{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:BC4I4CJGZOXAA7IV4SSZWUDG6Q","short_pith_number":"pith:BC4I4CJG","canonical_record":{"source":{"id":"2507.14376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T21:50:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a8f46abcc7ed94ceec912f9170cfb8c3d87efa47a279186cf43b21658c9d37fa","abstract_canon_sha256":"533b3ce5cf83ced65c664a587e22f45d75d5a93039a8bd9a87d43657b71f47d3"},"schema_version":"1.0"},"canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","source":{"kind":"arxiv","id":"2507.14376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14376","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14376v1","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14376","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"pith_short_12","alias_value":"BC4I4CJGZOXA","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"pith_short_16","alias_value":"BC4I4CJGZOXAA7IV","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"pith_short_8","alias_value":"BC4I4CJG","created_at":"2026-07-05T11:40:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:BC4I4CJGZOXAA7IV4SSZWUDG6Q","target":"record","payload":{"canonical_record":{"source":{"id":"2507.14376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T21:50:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a8f46abcc7ed94ceec912f9170cfb8c3d87efa47a279186cf43b21658c9d37fa","abstract_canon_sha256":"533b3ce5cf83ced65c664a587e22f45d75d5a93039a8bd9a87d43657b71f47d3"},"schema_version":"1.0"},"canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:40:05.091184Z","signature_b64":"ALU4M/1CBO3wIH1tSyTN57B1v7st6M8BrkxbiT5vknZNdjMLGBC7XWT4GeAkELHZa8wGQpA5sjJP3PpQOjSFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","last_reissued_at":"2026-07-05T11:40:05.090748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:40:05.090748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.14376","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":"2026-07-05T11:40:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s1ocShiCKNTjlJrLpxxKiLOmiW2kGVKYR3GfiuuG5qO2FpudJZLJFOvYghGDzgoNyC8LHdM8XCvVENzAw6d1CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:41:28.797913Z"},"content_sha256":"c773a53bdca25ddfcc8deb592cab32586c34a134224fb35f49a7c63704b110ff","schema_version":"1.0","event_id":"sha256:c773a53bdca25ddfcc8deb592cab32586c34a134224fb35f49a7c63704b110ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:BC4I4CJGZOXAA7IV4SSZWUDG6Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DB","authors_text":"Derak Paulsen, Osman Erman Gungor, William Kang","submitted_at":"2025-07-18T21:50:36Z","abstract_excerpt":"Schema matching is essential for integrating heterogeneous data sources and enhancing dataset discovery, yet it remains a complex and resource-intensive problem. We introduce SCHEMORA, a schema matching framework that combines large language models with hybrid retrieval techniques in a prompt-based approach, enabling efficient identification of candidate matches without relying on labeled training data or exhaustive pairwise comparisons. By enriching schema metadata and leveraging both vector-based and lexical retrieval, SCHEMORA improves matching accuracy and scalability. Evaluated on the MIM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14376","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/2507.14376/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":"2026-07-05T11:40:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pGxomNcIzh8WI36wcAZnzNqopLZeXljuszFj+8RmUQ3c9+5aIJIE8HXE84lCYQL7dEBvzNuZhkGptk5uT/xLCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:41:28.798387Z"},"content_sha256":"8e32c4899886697a5f13f4de1c112b8f3e9ec00c3c02d5d9385645f3940b7606","schema_version":"1.0","event_id":"sha256:8e32c4899886697a5f13f4de1c112b8f3e9ec00c3c02d5d9385645f3940b7606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/bundle.json","state_url":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/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":"2026-08-04T13:41:28Z","links":{"resolver":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q","bundle":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/bundle.json","state":"https://pith.science/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BC4I4CJGZOXAA7IV4SSZWUDG6Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:BC4I4CJGZOXAA7IV4SSZWUDG6Q","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":"533b3ce5cf83ced65c664a587e22f45d75d5a93039a8bd9a87d43657b71f47d3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T21:50:36Z","title_canon_sha256":"a8f46abcc7ed94ceec912f9170cfb8c3d87efa47a279186cf43b21658c9d37fa"},"schema_version":"1.0","source":{"id":"2507.14376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.14376","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.14376v1","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.14376","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"pith_short_12","alias_value":"BC4I4CJGZOXA","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"pith_short_16","alias_value":"BC4I4CJGZOXAA7IV","created_at":"2026-07-05T11:40:05Z"},{"alias_kind":"pith_short_8","alias_value":"BC4I4CJG","created_at":"2026-07-05T11:40:05Z"}],"graph_snapshots":[{"event_id":"sha256:8e32c4899886697a5f13f4de1c112b8f3e9ec00c3c02d5d9385645f3940b7606","target":"graph","created_at":"2026-07-05T11:40:05Z","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/2507.14376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Schema matching is essential for integrating heterogeneous data sources and enhancing dataset discovery, yet it remains a complex and resource-intensive problem. We introduce SCHEMORA, a schema matching framework that combines large language models with hybrid retrieval techniques in a prompt-based approach, enabling efficient identification of candidate matches without relying on labeled training data or exhaustive pairwise comparisons. By enriching schema metadata and leveraging both vector-based and lexical retrieval, SCHEMORA improves matching accuracy and scalability. Evaluated on the MIM","authors_text":"Derak Paulsen, Osman Erman Gungor, William Kang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T21:50:36Z","title":"Schemora: schema matching via multi-stage recommendation and metadata enrichment using off-the-shelf llms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.14376","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:c773a53bdca25ddfcc8deb592cab32586c34a134224fb35f49a7c63704b110ff","target":"record","created_at":"2026-07-05T11:40:05Z","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":"533b3ce5cf83ced65c664a587e22f45d75d5a93039a8bd9a87d43657b71f47d3","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-18T21:50:36Z","title_canon_sha256":"a8f46abcc7ed94ceec912f9170cfb8c3d87efa47a279186cf43b21658c9d37fa"},"schema_version":"1.0","source":{"id":"2507.14376","kind":"arxiv","version":1}},"canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08b88e0926cbae007d15e4a59b5066f436582db2ba96dec873c5f43f7f9277fc","first_computed_at":"2026-07-05T11:40:05.090748Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:05.090748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ALU4M/1CBO3wIH1tSyTN57B1v7st6M8BrkxbiT5vknZNdjMLGBC7XWT4GeAkELHZa8wGQpA5sjJP3PpQOjSFDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:05.091184Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.14376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c773a53bdca25ddfcc8deb592cab32586c34a134224fb35f49a7c63704b110ff","sha256:8e32c4899886697a5f13f4de1c112b8f3e9ec00c3c02d5d9385645f3940b7606"],"state_sha256":"26859cdc83dc8c342630113f93cfef4b5a97501891d3f29e7f5848c169c58ed5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0oquiyHFdC7skxkhHcS3ctYOEm5+uWW/3KFxLM05gGEZeh6xha58Pem5IKIgxu6fMvzR1+isa8yqdE9g1mV3Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:41:28.802425Z","bundle_sha256":"45ec906d77945c6e95ac0de403525fd91e1fb2b1b6c9ac60fe2e0d5da91738fa"}}