{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SHCITBJ4IFQC4PDSF5GCCWUJRI","short_pith_number":"pith:SHCITBJ4","canonical_record":{"source":{"id":"2509.02896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-09-02T23:41:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21402d1d1aeaa1ea50340b55c89adad7439d0f50079aa9b6046ea3994ae58bad","abstract_canon_sha256":"77e38be9d99dce9be87679e75a280d7de1baefdff89559b513629454e0f16eb9"},"schema_version":"1.0"},"canonical_sha256":"91c489853c41602e3c722f4c215a898a0ca0d7aaea3aa5bcae22185236186d39","source":{"kind":"arxiv","id":"2509.02896","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02896","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02896v2","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02896","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"SHCITBJ4IFQC","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"SHCITBJ4IFQC4PDS","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"SHCITBJ4","created_at":"2026-07-05T12:10:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SHCITBJ4IFQC4PDSF5GCCWUJRI","target":"record","payload":{"canonical_record":{"source":{"id":"2509.02896","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-09-02T23:41:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"21402d1d1aeaa1ea50340b55c89adad7439d0f50079aa9b6046ea3994ae58bad","abstract_canon_sha256":"77e38be9d99dce9be87679e75a280d7de1baefdff89559b513629454e0f16eb9"},"schema_version":"1.0"},"canonical_sha256":"91c489853c41602e3c722f4c215a898a0ca0d7aaea3aa5bcae22185236186d39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:10:59.955873Z","signature_b64":"8XQGm3JbzeFI+I+i5CfDiWPunInfD0Mk65adVM7vvPiB4S0rkxTD48k+DlVGiY4wN2iyaLhvKwgqKfbDwvdlAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"91c489853c41602e3c722f4c215a898a0ca0d7aaea3aa5bcae22185236186d39","last_reissued_at":"2026-07-05T12:10:59.955343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:10:59.955343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.02896","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4/ouLnQxgHT3KMH6bH3wbRgxdiuuSCopNmVRObDoCSH//8CXaNIxVb87R0tq+CeZZkSSNVAbp1RJmTwxTcg+Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:35.974717Z"},"content_sha256":"29105ef6daf620bc0207908133bb91390dad434e426ea8fadc9e36708d915da9","schema_version":"1.0","event_id":"sha256:29105ef6daf620bc0207908133bb91390dad434e426ea8fadc9e36708d915da9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SHCITBJ4IFQC4PDSF5GCCWUJRI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees","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","submitted_at":"2025-09-02T23:41:50Z","abstract_excerpt":"Large Language Models (LLMs) are being increasingly used as a building block in data systems to process large text datasets. To do so, LLM model providers offer multiple LLMs with different sizes, spanning various cost-quality trade-offs when processing text at scale. Top-of-the-line LLMs (e.g., GPT-4o, Claude Sonnet) operate with high accuracy but are prohibitively expensive when processing many records. To avoid high costs, more affordable but lower quality LLMs (e.g., GPT-4o-mini, Claude Haiku) can be used to process records, but we need to ensure that the overall accuracy does not deviate "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02896","kind":"arxiv","version":2},"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/2509.02896/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":"2026-07-05T12:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/uxLkdMSYqDITasPUzEbzL00iRLxNVBCmlm0sUiYrJi1lxgy0EeHTtJK8dzdSg+COHnwzOwfe4l95GX/oS0NCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T20:46:35.975209Z"},"content_sha256":"6ec7f603ba6141dcedc1f9f17754d5fbf1bd08f4e23301cf7f4b8cc357feaeb6","schema_version":"1.0","event_id":"sha256:6ec7f603ba6141dcedc1f9f17754d5fbf1bd08f4e23301cf7f4b8cc357feaeb6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI/bundle.json","state_url":"https://pith.science/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI/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":"2026-08-05T20:46:35Z","links":{"resolver":"https://pith.science/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI","bundle":"https://pith.science/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI/bundle.json","state":"https://pith.science/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SHCITBJ4IFQC4PDSF5GCCWUJRI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SHCITBJ4IFQC4PDSF5GCCWUJRI","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":"77e38be9d99dce9be87679e75a280d7de1baefdff89559b513629454e0f16eb9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-09-02T23:41:50Z","title_canon_sha256":"21402d1d1aeaa1ea50340b55c89adad7439d0f50079aa9b6046ea3994ae58bad"},"schema_version":"1.0","source":{"id":"2509.02896","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02896","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02896v2","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02896","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"SHCITBJ4IFQC","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"SHCITBJ4IFQC4PDS","created_at":"2026-07-05T12:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"SHCITBJ4","created_at":"2026-07-05T12:10:59Z"}],"graph_snapshots":[{"event_id":"sha256:6ec7f603ba6141dcedc1f9f17754d5fbf1bd08f4e23301cf7f4b8cc357feaeb6","target":"graph","created_at":"2026-07-05T12:10:59Z","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/2509.02896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are being increasingly used as a building block in data systems to process large text datasets. To do so, LLM model providers offer multiple LLMs with different sizes, spanning various cost-quality trade-offs when processing text at scale. Top-of-the-line LLMs (e.g., GPT-4o, Claude Sonnet) operate with high accuracy but are prohibitively expensive when processing many records. To avoid high costs, more affordable but lower quality LLMs (e.g., GPT-4o-mini, Claude Haiku) can be used to process records, but we need to ensure that the overall accuracy does not deviate ","authors_text":"Aditya Parameswaran, Sepanta Zeighami, Shreya Shankar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-09-02T23:41:50Z","title":"Cut Costs, Not Accuracy: LLM-Powered Data Processing with Guarantees"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02896","kind":"arxiv","version":2},"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":"sha256:29105ef6daf620bc0207908133bb91390dad434e426ea8fadc9e36708d915da9","target":"record","created_at":"2026-07-05T12:10:59Z","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":"77e38be9d99dce9be87679e75a280d7de1baefdff89559b513629454e0f16eb9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-09-02T23:41:50Z","title_canon_sha256":"21402d1d1aeaa1ea50340b55c89adad7439d0f50079aa9b6046ea3994ae58bad"},"schema_version":"1.0","source":{"id":"2509.02896","kind":"arxiv","version":2}},"canonical_sha256":"91c489853c41602e3c722f4c215a898a0ca0d7aaea3aa5bcae22185236186d39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"91c489853c41602e3c722f4c215a898a0ca0d7aaea3aa5bcae22185236186d39","first_computed_at":"2026-07-05T12:10:59.955343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:10:59.955343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8XQGm3JbzeFI+I+i5CfDiWPunInfD0Mk65adVM7vvPiB4S0rkxTD48k+DlVGiY4wN2iyaLhvKwgqKfbDwvdlAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:10:59.955873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02896","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29105ef6daf620bc0207908133bb91390dad434e426ea8fadc9e36708d915da9","sha256:6ec7f603ba6141dcedc1f9f17754d5fbf1bd08f4e23301cf7f4b8cc357feaeb6"],"state_sha256":"9aeeb1d7e29d71bbbd6c43ef33d95f73b90a62bb7052b97fa9482efdc94c01b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uOWTZqQZSfNGFnKQTflVCvgWoqbXkuJGJKdTyIpoOUUxlzOgRhl1/SeiGDomX4j1StifodFKslKEN3BjTPIWAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T20:46:35.978728Z","bundle_sha256":"66e3aadab01b82ecea8618a372ea10dce765900802eeac53f8e02bf0eccc9362"}}