{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:HISRMVWDFASL7YBBODMXDPDGS7","short_pith_number":"pith:HISRMVWD","canonical_record":{"source":{"id":"2505.24716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-30T15:36:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"010ba552194bc015925dcd9a63c32364f4bc64963aec9dfb7211526f2c263cec","abstract_canon_sha256":"ea21c3ced7d720dc839938a1e46db7cdfc6733058e69d6f2eaa56545d50e88f7"},"schema_version":"1.0"},"canonical_sha256":"3a251656c32824bfe02170d971bc6697f077764a0e6713f6f87b16c91001621f","source":{"kind":"arxiv","id":"2505.24716","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24716","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24716v1","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24716","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"HISRMVWDFASL","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"HISRMVWDFASL7YBB","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"HISRMVWD","created_at":"2026-07-05T11:12:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:HISRMVWDFASL7YBBODMXDPDGS7","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24716","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-30T15:36:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"010ba552194bc015925dcd9a63c32364f4bc64963aec9dfb7211526f2c263cec","abstract_canon_sha256":"ea21c3ced7d720dc839938a1e46db7cdfc6733058e69d6f2eaa56545d50e88f7"},"schema_version":"1.0"},"canonical_sha256":"3a251656c32824bfe02170d971bc6697f077764a0e6713f6f87b16c91001621f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:55.389706Z","signature_b64":"YO46Z5DpyDL4ocCcTpzsdIOp4N1hT8GpzkqSPgShfGPbDbMoON8ABhJSi6I+h3KrbRyf7xGDDvVumHA8e689AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3a251656c32824bfe02170d971bc6697f077764a0e6713f6f87b16c91001621f","last_reissued_at":"2026-07-05T11:12:55.389191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:55.389191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24716","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":"2026-07-05T11:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xphglZ5rbT3MKulHdWAeqn9Gqi62LOpPGYQtqzfEjMTMZxoiihuLuFStyjKQSqIGlgSPc2mMPJOpd9N7LPIZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:45:24.797814Z"},"content_sha256":"7f20ca029b8242f98d325e527cb964f66fa164e87dadadcda9be880ebf883476","schema_version":"1.0","event_id":"sha256:7f20ca029b8242f98d325e527cb964f66fa164e87dadadcda9be880ebf883476"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:HISRMVWDFASL7YBBODMXDPDGS7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Scalable Schema Mapping using Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Arash Termehchy, Christopher Buss, David Maier, Mahdis Safari, Stefan Lee","submitted_at":"2025-05-30T15:36:56Z","abstract_excerpt":"The growing need to integrate information from a large number of diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex, source-specific, and costly to maintain as sources evolve. While recent advances suggest that large language models (LLMs) can assist in automating schema matching by leveraging both structural and natural language cues, key challenges remain. In this paper, we identify three core issues with using LLMs for schema mapping: (1) inconsistent outputs due to sensitivit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24716","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/2505.24716/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":"2026-07-05T11:12:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GaHNG+9KSqt73YqLYcyL/zj87ZLQV5KDQnwCKBg8mOeJSYCX3M+rM/9UYi8id/nkB3knOO1KheDPoGViyvP4Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T02:45:24.798326Z"},"content_sha256":"a8887bb48126fb58ffbb846a0988df252602a8fbba0632e7a57f8e1151052505","schema_version":"1.0","event_id":"sha256:a8887bb48126fb58ffbb846a0988df252602a8fbba0632e7a57f8e1151052505"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HISRMVWDFASL7YBBODMXDPDGS7/bundle.json","state_url":"https://pith.science/pith/HISRMVWDFASL7YBBODMXDPDGS7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HISRMVWDFASL7YBBODMXDPDGS7/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":"2026-08-08T02:45:24Z","links":{"resolver":"https://pith.science/pith/HISRMVWDFASL7YBBODMXDPDGS7","bundle":"https://pith.science/pith/HISRMVWDFASL7YBBODMXDPDGS7/bundle.json","state":"https://pith.science/pith/HISRMVWDFASL7YBBODMXDPDGS7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HISRMVWDFASL7YBBODMXDPDGS7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HISRMVWDFASL7YBBODMXDPDGS7","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":"ea21c3ced7d720dc839938a1e46db7cdfc6733058e69d6f2eaa56545d50e88f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-30T15:36:56Z","title_canon_sha256":"010ba552194bc015925dcd9a63c32364f4bc64963aec9dfb7211526f2c263cec"},"schema_version":"1.0","source":{"id":"2505.24716","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24716","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24716v1","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24716","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_12","alias_value":"HISRMVWDFASL","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_16","alias_value":"HISRMVWDFASL7YBB","created_at":"2026-07-05T11:12:55Z"},{"alias_kind":"pith_short_8","alias_value":"HISRMVWD","created_at":"2026-07-05T11:12:55Z"}],"graph_snapshots":[{"event_id":"sha256:a8887bb48126fb58ffbb846a0988df252602a8fbba0632e7a57f8e1151052505","target":"graph","created_at":"2026-07-05T11:12:55Z","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/2505.24716/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing need to integrate information from a large number of diverse sources poses significant scalability challenges for data integration systems. These systems often rely on manually written schema mappings, which are complex, source-specific, and costly to maintain as sources evolve. While recent advances suggest that large language models (LLMs) can assist in automating schema matching by leveraging both structural and natural language cues, key challenges remain. In this paper, we identify three core issues with using LLMs for schema mapping: (1) inconsistent outputs due to sensitivit","authors_text":"Arash Termehchy, Christopher Buss, David Maier, Mahdis Safari, Stefan Lee","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-30T15:36:56Z","title":"Towards Scalable Schema Mapping using Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24716","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":"sha256:7f20ca029b8242f98d325e527cb964f66fa164e87dadadcda9be880ebf883476","target":"record","created_at":"2026-07-05T11:12:55Z","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":"ea21c3ced7d720dc839938a1e46db7cdfc6733058e69d6f2eaa56545d50e88f7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-30T15:36:56Z","title_canon_sha256":"010ba552194bc015925dcd9a63c32364f4bc64963aec9dfb7211526f2c263cec"},"schema_version":"1.0","source":{"id":"2505.24716","kind":"arxiv","version":1}},"canonical_sha256":"3a251656c32824bfe02170d971bc6697f077764a0e6713f6f87b16c91001621f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3a251656c32824bfe02170d971bc6697f077764a0e6713f6f87b16c91001621f","first_computed_at":"2026-07-05T11:12:55.389191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:55.389191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YO46Z5DpyDL4ocCcTpzsdIOp4N1hT8GpzkqSPgShfGPbDbMoON8ABhJSi6I+h3KrbRyf7xGDDvVumHA8e689AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:55.389706Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24716","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f20ca029b8242f98d325e527cb964f66fa164e87dadadcda9be880ebf883476","sha256:a8887bb48126fb58ffbb846a0988df252602a8fbba0632e7a57f8e1151052505"],"state_sha256":"ea80e7e0b3f03e86dc49fca4186d7fe16f11ea5b1f0fd791ffe95a598cdf6db7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GboHAB8I/HDoYyeNneoIw8Yp0ggiV9KjLjw5py3TJWJIrD28vn6BvTczyTTBZm32hBpvTctd7Q7i6LhjvdVOAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T02:45:24.801939Z","bundle_sha256":"f9a602a72c8fc4414c7d3fb90f695811b523b49b1377a9b528a1cff3f0c89bf3"}}