source":{"id":"2409.14556","kind":"arxiv","version":2}},"canonical_sha256":"390fb7088d697df53f2702753bcad9f4d9d7935f7eaac538750ea175a87fb0a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"390fb7088d697df53f2702753bcad9f4d9d7935f7eaac538750ea175a87fb0a4","first_computed_at":"2026-07-05T09:29:33.481990Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:33.481990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snQFO2EOvuFWvGZ+osQER5wqZKHdDcaGLLiO8GuXTC+tXlg1xrjcWSRtq+nvk8kGL62HfO4bHG5redT5pP0bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:33.482436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14556","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb7294dcbf20d4d764a2b733295b0e7e471d61e4872ca277a3e7d1e00d378e28","sha256:cabe24ff01b2f161e6b835f61ef1c2d27d0eb4cac016c524937df2fe73943bb0"],"state_sha256":"1b38d13ee032dd35cc3b76ca736a38f816f4ced984e971039402991adf3b88ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mAxDaaj2gyRFX4fn3OIPcAAZjr66sWE9WTxMfti7/Htim80WAOyL3PqpSJ1zedezpq6DVMw+yi5+3J2Nw747Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-26T06:37:24.233992Z","bundle_sha256":"c3af611e85c287d42b0967b7aed7e89a215fb8d07206cb98617eda3105c2c722"}}