{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NQ2SYCIZSXSHAJUM3IG74F3VT5","short_pith_number":"pith:NQ2SYCIZ","canonical_record":{"source":{"id":"2406.16349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T06:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"2c922961c959351b927a9ca54fbb7951c32f20c1c9b0642f8b8bc5ef33025cd5","abstract_canon_sha256":"21a1fadee44a0f29edfc9f57e690d633664fcc43b797bc7260d9103b526134b6"},"schema_version":"1.0"},"canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","source":{"kind":"arxiv","id":"2406.16349","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16349","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16349v1","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16349","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"NQ2SYCIZSXSH","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"NQ2SYCIZSXSHAJUM","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"NQ2SYCIZ","created_at":"2026-07-05T08:35:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NQ2SYCIZSXSHAJUM3IG74F3VT5","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16349","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T06:44:14Z","cross_cats_sorted":[],"title_canon_sha256":"2c922961c959351b927a9ca54fbb7951c32f20c1c9b0642f8b8bc5ef33025cd5","abstract_canon_sha256":"21a1fadee44a0f29edfc9f57e690d633664fcc43b797bc7260d9103b526134b6"},"schema_version":"1.0"},"canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:57.125034Z","signature_b64":"pWnE+YoeaHUayZRCalxPsJ0xR2NMOsTw23rcxEa6mSk9OxLysjemB03YzE8JwxU1XGza6kdrWUu2rdoEsVuxAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","last_reissued_at":"2026-07-05T08:35:57.124548Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:57.124548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16349","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":"2026-07-05T08:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hIMgle0HXR3D3V4nTWivqaoioHfVUHTRVuGeCSbSSmzlvO0lHKu0zVyJnG6c+NiaAdJ5Vh8r7UelyQpWfCwzDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:20:03.843250Z"},"content_sha256":"ae3b0ed9dab37c19840d5aec945cdbfbf30f688771244139459b48489b692547","schema_version":"1.0","event_id":"sha256:ae3b0ed9dab37c19840d5aec945cdbfbf30f688771244139459b48489b692547"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NQ2SYCIZSXSHAJUM3IG74F3VT5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AnnotatedTables: A Large Tabular Dataset with Language Model Annotations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ilias Fountalis, Jin Tian, Nikolaos Vasiloglou, Yaojie Hu","submitted_at":"2024-06-24T06:44:14Z","abstract_excerpt":"Tabular data is ubiquitous in real-world applications and abundant on the web, yet its annotation has traditionally required human labor, posing a significant scalability bottleneck for tabular machine learning. Our methodology can successfully annotate a large amount of tabular data and can be flexibly steered to generate various types of annotations based on specific research objectives, as we demonstrate with SQL annotation and input-target column annotation as examples. As a result, we release AnnotatedTables, a collection of 32,119 databases with LLM-generated annotations. The dataset inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16349","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/2406.16349/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":"2026-07-05T08:35:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ravRwZnA9mKXgL7pYgM13bjsZI4OwT2Vf+dTA2stTus1Py0s2TygXcxJnS/ZxKE8zyBUovHdsSxE2gaGM9hfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T03:20:03.843629Z"},"content_sha256":"7a29ef9b2eea4bc4cb135e8d4c60118710b0e3075afc0d0aef88367adb0b0d20","schema_version":"1.0","event_id":"sha256:7a29ef9b2eea4bc4cb135e8d4c60118710b0e3075afc0d0aef88367adb0b0d20"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/bundle.json","state_url":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/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":"2026-07-07T03:20:03Z","links":{"resolver":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5","bundle":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/bundle.json","state":"https://pith.science/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NQ2SYCIZSXSHAJUM3IG74F3VT5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NQ2SYCIZSXSHAJUM3IG74F3VT5","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":"21a1fadee44a0f29edfc9f57e690d633664fcc43b797bc7260d9103b526134b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T06:44:14Z","title_canon_sha256":"2c922961c959351b927a9ca54fbb7951c32f20c1c9b0642f8b8bc5ef33025cd5"},"schema_version":"1.0","source":{"id":"2406.16349","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16349","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16349v1","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16349","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_12","alias_value":"NQ2SYCIZSXSH","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_16","alias_value":"NQ2SYCIZSXSHAJUM","created_at":"2026-07-05T08:35:57Z"},{"alias_kind":"pith_short_8","alias_value":"NQ2SYCIZ","created_at":"2026-07-05T08:35:57Z"}],"graph_snapshots":[{"event_id":"sha256:7a29ef9b2eea4bc4cb135e8d4c60118710b0e3075afc0d0aef88367adb0b0d20","target":"graph","created_at":"2026-07-05T08:35:57Z","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/2406.16349/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data is ubiquitous in real-world applications and abundant on the web, yet its annotation has traditionally required human labor, posing a significant scalability bottleneck for tabular machine learning. Our methodology can successfully annotate a large amount of tabular data and can be flexibly steered to generate various types of annotations based on specific research objectives, as we demonstrate with SQL annotation and input-target column annotation as examples. As a result, we release AnnotatedTables, a collection of 32,119 databases with LLM-generated annotations. The dataset inc","authors_text":"Ilias Fountalis, Jin Tian, Nikolaos Vasiloglou, Yaojie Hu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T06:44:14Z","title":"AnnotatedTables: A Large Tabular Dataset with Language Model Annotations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16349","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:ae3b0ed9dab37c19840d5aec945cdbfbf30f688771244139459b48489b692547","target":"record","created_at":"2026-07-05T08:35:57Z","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":"21a1fadee44a0f29edfc9f57e690d633664fcc43b797bc7260d9103b526134b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-24T06:44:14Z","title_canon_sha256":"2c922961c959351b927a9ca54fbb7951c32f20c1c9b0642f8b8bc5ef33025cd5"},"schema_version":"1.0","source":{"id":"2406.16349","kind":"arxiv","version":1}},"canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c352c091995e470268cda0dfe17759f7d259149f61895b83744c36e7dd9963e","first_computed_at":"2026-07-05T08:35:57.124548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:35:57.124548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pWnE+YoeaHUayZRCalxPsJ0xR2NMOsTw23rcxEa6mSk9OxLysjemB03YzE8JwxU1XGza6kdrWUu2rdoEsVuxAw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:35:57.125034Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16349","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae3b0ed9dab37c19840d5aec945cdbfbf30f688771244139459b48489b692547","sha256:7a29ef9b2eea4bc4cb135e8d4c60118710b0e3075afc0d0aef88367adb0b0d20"],"state_sha256":"4cd71782aab9f587081db4306885ca6754bd2f80d4f5887ff0b949457408c8af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ompKucgC4dZzymTy4VK/OP11/w0gOuMRTgHYqQ0UgofL7FLrGshmbz3QDdKu0KFWdiHZFQ6c6gxit5H5QTjuBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T03:20:03.845887Z","bundle_sha256":"b532ba350d2466b12e49d290ba142c60758339210f8855eb104c51ee5308e171"}}