{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PJML2O44FOBY6FRV55NGK5JLZ7","short_pith_number":"pith:PJML2O44","canonical_record":{"source":{"id":"2307.03113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-06T16:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"df1ff2e11df1b6c683baa235cac5fc154aa6118f90105771bece3913bb9a8feb","abstract_canon_sha256":"2bb721d3a05f22aa1bbde5eda0e2a8337fb507e4fd056d1fcd505e554ec7eb5b"},"schema_version":"1.0"},"canonical_sha256":"7a58bd3b9c2b838f1635ef5a65752bcff2626541d2aaa3f96726af1c27e055ee","source":{"kind":"arxiv","id":"2307.03113","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03113","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03113v1","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03113","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"PJML2O44FOBY","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"PJML2O44FOBY6FRV","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"PJML2O44","created_at":"2026-07-05T06:28:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PJML2O44FOBY6FRV55NGK5JLZ7","target":"record","payload":{"canonical_record":{"source":{"id":"2307.03113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-06T16:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"df1ff2e11df1b6c683baa235cac5fc154aa6118f90105771bece3913bb9a8feb","abstract_canon_sha256":"2bb721d3a05f22aa1bbde5eda0e2a8337fb507e4fd056d1fcd505e554ec7eb5b"},"schema_version":"1.0"},"canonical_sha256":"7a58bd3b9c2b838f1635ef5a65752bcff2626541d2aaa3f96726af1c27e055ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:28.142118Z","signature_b64":"pRzpfvSOpZSGmahwvShf8HFvXtvkgfbAvJ5Uf57yIBaNW+j+LCAJw3ZpQvmxfUvlZsqSLqz83nr/XOBAjwq5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a58bd3b9c2b838f1635ef5a65752bcff2626541d2aaa3f96726af1c27e055ee","last_reissued_at":"2026-07-05T06:28:28.141769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:28.141769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.03113","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":"2026-07-05T06:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xqZQ7bg7+1NDP8V+W8zBZWaf0BywL1279NHXNGbHbk8sm73gYbS+HYQWrILwrgk+9pSqeUx3EwxnIKPsv4/1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:05:30.805682Z"},"content_sha256":"41573d04850be701629c09a8d7add5173e91211ead06afe577aa9482f509cf19","schema_version":"1.0","event_id":"sha256:41573d04850be701629c09a8d7add5173e91211ead06afe577aa9482f509cf19"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PJML2O44FOBY6FRV55NGK5JLZ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"JSONoid: Monoid-based Enrichment for Configurable and Scalable Data-Driven 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":"2023-07-06T16:30:38Z","abstract_excerpt":"Schema discovery is an important aspect to working with data in formats such as JSON. Unlike relational databases, JSON data sets often do not have associated structural information. Consumers of such datasets are often left to browse through data in an attempt to observe commonalities in structure across documents to construct suitable code for data processing. However, this process is time-consuming and error-prone. Existing distributed approaches to mining schemas present a significant usability advantage as they provide useful metadata for large data sources. However, depending on the data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03113","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/2307.03113/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":"2026-07-05T06:28:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wn6Kzr7dgWK9FVTbNj4ILrgt/jE9vTOqfNK9DyNTjxucallC68cZakc6Xu/Fzv8rntkKC+z52UFEvOpd5MOAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T04:05:30.806175Z"},"content_sha256":"a18958298d8b64994721af673f9ecdba94ac7f2f32cd332cf7554aa0702938a4","schema_version":"1.0","event_id":"sha256:a18958298d8b64994721af673f9ecdba94ac7f2f32cd332cf7554aa0702938a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJML2O44FOBY6FRV55NGK5JLZ7/bundle.json","state_url":"https://pith.science/pith/PJML2O44FOBY6FRV55NGK5JLZ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJML2O44FOBY6FRV55NGK5JLZ7/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":"2026-08-13T04:05:30Z","links":{"resolver":"https://pith.science/pith/PJML2O44FOBY6FRV55NGK5JLZ7","bundle":"https://pith.science/pith/PJML2O44FOBY6FRV55NGK5JLZ7/bundle.json","state":"https://pith.science/pith/PJML2O44FOBY6FRV55NGK5JLZ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJML2O44FOBY6FRV55NGK5JLZ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PJML2O44FOBY6FRV55NGK5JLZ7","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":"2bb721d3a05f22aa1bbde5eda0e2a8337fb507e4fd056d1fcd505e554ec7eb5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-06T16:30:38Z","title_canon_sha256":"df1ff2e11df1b6c683baa235cac5fc154aa6118f90105771bece3913bb9a8feb"},"schema_version":"1.0","source":{"id":"2307.03113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.03113","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.03113v1","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.03113","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"pith_short_12","alias_value":"PJML2O44FOBY","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"pith_short_16","alias_value":"PJML2O44FOBY6FRV","created_at":"2026-07-05T06:28:28Z"},{"alias_kind":"pith_short_8","alias_value":"PJML2O44","created_at":"2026-07-05T06:28:28Z"}],"graph_snapshots":[{"event_id":"sha256:a18958298d8b64994721af673f9ecdba94ac7f2f32cd332cf7554aa0702938a4","target":"graph","created_at":"2026-07-05T06:28:28Z","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/2307.03113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Schema discovery is an important aspect to working with data in formats such as JSON. Unlike relational databases, JSON data sets often do not have associated structural information. Consumers of such datasets are often left to browse through data in an attempt to observe commonalities in structure across documents to construct suitable code for data processing. However, this process is time-consuming and error-prone. Existing distributed approaches to mining schemas present a significant usability advantage as they provide useful metadata for large data sources. However, depending on the data","authors_text":"Michael J. Mior","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-06T16:30:38Z","title":"JSONoid: Monoid-based Enrichment for Configurable and Scalable Data-Driven Schema Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.03113","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":"sha256:41573d04850be701629c09a8d7add5173e91211ead06afe577aa9482f509cf19","target":"record","created_at":"2026-07-05T06:28:28Z","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":"2bb721d3a05f22aa1bbde5eda0e2a8337fb507e4fd056d1fcd505e554ec7eb5b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2023-07-06T16:30:38Z","title_canon_sha256":"df1ff2e11df1b6c683baa235cac5fc154aa6118f90105771bece3913bb9a8feb"},"schema_version":"1.0","source":{"id":"2307.03113","kind":"arxiv","version":1}},"canonical_sha256":"7a58bd3b9c2b838f1635ef5a65752bcff2626541d2aaa3f96726af1c27e055ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a58bd3b9c2b838f1635ef5a65752bcff2626541d2aaa3f96726af1c27e055ee","first_computed_at":"2026-07-05T06:28:28.141769Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:28:28.141769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pRzpfvSOpZSGmahwvShf8HFvXtvkgfbAvJ5Uf57yIBaNW+j+LCAJw3ZpQvmxfUvlZsqSLqz83nr/XOBAjwq5AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:28:28.142118Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.03113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41573d04850be701629c09a8d7add5173e91211ead06afe577aa9482f509cf19","sha256:a18958298d8b64994721af673f9ecdba94ac7f2f32cd332cf7554aa0702938a4"],"state_sha256":"2c0c828b7420cdae08bdd7fd37f8906555d4711390ef3d9d86c9f0f222641968"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TC3cyXEaHddyI1MU2xEBcBMRG6hc1ZvROQEDJO6g/LXRSo2P4M0sxhRpqLKefa5P30BiP2fWS6td292t5hcAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T04:05:30.811642Z","bundle_sha256":"b73ca5093901e8a6bf8a8c75d09f785a67c584c9d485a6f2ebe0672dcd686ed7"}}