{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3PBDHBAM3YVHEKIIQYKDSFVNHC","short_pith_number":"pith:3PBDHBAM","canonical_record":{"source":{"id":"2407.03286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-07-03T17:17:37Z","cross_cats_sorted":[],"title_canon_sha256":"4cbd231e9a0445bc99ec39ff51e8493b028ef153ffb4fbb7fbf8967a4df74384","abstract_canon_sha256":"acd83fb1c8f85e2085346c486040c6d585a21cbb0b04500619b477eb5cde6e86"},"schema_version":"1.0"},"canonical_sha256":"dbc233840cde2a72290886143916ad38b28cd533d9087e522b0a9577fbb004ab","source":{"kind":"arxiv","id":"2407.03286","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03286","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03286v1","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03286","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"pith_short_12","alias_value":"3PBDHBAM3YVH","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"pith_short_16","alias_value":"3PBDHBAM3YVHEKII","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"pith_short_8","alias_value":"3PBDHBAM","created_at":"2026-07-05T08:39:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3PBDHBAM3YVHEKIIQYKDSFVNHC","target":"record","payload":{"canonical_record":{"source":{"id":"2407.03286","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-07-03T17:17:37Z","cross_cats_sorted":[],"title_canon_sha256":"4cbd231e9a0445bc99ec39ff51e8493b028ef153ffb4fbb7fbf8967a4df74384","abstract_canon_sha256":"acd83fb1c8f85e2085346c486040c6d585a21cbb0b04500619b477eb5cde6e86"},"schema_version":"1.0"},"canonical_sha256":"dbc233840cde2a72290886143916ad38b28cd533d9087e522b0a9577fbb004ab","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:48.618162Z","signature_b64":"zC9NlBqwXKyfpyo+EBs3kJcyW3QWcOhqjCC3tn4laB1xb6MtRxiYBRHfHmGjVaS+1eLBPZ7ECQ+iPKNNY2iUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dbc233840cde2a72290886143916ad38b28cd533d9087e522b0a9577fbb004ab","last_reissued_at":"2026-07-05T08:39:48.617729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:48.617729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.03286","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":"2026-07-05T08:39:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ye+boXjowTepcK78Dom2AcPODi/C4m/69dVelqif6weGeJjFj/hS4UvakDJURh3xbtoRawmsVRrPRTtz57SXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:37:30.079218Z"},"content_sha256":"4e611c7c0865a9472a8a1a720151272b5af8b109b5483f6e21ea333bcfbd54f8","schema_version":"1.0","event_id":"sha256:4e611c7c0865a9472a8a1a720151272b5af8b109b5483f6e21ea333bcfbd54f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3PBDHBAM3YVHEKIIQYKDSFVNHC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models for JSON Schema Discovery","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Michael J. Mior","submitted_at":"2024-07-03T17:17:37Z","abstract_excerpt":"Semi-structured data formats such as JSON have proved to be useful data models for applications that require flexibility in the format of data stored. However, JSON data often come without the schemas that are typically available with relational data. This has resulted in a number of tools for discovering schemas from a collection of data. Although such tools can be useful, existing approaches focus on the syntax of documents and ignore semantic information.\n  In this work, we explore the automatic addition of meaningful semantic information to discovered schemas similar to information that is"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03286","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/2407.03286/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":"2026-07-05T08:39:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dkkrH7dRbIYMvA9kbGgcQxL0Num6/xbm0l4REAgFlBwfhwxHGp2idiyeI1O7buvpjfWb0NgOvNL4xooAmcc2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:37:30.079837Z"},"content_sha256":"590002e8c19afaf38d1ac5124a900ecae64d66190ebaaa5885e9d08bee6c4fc4","schema_version":"1.0","event_id":"sha256:590002e8c19afaf38d1ac5124a900ecae64d66190ebaaa5885e9d08bee6c4fc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC/bundle.json","state_url":"https://pith.science/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC/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":"2026-08-09T00:37:30Z","links":{"resolver":"https://pith.science/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC","bundle":"https://pith.science/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC/bundle.json","state":"https://pith.science/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3PBDHBAM3YVHEKIIQYKDSFVNHC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3PBDHBAM3YVHEKIIQYKDSFVNHC","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":"acd83fb1c8f85e2085346c486040c6d585a21cbb0b04500619b477eb5cde6e86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-07-03T17:17:37Z","title_canon_sha256":"4cbd231e9a0445bc99ec39ff51e8493b028ef153ffb4fbb7fbf8967a4df74384"},"schema_version":"1.0","source":{"id":"2407.03286","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.03286","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.03286v1","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.03286","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"pith_short_12","alias_value":"3PBDHBAM3YVH","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"pith_short_16","alias_value":"3PBDHBAM3YVHEKII","created_at":"2026-07-05T08:39:48Z"},{"alias_kind":"pith_short_8","alias_value":"3PBDHBAM","created_at":"2026-07-05T08:39:48Z"}],"graph_snapshots":[{"event_id":"sha256:590002e8c19afaf38d1ac5124a900ecae64d66190ebaaa5885e9d08bee6c4fc4","target":"graph","created_at":"2026-07-05T08:39:48Z","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/2407.03286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Semi-structured data formats such as JSON have proved to be useful data models for applications that require flexibility in the format of data stored. However, JSON data often come without the schemas that are typically available with relational data. This has resulted in a number of tools for discovering schemas from a collection of data. Although such tools can be useful, existing approaches focus on the syntax of documents and ignore semantic information.\n  In this work, we explore the automatic addition of meaningful semantic information to discovered schemas similar to information that is","authors_text":"Michael J. Mior","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-07-03T17:17:37Z","title":"Large Language Models for JSON Schema Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.03286","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":"sha256:4e611c7c0865a9472a8a1a720151272b5af8b109b5483f6e21ea333bcfbd54f8","target":"record","created_at":"2026-07-05T08:39:48Z","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":"acd83fb1c8f85e2085346c486040c6d585a21cbb0b04500619b477eb5cde6e86","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2024-07-03T17:17:37Z","title_canon_sha256":"4cbd231e9a0445bc99ec39ff51e8493b028ef153ffb4fbb7fbf8967a4df74384"},"schema_version":"1.0","source":{"id":"2407.03286","kind":"arxiv","version":1}},"canonical_sha256":"dbc233840cde2a72290886143916ad38b28cd533d9087e522b0a9577fbb004ab","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dbc233840cde2a72290886143916ad38b28cd533d9087e522b0a9577fbb004ab","first_computed_at":"2026-07-05T08:39:48.617729Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:48.617729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zC9NlBqwXKyfpyo+EBs3kJcyW3QWcOhqjCC3tn4laB1xb6MtRxiYBRHfHmGjVaS+1eLBPZ7ECQ+iPKNNY2iUCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:48.618162Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.03286","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e611c7c0865a9472a8a1a720151272b5af8b109b5483f6e21ea333bcfbd54f8","sha256:590002e8c19afaf38d1ac5124a900ecae64d66190ebaaa5885e9d08bee6c4fc4"],"state_sha256":"2b76fded90f7c2577e8444b428112eea7e57de4c6bed3afb2c9666a0c5b796d2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lgufQ1xyWHcK1jUQ59e/OoFe9kOLHo//P2mbu0urwQerlQdUjHQFTWw7pSvTJPsNAGsZg5ay08StQ79Ff9WtCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:37:30.084662Z","bundle_sha256":"0e9f4879f8a7d5d798192088f28f2390e4f641b693ab0ebb0b8c95519ac2e5a7"}}