{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OUV7UOKT4AYW7HTG27PBGOSAF6","short_pith_number":"pith:OUV7UOKT","schema_version":"1.0","canonical_sha256":"752bfa3953e0316f9e66d7de133a402f8e058949fecada1d6c1b2532862ac498","source":{"kind":"arxiv","id":"2407.11418","version":3},"attestation_state":"computed","paper":{"title":"Semantic Operators: A Declarative Model for Rich, AI-based Data Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Carlos Guestrin, Harshit Gupta, Liana Patel, Matei Zaharia, Melissa Pan, Parth Asawa, Siddharth Jha","submitted_at":"2024-07-16T06:19:14Z","abstract_excerpt":"The semantic capabilities of large language models (LLMs) have the potential to enable rich analytics and reasoning over vast knowledge corpora. Unfortunately, existing systems either empirically optimize expensive LLM-powered operations with no performance guarantees, or serve a limited set of row-wise LLM operations, providing limited robustness, expressiveness and usability. We introduce semantic operators, the first formalism for declarative and general-purpose AI-based transformations based on natural language specifications (e.g., filtering, sorting, joining or aggregating records using "},"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":"2407.11418","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-07-16T06:19:14Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"e82b047f00f5bb2c3d7b13c70111c9245e46e95b3879503e0b19a1da8f5c05f1","abstract_canon_sha256":"43e780d20ba3139f276beac7577a1851f684eef4d0921513954416f00a4f115a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:02.245369Z","signature_b64":"E4bK366saAX6zKQqEb8rWjCL6t7HC8uvtLs+WYOPS1O2dibNf0jDiWr2vtqW90pB73mJLNaVlyyl5p57gXxBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"752bfa3953e0316f9e66d7de133a402f8e058949fecada1d6c1b2532862ac498","last_reissued_at":"2026-07-05T10:22:02.244838Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:02.244838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantic Operators: A Declarative Model for Rich, AI-based Data Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.DB","authors_text":"Carlos Guestrin, Harshit Gupta, Liana Patel, Matei Zaharia, Melissa Pan, Parth Asawa, Siddharth Jha","submitted_at":"2024-07-16T06:19:14Z","abstract_excerpt":"The semantic capabilities of large language models (LLMs) have the potential to enable rich analytics and reasoning over vast knowledge corpora. Unfortunately, existing systems either empirically optimize expensive LLM-powered operations with no performance guarantees, or serve a limited set of row-wise LLM operations, providing limited robustness, expressiveness and usability. We introduce semantic operators, the first formalism for declarative and general-purpose AI-based transformations based on natural language specifications (e.g., filtering, sorting, joining or aggregating records using "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11418","kind":"arxiv","version":3},"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/2407.11418/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":"2407.11418","created_at":"2026-07-05T10:22:02.244896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.11418v3","created_at":"2026-07-05T10:22:02.244896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11418","created_at":"2026-07-05T10:22:02.244896+00:00"},{"alias_kind":"pith_short_12","alias_value":"OUV7UOKT4AYW","created_at":"2026-07-05T10:22:02.244896+00:00"},{"alias_kind":"pith_short_16","alias_value":"OUV7UOKT4AYW7HTG","created_at":"2026-07-05T10:22:02.244896+00:00"},{"alias_kind":"pith_short_8","alias_value":"OUV7UOKT","created_at":"2026-07-05T10:22:02.244896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06229","citing_title":"Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23081","citing_title":"SemCEB: A Cardinality Estimation Benchmark for Semantic Operators","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07923","citing_title":"Larch: Learned Query Optimization for Semantic Predicates","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31808","citing_title":"Large Databases Need Small, Open-Weight Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29532","citing_title":"SemJoin: Semantic Join Optimization","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03946","citing_title":"MLSkip: Data Skipping for ML Filters via Lightweight Metadata","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03152","citing_title":"Cost-Aware Optimization for Agentic Query Execution","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2503.04338","citing_title":"In-depth Analysis of Graph-based RAG in a Unified Framework","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12610","citing_title":"ScaleDoc: Scaling LLM-based Predicates over Large Document Collections","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05012","citing_title":"Making Prompts First-Class Citizens for Adaptive LLM Pipelines","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16432","citing_title":"iPDB -- Optimizing Semantic SQL Queries","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01707","citing_title":"Memory in the LLM Era: Modular Architectures and Strategies in a Unified Framework","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02690","citing_title":"AnnoRetrieve: Efficient Structured Retrieval for Unstructured Document Analysis","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02655","citing_title":"Semantic Data Processing with Holistic Data Understanding","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10776","citing_title":"Natural Language to What? A Vision for Intermediate Representations in NL-to-X Querying","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04603","citing_title":"Cardinality Estimation for High Dimensional Similarity Queries with Adaptive Bucket Probing","ref_index":27,"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":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6","json":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6.json","graph_json":"https://pith.science/api/pith-number/OUV7UOKT4AYW7HTG27PBGOSAF6/graph.json","events_json":"https://pith.science/api/pith-number/OUV7UOKT4AYW7HTG27PBGOSAF6/events.json","paper":"https://pith.science/paper/OUV7UOKT"},"agent_actions":{"view_html":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6","download_json":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6.json","view_paper":"https://pith.science/paper/OUV7UOKT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.11418&json=true","fetch_graph":"https://pith.science/api/pith-number/OUV7UOKT4AYW7HTG27PBGOSAF6/graph.json","fetch_events":"https://pith.science/api/pith-number/OUV7UOKT4AYW7HTG27PBGOSAF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/action/storage_attestation","attest_author":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/action/author_attestation","sign_citation":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/action/citation_signature","submit_replication":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/action/replication_record"}},"created_at":"2026-07-05T10:22:02.244896+00:00","updated_at":"2026-07-05T10:22:02.244896+00:00"}