{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7BJQMEG6R7AVGFH4U2NZH7HLLH","short_pith_number":"pith:7BJQMEG6","schema_version":"1.0","canonical_sha256":"f8530610de8fc15314fca69b93fceb59d1c7b41b0e7921b045909812936bcebf","source":{"kind":"arxiv","id":"2509.02751","version":1},"attestation_state":"computed","paper":{"title":"Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Matthew Russo, Tim Kraska","submitted_at":"2025-09-02T18:59:15Z","abstract_excerpt":"With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators -- a declarative set of AI-powered data transformations with natural language specifications. However, even when optimized, these operators can be expensive to execute on millions of records and their iterator execution semantics make them ill-suited for interactive data analytics tasks. In another line of work, Deep Research systems have demonstrated an abili"},"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":"2509.02751","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-09-02T18:59:15Z","cross_cats_sorted":["cs.DB","cs.LG","cs.MA"],"title_canon_sha256":"e603bb84967ab534e780699642b328fa0ed542c46c18b8f4a7c80ed859a29f17","abstract_canon_sha256":"718af27dd828c0496782727385399a5c4cc2e7b7f8406c07c716a48baa4056e3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:57.164255Z","signature_b64":"vaqaewfekLUh6dVVKU2fMG+rx/Q4wixn/jLRWr+SrXs6GTXcR8ZmdehfsZhi9zaJ74I7LnM4EPdrB6so4kiZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8530610de8fc15314fca69b93fceb59d1c7b41b0e7921b045909812936bcebf","last_reissued_at":"2026-07-05T12:03:57.163687Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:57.163687Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Research is the New Analytics System: Towards Building the Runtime for AI-Driven Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DB","cs.LG","cs.MA"],"primary_cat":"cs.AI","authors_text":"Matthew Russo, Tim Kraska","submitted_at":"2025-09-02T18:59:15Z","abstract_excerpt":"With advances in large language models (LLMs), researchers are creating new systems that can perform AI-driven analytics over large unstructured datasets. Recent work has explored executing such analytics queries using semantic operators -- a declarative set of AI-powered data transformations with natural language specifications. However, even when optimized, these operators can be expensive to execute on millions of records and their iterator execution semantics make them ill-suited for interactive data analytics tasks. In another line of work, Deep Research systems have demonstrated an abili"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02751","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/2509.02751/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":"2509.02751","created_at":"2026-07-05T12:03:57.163756+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02751v1","created_at":"2026-07-05T12:03:57.163756+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02751","created_at":"2026-07-05T12:03:57.163756+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BJQMEG6R7AV","created_at":"2026-07-05T12:03:57.163756+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BJQMEG6R7AVGFH4","created_at":"2026-07-05T12:03:57.163756+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BJQMEG6","created_at":"2026-07-05T12:03:57.163756+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.15184","citing_title":"Agent-Aided Design for Dynamic CAD Models","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH","json":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH.json","graph_json":"https://pith.science/api/pith-number/7BJQMEG6R7AVGFH4U2NZH7HLLH/graph.json","events_json":"https://pith.science/api/pith-number/7BJQMEG6R7AVGFH4U2NZH7HLLH/events.json","paper":"https://pith.science/paper/7BJQMEG6"},"agent_actions":{"view_html":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH","download_json":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH.json","view_paper":"https://pith.science/paper/7BJQMEG6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02751&json=true","fetch_graph":"https://pith.science/api/pith-number/7BJQMEG6R7AVGFH4U2NZH7HLLH/graph.json","fetch_events":"https://pith.science/api/pith-number/7BJQMEG6R7AVGFH4U2NZH7HLLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH/action/storage_attestation","attest_author":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH/action/author_attestation","sign_citation":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH/action/citation_signature","submit_replication":"https://pith.science/pith/7BJQMEG6R7AVGFH4U2NZH7HLLH/action/replication_record"}},"created_at":"2026-07-05T12:03:57.163756+00:00","updated_at":"2026-07-05T12:03:57.163756+00:00"}