{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CB46LKQNKQ27VPE6CGGFOCVLDQ","short_pith_number":"pith:CB46LKQN","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"},"canonical_sha256":"1079e5aa0d5435fabc9e118c570aab1c1a9072f311363799ae6b49e79ac482d2","source":{"kind":"arxiv","id":"2508.07179","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CB46LKQNKQ27VPE6CGGFOCVLDQ","target":"record","payload":{"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"},"canonical_sha256":"1079e5aa0d5435fabc9e118c570aab1c1a9072f311363799ae6b49e79ac482d2","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"},"source_kind":"arxiv","source_id":"2508.07179","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":"2026-07-05T11:51:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PgK6ixx0PrhQ23LRurpzYq0mD5cn/OYzbluOXzD5nS4g//GWf9BWVtTo2KR52rhyhdFSpC8+wn893DfTphj3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:23:25.392116Z"},"content_sha256":"c714aa901a6162ccd15882e956cc0a0f51cd373f6f76ab97135e67661e8f452f","schema_version":"1.0","event_id":"sha256:c714aa901a6162ccd15882e956cc0a0f51cd373f6f76ab97135e67661e8f452f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CB46LKQNKQ27VPE6CGGFOCVLDQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:51:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PgHt79qafwoFXUM32IVRNErzAaaFd07ez04CRaEezT4umX8bnPPO61/mJN1iTTZOUFJz9iSLpghcDAosaTDFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:23:25.392666Z"},"content_sha256":"c3bbf9a627952285b8c0cb7ba4386b9a4aa75776999e11ea1228370e6e5f7757","schema_version":"1.0","event_id":"sha256:c3bbf9a627952285b8c0cb7ba4386b9a4aa75776999e11ea1228370e6e5f7757"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/bundle.json","state_url":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/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":"2026-08-06T06:23:25Z","links":{"resolver":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ","bundle":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/bundle.json","state":"https://pith.science/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CB46LKQNKQ27VPE6CGGFOCVLDQ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p3Wu+9O1B2OSC0BGt48AgyKrJv2j5hMMiZn2m+F0OHOEZkXBhRemA6XlAtmPgCJfE/rqzvgH/JjeOg9tcZ66Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:23:25.397580Z","bundle_sha256":"de8f537fdfe818648ec2b01135b82e2439534c1630ee5a1629c39278312cb5f4"}}