{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CB46LKQNKQ27VPE6CGGFOCVLDQ","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":"07ef5204d0b0e0cb0fae80f105552087285d97665ee28cdb0cc5870ea63628df","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T05:04:32Z","title_canon_sha256":"d9bfc33d3bfd80780dbe923aac67d9a3ea20229a84b5e53b824729c0c2bf8dac"},"schema_version":"1.0","source":{"id":"2508.07179","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07179","created_at":"2026-07-05T11:51:42Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07179v1","created_at":"2026-07-05T11:51:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07179","created_at":"2026-07-05T11:51:42Z"},{"alias_kind":"pith_short_12","alias_value":"CB46LKQNKQ27","created_at":"2026-07-05T11:51:42Z"},{"alias_kind":"pith_short_16","alias_value":"CB46LKQNKQ27VPE6","created_at":"2026-07-05T11:51:42Z"},{"alias_kind":"pith_short_8","alias_value":"CB46LKQN","created_at":"2026-07-05T11:51:42Z"}],"graph_snapshots":[{"event_id":"sha256:c3bbf9a627952285b8c0cb7ba4386b9a4aa75776999e11ea1228370e6e5f7757","target":"graph","created_at":"2026-07-05T11:51:42Z","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/2508.07179/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiaqi Yin, Meng-Lung Lee, Xiya Liu, Yi-Wei Chen","cross_cats":["cs.AI","cs.DB"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T05:04:32Z","title":"Schema Lineage Extraction at Scale: Multilingual Pipelines, Composite Evaluation, and Language-Model Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07179","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:c714aa901a6162ccd15882e956cc0a0f51cd373f6f76ab97135e67661e8f452f","target":"record","created_at":"2026-07-05T11:51:42Z","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":"07ef5204d0b0e0cb0fae80f105552087285d97665ee28cdb0cc5870ea63628df","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T05:04:32Z","title_canon_sha256":"d9bfc33d3bfd80780dbe923aac67d9a3ea20229a84b5e53b824729c0c2bf8dac"},"schema_version":"1.0","source":{"id":"2508.07179","kind":"arxiv","version":1}},"canonical_sha256":"1079e5aa0d5435fabc9e118c570aab1c1a9072f311363799ae6b49e79ac482d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1079e5aa0d5435fabc9e118c570aab1c1a9072f311363799ae6b49e79ac482d2","first_computed_at":"2026-07-05T11:51:42.045771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:51:42.045771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hvgl/TKc7TBrdribYNd73V6/GtdBtzdosyhVXcEEAxbMbNrO7dNV2CkJCyN/kCkSsfYmRrZBKUq31A02yofdBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:51:42.046254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07179","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c714aa901a6162ccd15882e956cc0a0f51cd373f6f76ab97135e67661e8f452f","sha256:c3bbf9a627952285b8c0cb7ba4386b9a4aa75776999e11ea1228370e6e5f7757"],"state_sha256":"63fba3cb74a57169484f3d77b4cedfbc1b8b4ce76a14bbc83f9b9a3fc6affeb0"}