{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DHEM7HAC6327TNEOJ32LUA3EVS","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":"169959449bb5dd65a6c0621b79b549d8a683ece8906b5228b29f650e25cfa991","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-04T10:23:30Z","title_canon_sha256":"8936bc737d1cfba3a45fe11f1dc70006e75d9988545f5a9aa0441c58ee6a2a54"},"schema_version":"1.0","source":{"id":"2507.21056","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21056","created_at":"2026-07-05T11:44:30Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21056v1","created_at":"2026-07-05T11:44:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21056","created_at":"2026-07-05T11:44:30Z"},{"alias_kind":"pith_short_12","alias_value":"DHEM7HAC6327","created_at":"2026-07-05T11:44:30Z"},{"alias_kind":"pith_short_16","alias_value":"DHEM7HAC6327TNEO","created_at":"2026-07-05T11:44:30Z"},{"alias_kind":"pith_short_8","alias_value":"DHEM7HAC","created_at":"2026-07-05T11:44:30Z"}],"graph_snapshots":[{"event_id":"sha256:14d88b4f57d76b307e4a76fb66106648d7d1ed786ddadffde2f026ea861fecae","target":"graph","created_at":"2026-07-05T11:44:30Z","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/2507.21056/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data contracts formalize agreements between data producers and consumers regarding schema, semantics, and quality expectations. As data pipelines grow in complexity, manual authoring and maintenance of contracts becomes error-prone and labor-intensive. We present an AI-driven framework for automatic data contract generation using large language models (LLMs). Our system leverages parameter-efficient fine-tuning methods, including LoRA and PEFT, to adapt LLMs to structured data domains. The models take sample data or schema descriptions and output validated contract definitions in formats such ","authors_text":"Harshraj Bhoite","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-04T10:23:30Z","title":"AI-Driven Generation of Data Contracts in Modern Data Engineering Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21056","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":"sha256:7073cd3595cbcf4ce3437773b80cae2520a54070d2d6fc8135ad7f596f92f7dd","target":"record","created_at":"2026-07-05T11:44:30Z","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":"169959449bb5dd65a6c0621b79b549d8a683ece8906b5228b29f650e25cfa991","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-05-04T10:23:30Z","title_canon_sha256":"8936bc737d1cfba3a45fe11f1dc70006e75d9988545f5a9aa0441c58ee6a2a54"},"schema_version":"1.0","source":{"id":"2507.21056","kind":"arxiv","version":1}},"canonical_sha256":"19c8cf9c02f6f5f9b48e4ef4ba0364ac87bc0fb2df9893ccf9afc4231c6c8d0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19c8cf9c02f6f5f9b48e4ef4ba0364ac87bc0fb2df9893ccf9afc4231c6c8d0d","first_computed_at":"2026-07-05T11:44:30.355570Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:30.355570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OEBfm99xL+RPgEKNzNvq2SuovLubuTgVBQdIP2qpUHekkVYzfKGwAKdWx8uVG7mCo7mp4177+/A4ajr9CPYyAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:30.356005Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21056","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7073cd3595cbcf4ce3437773b80cae2520a54070d2d6fc8135ad7f596f92f7dd","sha256:14d88b4f57d76b307e4a76fb66106648d7d1ed786ddadffde2f026ea861fecae"],"state_sha256":"6c15ee5c221f27706e67d24728d90738fb60003108892994329f8e89afa13fe6"}