{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CB46LKQNKQ27VPE6CGGFOCVLDQ","short_pith_number":"pith:CB46LKQN","schema_version":"1.0","canonical_sha256":"1079e5aa0d5435fabc9e118c570aab1c1a9072f311363799ae6b49e79ac482d2","source":{"kind":"arxiv","id":"2508.07179","version":1},"attestation_state":"computed","paper":{"title":"Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Jiaqi Yin, Meng-Lung Lee, Xiya Liu, Yi-Wei Chen","submitted_at":"2025-08-10T05:04:32Z","abstract_excerpt":"Enterprise data pipelines, characterized by complex transformations across multiple programming languages, often cause a semantic disconnect between original metadata and downstream data. This \"semantic drift\" compromises data reproducibility and governance, and impairs the utility of services like retrieval-augmented generation (RAG) and text-to-SQL systems. To address this, a novel framework is proposed for the automated extraction of fine-grained schema lineage from multilingual enterprise pipeline scripts. This method identifies four key components: source schemas, source tables, transform"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.07179","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T05:04:32Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"d9bfc33d3bfd80780dbe923aac67d9a3ea20229a84b5e53b824729c0c2bf8dac","abstract_canon_sha256":"07ef5204d0b0e0cb0fae80f105552087285d97665ee28cdb0cc5870ea63628df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:42.046254Z","signature_b64":"Hvgl/TKc7TBrdribYNd73V6/GtdBtzdosyhVXcEEAxbMbNrO7dNV2CkJCyN/kCkSsfYmRrZBKUq31A02yofdBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1079e5aa0d5435fabc9e118c570aab1c1a9072f311363799ae6b49e79ac482d2","last_reissued_at":"2026-07-05T11:51:42.045771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:42.045771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.CL","authors_text":"Jiaqi Yin, Meng-Lung Lee, Xiya Liu, Yi-Wei Chen","submitted_at":"2025-08-10T05:04:32Z","abstract_excerpt":"Enterprise data pipelines, characterized by complex transformations across multiple programming languages, often cause a semantic disconnect between original metadata and downstream data. This \"semantic drift\" compromises data reproducibility and governance, and impairs the utility of services like retrieval-augmented generation (RAG) and text-to-SQL systems. To address this, a novel framework is proposed for the automated extraction of fine-grained schema lineage from multilingual enterprise pipeline scripts. This method identifies four key components: source schemas, source tables, transform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07179","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/2508.07179/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.07179","created_at":"2026-07-05T11:51:42.045830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.07179v1","created_at":"2026-07-05T11:51:42.045830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07179","created_at":"2026-07-05T11:51:42.045830+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB46LKQNKQ27","created_at":"2026-07-05T11:51:42.045830+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB46LKQNKQ27VPE6","created_at":"2026-07-05T11:51:42.045830+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB46LKQN","created_at":"2026-07-05T11:51:42.045830+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ","json":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ.json","graph_json":"https://pith.science/api/pith-number/CB46LKQNKQ27VPE6CGGFOCVLDQ/graph.json","events_json":"https://pith.science/api/pith-number/CB46LKQNKQ27VPE6CGGFOCVLDQ/events.json","paper":"https://pith.science/paper/CB46LKQN"},"agent_actions":{"view_html":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ","download_json":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ.json","view_paper":"https://pith.science/paper/CB46LKQN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.07179&json=true","fetch_graph":"https://pith.science/api/pith-number/CB46LKQNKQ27VPE6CGGFOCVLDQ/graph.json","fetch_events":"https://pith.science/api/pith-number/CB46LKQNKQ27VPE6CGGFOCVLDQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/action/storage_attestation","attest_author":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/action/author_attestation","sign_citation":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/action/citation_signature","submit_replication":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/action/replication_record"}},"created_at":"2026-07-05T11:51:42.045830+00:00","updated_at":"2026-07-05T11:51:42.045830+00:00"}