{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5RHDWABRK4HBKUGIMVT6HNPTPE","short_pith_number":"pith:5RHDWABR","canonical_record":{"source":{"id":"2408.16173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-28T23:39:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f1ec89f2aee040448da9a71cece644341e400a0891147c851061b6fa5827a3f","abstract_canon_sha256":"9babf2a31dbdb67f3f9f33ccced35a9f6ee96aedc71cda19c98b6fbd5f74a5c8"},"schema_version":"1.0"},"canonical_sha256":"ec4e3b0031570e1550c86567e3b5f3792906715da029cff87b76ac232d1706ad","source":{"kind":"arxiv","id":"2408.16173","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16173","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16173v1","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16173","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"pith_short_12","alias_value":"5RHDWABRK4HB","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"pith_short_16","alias_value":"5RHDWABRK4HBKUGI","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"pith_short_8","alias_value":"5RHDWABR","created_at":"2026-07-05T09:00:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5RHDWABRK4HBKUGIMVT6HNPTPE","target":"record","payload":{"canonical_record":{"source":{"id":"2408.16173","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-28T23:39:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f1ec89f2aee040448da9a71cece644341e400a0891147c851061b6fa5827a3f","abstract_canon_sha256":"9babf2a31dbdb67f3f9f33ccced35a9f6ee96aedc71cda19c98b6fbd5f74a5c8"},"schema_version":"1.0"},"canonical_sha256":"ec4e3b0031570e1550c86567e3b5f3792906715da029cff87b76ac232d1706ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:00:27.008785Z","signature_b64":"jDfmBirmxSriKJ5WL8drEoZFGQyI3+xZFjobhWxPgn3sLVCSg/QUKqiHLJPFh0/cpwjP9au+yUqHf0rtexFZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec4e3b0031570e1550c86567e3b5f3792906715da029cff87b76ac232d1706ad","last_reissued_at":"2026-07-05T09:00:27.008332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:00:27.008332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.16173","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:00:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rxh4HxZtJASYZX72muJbiCdmHRHbP87TJiKl3FEAN7pMvIWBO8Z+ZzEuSKvLJfzXD6jGP7odP+LITMqH+vSCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:33:31.661499Z"},"content_sha256":"a0ac69827c03a7349eb5ed9f71326c47d2034a68f7dbcc68990ebdba640940ae","schema_version":"1.0","event_id":"sha256:a0ac69827c03a7349eb5ed9f71326c47d2034a68f7dbcc68990ebdba640940ae"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5RHDWABRK4HBKUGIMVT6HNPTPE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLM-assisted Labeling Function Generation for Semantic Type Detection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Chenjie Li, Dan Zhang, Jin Wang","submitted_at":"2024-08-28T23:39:50Z","abstract_excerpt":"Detecting semantic types of columns in data lake tables is an important application. A key bottleneck in semantic type detection is the availability of human annotation due to the inherent complexity of data lakes. In this paper, we propose using programmatic weak supervision to assist in annotating the training data for semantic type detection by leveraging labeling functions. One challenge in this process is the difficulty of manually writing labeling functions due to the large volume and low quality of the data lake table datasets. To address this issue, we explore employing Large Language "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16173","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/2408.16173/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":"2026-07-05T09:00:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f67yMk0rkpP87n5o3yH1T+jAuvNj5/UYm5+DHEYzg4FfQ0/AfXa6kc+sRsxKqpzGDGyAwdkV/TjbdBm7lPfvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T03:33:31.662005Z"},"content_sha256":"07bae9cfba4163f804d16a11f5483227a484bfde60270f9cfea8b41f0ee74f0d","schema_version":"1.0","event_id":"sha256:07bae9cfba4163f804d16a11f5483227a484bfde60270f9cfea8b41f0ee74f0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RHDWABRK4HBKUGIMVT6HNPTPE/bundle.json","state_url":"https://pith.science/pith/5RHDWABRK4HBKUGIMVT6HNPTPE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RHDWABRK4HBKUGIMVT6HNPTPE/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":"2026-08-09T03:33:31Z","links":{"resolver":"https://pith.science/pith/5RHDWABRK4HBKUGIMVT6HNPTPE","bundle":"https://pith.science/pith/5RHDWABRK4HBKUGIMVT6HNPTPE/bundle.json","state":"https://pith.science/pith/5RHDWABRK4HBKUGIMVT6HNPTPE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RHDWABRK4HBKUGIMVT6HNPTPE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5RHDWABRK4HBKUGIMVT6HNPTPE","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":"9babf2a31dbdb67f3f9f33ccced35a9f6ee96aedc71cda19c98b6fbd5f74a5c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-28T23:39:50Z","title_canon_sha256":"5f1ec89f2aee040448da9a71cece644341e400a0891147c851061b6fa5827a3f"},"schema_version":"1.0","source":{"id":"2408.16173","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.16173","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"arxiv_version","alias_value":"2408.16173v1","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.16173","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"pith_short_12","alias_value":"5RHDWABRK4HB","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"pith_short_16","alias_value":"5RHDWABRK4HBKUGI","created_at":"2026-07-05T09:00:27Z"},{"alias_kind":"pith_short_8","alias_value":"5RHDWABR","created_at":"2026-07-05T09:00:27Z"}],"graph_snapshots":[{"event_id":"sha256:07bae9cfba4163f804d16a11f5483227a484bfde60270f9cfea8b41f0ee74f0d","target":"graph","created_at":"2026-07-05T09:00:27Z","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/2408.16173/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting semantic types of columns in data lake tables is an important application. A key bottleneck in semantic type detection is the availability of human annotation due to the inherent complexity of data lakes. In this paper, we propose using programmatic weak supervision to assist in annotating the training data for semantic type detection by leveraging labeling functions. One challenge in this process is the difficulty of manually writing labeling functions due to the large volume and low quality of the data lake table datasets. To address this issue, we explore employing Large Language ","authors_text":"Chenjie Li, Dan Zhang, Jin Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-28T23:39:50Z","title":"LLM-assisted Labeling Function Generation for Semantic Type Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.16173","kind":"arxiv","version":1},"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:a0ac69827c03a7349eb5ed9f71326c47d2034a68f7dbcc68990ebdba640940ae","target":"record","created_at":"2026-07-05T09:00:27Z","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":"9babf2a31dbdb67f3f9f33ccced35a9f6ee96aedc71cda19c98b6fbd5f74a5c8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.DB","submitted_at":"2024-08-28T23:39:50Z","title_canon_sha256":"5f1ec89f2aee040448da9a71cece644341e400a0891147c851061b6fa5827a3f"},"schema_version":"1.0","source":{"id":"2408.16173","kind":"arxiv","version":1}},"canonical_sha256":"ec4e3b0031570e1550c86567e3b5f3792906715da029cff87b76ac232d1706ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec4e3b0031570e1550c86567e3b5f3792906715da029cff87b76ac232d1706ad","first_computed_at":"2026-07-05T09:00:27.008332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:00:27.008332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jDfmBirmxSriKJ5WL8drEoZFGQyI3+xZFjobhWxPgn3sLVCSg/QUKqiHLJPFh0/cpwjP9au+yUqHf0rtexFZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:00:27.008785Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.16173","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a0ac69827c03a7349eb5ed9f71326c47d2034a68f7dbcc68990ebdba640940ae","sha256:07bae9cfba4163f804d16a11f5483227a484bfde60270f9cfea8b41f0ee74f0d"],"state_sha256":"20e66e08a697a5272cc5676cd3da6ffa88565663f770df8e52271ce099865fb6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BjsgSpPeRfobCZbCW+C9i5bUUTn0Dvba1fTYWbFk6gAPsh8o2I8lZ1UkvxY1X0zx25jtiEp0ntGrPQOIKpG8Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T03:33:31.666084Z","bundle_sha256":"7e73094a3752e406435b14bf434ebc6b594b8f8e5ddc045d68ef271f4bbbfc18"}}