{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BAEV4JKA6AENT6M526DK5JFLUB","short_pith_number":"pith:BAEV4JKA","schema_version":"1.0","canonical_sha256":"08095e2540f008d9f99dd786aea4aba07206fef1ce6c4414494bc2362c0d4aad","source":{"kind":"arxiv","id":"2502.13016","version":1},"attestation_state":"computed","paper":{"title":"LLM-Powered Proactive Data Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aditya Parameswaran, Sepanta Zeighami, Shreya Shankar, Yiming Lin","submitted_at":"2025-02-18T16:34:45Z","abstract_excerpt":"With the power of LLMs, we now have the ability to query data that was previously impossible to query, including text, images, and video. However, despite this enormous potential, most present-day data systems that leverage LLMs are reactive, reflecting our community's desire to map LLMs to known abstractions. Most data systems treat LLMs as an opaque black box that operates on user inputs and data as is, optimizing them much like any other approximate, expensive UDFs, in conjunction with other relational operators. Such data systems do as they are told, but fail to understand and leverage wha"},"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":"2502.13016","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-02-18T16:34:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1ec98526ab8d252f2bb589d248c1295d5d7c3dfd845f591dc83fed71040b24ef","abstract_canon_sha256":"6a9d8c99c524acd949253122d81b3fc856523404f72a9bb9e68ef4de0025eac5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:28.031553Z","signature_b64":"Y0VhL4ZJUNWuuVnAGMjlhA+ENXm1gLNQRU/zGR4Pa/7PtqCS5L9pCyRlEqbc8hXyjKdS7rsnz9OanFq0hcx6AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08095e2540f008d9f99dd786aea4aba07206fef1ce6c4414494bc2362c0d4aad","last_reissued_at":"2026-07-05T10:16:28.031064Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:28.031064Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-Powered Proactive Data Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aditya Parameswaran, Sepanta Zeighami, Shreya Shankar, Yiming Lin","submitted_at":"2025-02-18T16:34:45Z","abstract_excerpt":"With the power of LLMs, we now have the ability to query data that was previously impossible to query, including text, images, and video. However, despite this enormous potential, most present-day data systems that leverage LLMs are reactive, reflecting our community's desire to map LLMs to known abstractions. Most data systems treat LLMs as an opaque black box that operates on user inputs and data as is, optimizing them much like any other approximate, expensive UDFs, in conjunction with other relational operators. Such data systems do as they are told, but fail to understand and leverage wha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13016","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/2502.13016/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":"2502.13016","created_at":"2026-07-05T10:16:28.031125+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13016v1","created_at":"2026-07-05T10:16:28.031125+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13016","created_at":"2026-07-05T10:16:28.031125+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAEV4JKA6AEN","created_at":"2026-07-05T10:16:28.031125+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAEV4JKA6AENT6M5","created_at":"2026-07-05T10:16:28.031125+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAEV4JKA","created_at":"2026-07-05T10:16:28.031125+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00828","citing_title":"Exploring the Semantic Gap in Agentic Data Systems: A Formative Study of Operationalization Failures in Analytical Workflows","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02655","citing_title":"Semantic Data Processing with Holistic Data Understanding","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15233","citing_title":"Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21765","citing_title":"PrismaDV: Automated Task-Aware Data Unit Test Generation","ref_index":85,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB","json":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB.json","graph_json":"https://pith.science/api/pith-number/BAEV4JKA6AENT6M526DK5JFLUB/graph.json","events_json":"https://pith.science/api/pith-number/BAEV4JKA6AENT6M526DK5JFLUB/events.json","paper":"https://pith.science/paper/BAEV4JKA"},"agent_actions":{"view_html":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB","download_json":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB.json","view_paper":"https://pith.science/paper/BAEV4JKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13016&json=true","fetch_graph":"https://pith.science/api/pith-number/BAEV4JKA6AENT6M526DK5JFLUB/graph.json","fetch_events":"https://pith.science/api/pith-number/BAEV4JKA6AENT6M526DK5JFLUB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB/action/storage_attestation","attest_author":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB/action/author_attestation","sign_citation":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB/action/citation_signature","submit_replication":"https://pith.science/pith/BAEV4JKA6AENT6M526DK5JFLUB/action/replication_record"}},"created_at":"2026-07-05T10:16:28.031125+00:00","updated_at":"2026-07-05T10:16:28.031125+00:00"}