{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:OUV7UOKT4AYW7HTG27PBGOSAF6","short_pith_number":"pith:OUV7UOKT","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"},"canonical_sha256":"752bfa3953e0316f9e66d7de133a402f8e058949fecada1d6c1b2532862ac498","source":{"kind":"arxiv","id":"2407.11418","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11418","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11418v3","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11418","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"OUV7UOKT4AYW","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"OUV7UOKT4AYW7HTG","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"OUV7UOKT","created_at":"2026-07-05T10:22:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:OUV7UOKT4AYW7HTG27PBGOSAF6","target":"record","payload":{"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"},"canonical_sha256":"752bfa3953e0316f9e66d7de133a402f8e058949fecada1d6c1b2532862ac498","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"},"source_kind":"arxiv","source_id":"2407.11418","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sXA3RTzCuujfmgKArkAKoQaJ0nIs5GKQ95M5miCaZ/eqC4fLgBFMay6igFrAoC25jdtC7mNDIIQtTCeAGVi1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:58:11.629474Z"},"content_sha256":"bd9a01a5cbe95d8bcd56c3b703315b486aafef6413fa13ef550c0a96874787ef","schema_version":"1.0","event_id":"sha256:bd9a01a5cbe95d8bcd56c3b703315b486aafef6413fa13ef550c0a96874787ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:OUV7UOKT4AYW7HTG27PBGOSAF6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:22:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CNVGXG1N2Zy8h5lNJe471UVBUgpip2pSGFRZ3R0pUIvzbEIRPPY7ipQcF8VLnprMxZ9sOmVHoca9kvcnGZv9AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T09:58:11.630090Z"},"content_sha256":"355c426f2168c082a9d6918bb986f789e1150bc2b5d0f153bcc60e449fed013c","schema_version":"1.0","event_id":"sha256:355c426f2168c082a9d6918bb986f789e1150bc2b5d0f153bcc60e449fed013c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/bundle.json","state_url":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T09:58:11Z","links":{"resolver":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6","bundle":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/bundle.json","state":"https://pith.science/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OUV7UOKT4AYW7HTG27PBGOSAF6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OUV7UOKT4AYW7HTG27PBGOSAF6","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":"43e780d20ba3139f276beac7577a1851f684eef4d0921513954416f00a4f115a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-07-16T06:19:14Z","title_canon_sha256":"e82b047f00f5bb2c3d7b13c70111c9245e46e95b3879503e0b19a1da8f5c05f1"},"schema_version":"1.0","source":{"id":"2407.11418","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.11418","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"arxiv_version","alias_value":"2407.11418v3","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.11418","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_12","alias_value":"OUV7UOKT4AYW","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_16","alias_value":"OUV7UOKT4AYW7HTG","created_at":"2026-07-05T10:22:02Z"},{"alias_kind":"pith_short_8","alias_value":"OUV7UOKT","created_at":"2026-07-05T10:22:02Z"}],"graph_snapshots":[{"event_id":"sha256:355c426f2168c082a9d6918bb986f789e1150bc2b5d0f153bcc60e449fed013c","target":"graph","created_at":"2026-07-05T10:22:02Z","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/2407.11418/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Carlos Guestrin, Harshit Gupta, Liana Patel, Matei Zaharia, Melissa Pan, Parth Asawa, Siddharth Jha","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-07-16T06:19:14Z","title":"Semantic Operators: A Declarative Model for Rich, AI-based Data Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.11418","kind":"arxiv","version":3},"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:bd9a01a5cbe95d8bcd56c3b703315b486aafef6413fa13ef550c0a96874787ef","target":"record","created_at":"2026-07-05T10:22:02Z","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":"43e780d20ba3139f276beac7577a1851f684eef4d0921513954416f00a4f115a","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-07-16T06:19:14Z","title_canon_sha256":"e82b047f00f5bb2c3d7b13c70111c9245e46e95b3879503e0b19a1da8f5c05f1"},"schema_version":"1.0","source":{"id":"2407.11418","kind":"arxiv","version":3}},"canonical_sha256":"752bfa3953e0316f9e66d7de133a402f8e058949fecada1d6c1b2532862ac498","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"752bfa3953e0316f9e66d7de133a402f8e058949fecada1d6c1b2532862ac498","first_computed_at":"2026-07-05T10:22:02.244838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:22:02.244838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"E4bK366saAX6zKQqEb8rWjCL6t7HC8uvtLs+WYOPS1O2dibNf0jDiWr2vtqW90pB73mJLNaVlyyl5p57gXxBBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:22:02.245369Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.11418","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd9a01a5cbe95d8bcd56c3b703315b486aafef6413fa13ef550c0a96874787ef","sha256:355c426f2168c082a9d6918bb986f789e1150bc2b5d0f153bcc60e449fed013c"],"state_sha256":"869937653b24b65fdf54dd529f43c0249c131fbdaaf89013297ae7eb6ff572bc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eXrI85VARMn+LJ9isNsNHxUE8ImxAe2Ayyu03XlwbR62bN991oP1YCaQVqHdA/pHdi1OOSbwrINZRgTX1EurCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T09:58:11.634885Z","bundle_sha256":"f93122aa0ea88602f5781c2d936fdd19149683a82932933366b8601dc99ac3a5"}}