{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YCAUBQNUB2VRA47TBWYMORHV3B","short_pith_number":"pith:YCAUBQNU","canonical_record":{"source":{"id":"2307.12807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-24T13:58:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3e25a1cb6722efa41bc11394370fa5bdfae6260cf4551c9857c6e082aa23ddf","abstract_canon_sha256":"90983724a50fa8a5f2fc21e1abe19161b4199396f38637cc050434697e346ea7"},"schema_version":"1.0"},"canonical_sha256":"c08140c1b40eab1073f30db0c744f5d84490eba1a7173a48f6e3d8c6542703f6","source":{"kind":"arxiv","id":"2307.12807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12807","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12807v1","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12807","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"YCAUBQNUB2VR","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"YCAUBQNUB2VRA47T","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"YCAUBQNU","created_at":"2026-07-05T07:56:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YCAUBQNUB2VRA47TBWYMORHV3B","target":"record","payload":{"canonical_record":{"source":{"id":"2307.12807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-24T13:58:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3e25a1cb6722efa41bc11394370fa5bdfae6260cf4551c9857c6e082aa23ddf","abstract_canon_sha256":"90983724a50fa8a5f2fc21e1abe19161b4199396f38637cc050434697e346ea7"},"schema_version":"1.0"},"canonical_sha256":"c08140c1b40eab1073f30db0c744f5d84490eba1a7173a48f6e3d8c6542703f6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:16.327098Z","signature_b64":"fx1POpQRXpgjKy9g2W2cEqbjog3IEPOzvkbfTTZBRxZ2xppC5EZopS6eiZi1+Cg0s4MAz3NBlY7Tm+f4VMLRBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c08140c1b40eab1073f30db0c744f5d84490eba1a7173a48f6e3d8c6542703f6","last_reissued_at":"2026-07-05T07:56:16.326621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:16.326621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.12807","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":"2026-07-05T07:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vmDjhIbAyOiUKxNK42ZDg42IV9rn1TnUahbbdvU7w7JwRKli9qcf8sCG2Qn/n2PZyBhJsNteA3sLHxA7/c4sAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:58:16.132994Z"},"content_sha256":"3b27ea0eff269ee14a9814401f91e7cfe74edf66e95764ddd1d5b85bc1781c12","schema_version":"1.0","event_id":"sha256:3b27ea0eff269ee14a9814401f91e7cfe74edf66e95764ddd1d5b85bc1781c12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YCAUBQNUB2VRA47TBWYMORHV3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Comprehending Semantic Types in JSON Data with Graph Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Michael J. Mior, Shuang Wei","submitted_at":"2023-07-24T13:58:15Z","abstract_excerpt":"Semantic types are a more powerful and detailed way of describing data than atomic types such as strings or integers. They establish connections between columns and concepts from the real world, providing more nuanced and fine-grained information that can be useful for tasks such as automated data cleaning, schema matching, and data discovery. Existing deep learning models trained on large text corpora have been successful at performing single-column semantic type prediction for relational data. However, in this work, we propose an extension of the semantic type prediction problem to JSON data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12807","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/2307.12807/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":"2026-07-05T07:56:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P1K4rrvGKocqVvN1W6z3NxkD8oWnwfsCaN/EGOa1BE2wHuorTX5QO9WRQhNZ8X++QoRuWp5c25txQaN4mkPPDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T14:58:16.133940Z"},"content_sha256":"a541201d1ba7ee96270f573eca9d24cd13160ec2241294cbab052d2fed4fe6b1","schema_version":"1.0","event_id":"sha256:a541201d1ba7ee96270f573eca9d24cd13160ec2241294cbab052d2fed4fe6b1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YCAUBQNUB2VRA47TBWYMORHV3B/bundle.json","state_url":"https://pith.science/pith/YCAUBQNUB2VRA47TBWYMORHV3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YCAUBQNUB2VRA47TBWYMORHV3B/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":"2026-08-12T14:58:16Z","links":{"resolver":"https://pith.science/pith/YCAUBQNUB2VRA47TBWYMORHV3B","bundle":"https://pith.science/pith/YCAUBQNUB2VRA47TBWYMORHV3B/bundle.json","state":"https://pith.science/pith/YCAUBQNUB2VRA47TBWYMORHV3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YCAUBQNUB2VRA47TBWYMORHV3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YCAUBQNUB2VRA47TBWYMORHV3B","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":"90983724a50fa8a5f2fc21e1abe19161b4199396f38637cc050434697e346ea7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-24T13:58:15Z","title_canon_sha256":"b3e25a1cb6722efa41bc11394370fa5bdfae6260cf4551c9857c6e082aa23ddf"},"schema_version":"1.0","source":{"id":"2307.12807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.12807","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"arxiv_version","alias_value":"2307.12807v1","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.12807","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"pith_short_12","alias_value":"YCAUBQNUB2VR","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"pith_short_16","alias_value":"YCAUBQNUB2VRA47T","created_at":"2026-07-05T07:56:16Z"},{"alias_kind":"pith_short_8","alias_value":"YCAUBQNU","created_at":"2026-07-05T07:56:16Z"}],"graph_snapshots":[{"event_id":"sha256:a541201d1ba7ee96270f573eca9d24cd13160ec2241294cbab052d2fed4fe6b1","target":"graph","created_at":"2026-07-05T07:56:16Z","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/2307.12807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semantic types are a more powerful and detailed way of describing data than atomic types such as strings or integers. They establish connections between columns and concepts from the real world, providing more nuanced and fine-grained information that can be useful for tasks such as automated data cleaning, schema matching, and data discovery. Existing deep learning models trained on large text corpora have been successful at performing single-column semantic type prediction for relational data. However, in this work, we propose an extension of the semantic type prediction problem to JSON data","authors_text":"Michael J. Mior, Shuang Wei","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-24T13:58:15Z","title":"Comprehending Semantic Types in JSON Data with Graph Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.12807","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":"sha256:3b27ea0eff269ee14a9814401f91e7cfe74edf66e95764ddd1d5b85bc1781c12","target":"record","created_at":"2026-07-05T07:56:16Z","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":"90983724a50fa8a5f2fc21e1abe19161b4199396f38637cc050434697e346ea7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-24T13:58:15Z","title_canon_sha256":"b3e25a1cb6722efa41bc11394370fa5bdfae6260cf4551c9857c6e082aa23ddf"},"schema_version":"1.0","source":{"id":"2307.12807","kind":"arxiv","version":1}},"canonical_sha256":"c08140c1b40eab1073f30db0c744f5d84490eba1a7173a48f6e3d8c6542703f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c08140c1b40eab1073f30db0c744f5d84490eba1a7173a48f6e3d8c6542703f6","first_computed_at":"2026-07-05T07:56:16.326621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:56:16.326621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fx1POpQRXpgjKy9g2W2cEqbjog3IEPOzvkbfTTZBRxZ2xppC5EZopS6eiZi1+Cg0s4MAz3NBlY7Tm+f4VMLRBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:56:16.327098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.12807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3b27ea0eff269ee14a9814401f91e7cfe74edf66e95764ddd1d5b85bc1781c12","sha256:a541201d1ba7ee96270f573eca9d24cd13160ec2241294cbab052d2fed4fe6b1"],"state_sha256":"cdb76ca835baf5bc1f1bf54bca4eab3d73eb9d4b27494449693672c4d71107e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7hQ8vMy0AffosyH0elxfiChv2Bn97A12KCJZWz96whigHnoVbHfcJZIQQfLhs4PpuycF4nmYAAPQH/O3XIhIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T14:58:16.140974Z","bundle_sha256":"8f541ac8821df914a8f03ad59f4bacad3afd19d7e5a14f9dbc6062027cd71cf1"}}