{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6AJ5U7C7CDLKFJKGNAUX4VLSJJ","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":"736c5b683c9a9e2e71620c6b01bf51a0e4421d46aa5bf3b3219807d2fca63966","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-01T06:03:55Z","title_canon_sha256":"135e8ea2adf588013919a5433728633de35f117f37ddf9d1bbc54f54a9c091e8"},"schema_version":"1.0","source":{"id":"2502.00329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00329","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00329v1","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00329","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"6AJ5U7C7CDLK","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"6AJ5U7C7CDLKFJKG","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"6AJ5U7C7","created_at":"2026-07-05T10:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:38f71e62ffe4d71543604ea9aa7a3301db525a537318e70a9700141f359bf83a","target":"graph","created_at":"2026-07-05T10:08:32Z","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/2502.00329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have the potential to revolutionize data analytics by simplifying tasks such as data discovery and SQL query synthesis through natural language interactions. This work serves as a pivotal first step toward the development of foundation models explicitly designed for data analytics applications. To propel this vision forward, we unveil a new data recipe for post-training LLMs, enhancing their comprehension of data management and empowering them to tackle complex real-world analytics tasks. Specifically, our innovative approach includes a scalable synthetic data gene","authors_text":"Alon Halevy, Asterios Katsifodimos, George Karypis, Hengrui Zhang, Huzefa Rangwala, Jiani Zhang, Patrick Ng, Rishav Chakravarti, Yiqun Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-01T06:03:55Z","title":"CoddLLM: Empowering Large Language Models for Data Analytics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00329","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:eeacba58a7581110d5b039be0cbe3640f11fe08e75403345d9c3aaeab8ddfe3f","target":"record","created_at":"2026-07-05T10:08:32Z","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":"736c5b683c9a9e2e71620c6b01bf51a0e4421d46aa5bf3b3219807d2fca63966","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-01T06:03:55Z","title_canon_sha256":"135e8ea2adf588013919a5433728633de35f117f37ddf9d1bbc54f54a9c091e8"},"schema_version":"1.0","source":{"id":"2502.00329","kind":"arxiv","version":1}},"canonical_sha256":"f013da7c5f10d6a2a54668297e55724a7c987e762b4a39b89fb2dd3caaa465df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f013da7c5f10d6a2a54668297e55724a7c987e762b4a39b89fb2dd3caaa465df","first_computed_at":"2026-07-05T10:08:32.222727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:32.222727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zPhLT/K213M0RRphC/OPQSSjPNnuqQ5UKU/1vsLRXca93UEDpC2Fnx707Abqokg1P9TWiCOaEmcyaOpMYEkZAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:32.223115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eeacba58a7581110d5b039be0cbe3640f11fe08e75403345d9c3aaeab8ddfe3f","sha256:38f71e62ffe4d71543604ea9aa7a3301db525a537318e70a9700141f359bf83a"],"state_sha256":"2166013331825da815c277d48583c298c332b5b9d2ddb00968d06d9a07afee6f"}