{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:23NNQ6EODBKEEREPDJE2XVOLVW","short_pith_number":"pith:23NNQ6EO","canonical_record":{"source":{"id":"2410.12189","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-16T03:22:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78a04a2fe22b6facadb6f3143e6ae0ba676b2118f8ddc6c9bfb6da7e347f0bd4","abstract_canon_sha256":"ca26eec14157c174ff7f9c3d4ec712e27dd820e9f8bdc9219d268fb27c370245"},"schema_version":"1.0"},"canonical_sha256":"d6dad8788e185442448f1a49abd5cbadb7d2eb922f040bf07ed2610b6fb97d4e","source":{"kind":"arxiv","id":"2410.12189","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12189","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12189v3","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12189","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_12","alias_value":"23NNQ6EODBKE","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_16","alias_value":"23NNQ6EODBKEEREP","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_8","alias_value":"23NNQ6EO","created_at":"2026-07-05T10:43:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:23NNQ6EODBKEEREPDJE2XVOLVW","target":"record","payload":{"canonical_record":{"source":{"id":"2410.12189","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-16T03:22:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"78a04a2fe22b6facadb6f3143e6ae0ba676b2118f8ddc6c9bfb6da7e347f0bd4","abstract_canon_sha256":"ca26eec14157c174ff7f9c3d4ec712e27dd820e9f8bdc9219d268fb27c370245"},"schema_version":"1.0"},"canonical_sha256":"d6dad8788e185442448f1a49abd5cbadb7d2eb922f040bf07ed2610b6fb97d4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:02.387254Z","signature_b64":"aKO3Sz15x3RvINgDLuInOwDBEub1k7KvYm6hAk5JC0wLgRS+tk6f7RKtrLM1fBaIwxa3KM8fT1RN00Ep4TQMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6dad8788e185442448f1a49abd5cbadb7d2eb922f040bf07ed2610b6fb97d4e","last_reissued_at":"2026-07-05T10:43:02.386819Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:02.386819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.12189","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":"2026-07-05T10:43:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6kEMq4EKfBjKVL31/cMofxNlKhs6QgzmbiKMDvlc2KxxAlX23HhfRDkHs4i5C0oB9Bo6yJPxSRo4Qy0WauDFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:36:24.170975Z"},"content_sha256":"1296be350331b3b1fc0284f6f53ecc5bd8e18b42398b7743e1680766fd7a7ce2","schema_version":"1.0","event_id":"sha256:1296be350331b3b1fc0284f6f53ecc5bd8e18b42398b7743e1680766fd7a7ce2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:23NNQ6EODBKEEREPDJE2XVOLVW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Aditya G. Parameswaran, Eugene Wu, Shreya Shankar, Tarak Shah, Tristan Chambers","submitted_at":"2024-10-16T03:22:35Z","abstract_excerpt":"Analyzing unstructured data has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered processing of unstructured data. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving accuracy, executing most operations as-is (in a single LLM call). This is problematic for complex tasks and data, where LLM outputs for user-defined operations are often inaccurate, even with optimized prompts. For example, an L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12189","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/2410.12189/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":"2026-07-05T10:43:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"82/Rt1RZ+Nwh1qmECSJjB37qNSbbvx3ttczJlQIzKpApY6oQKuRFvYtszY3WRjIJrYlLR/tyrLl9EdY46QdxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T07:36:24.171359Z"},"content_sha256":"999745faebb16644677c63293ad168012cdd9d8f611df2c52a76153663b80206","schema_version":"1.0","event_id":"sha256:999745faebb16644677c63293ad168012cdd9d8f611df2c52a76153663b80206"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/23NNQ6EODBKEEREPDJE2XVOLVW/bundle.json","state_url":"https://pith.science/pith/23NNQ6EODBKEEREPDJE2XVOLVW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/23NNQ6EODBKEEREPDJE2XVOLVW/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":"2026-08-01T07:36:24Z","links":{"resolver":"https://pith.science/pith/23NNQ6EODBKEEREPDJE2XVOLVW","bundle":"https://pith.science/pith/23NNQ6EODBKEEREPDJE2XVOLVW/bundle.json","state":"https://pith.science/pith/23NNQ6EODBKEEREPDJE2XVOLVW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/23NNQ6EODBKEEREPDJE2XVOLVW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:23NNQ6EODBKEEREPDJE2XVOLVW","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":"ca26eec14157c174ff7f9c3d4ec712e27dd820e9f8bdc9219d268fb27c370245","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-16T03:22:35Z","title_canon_sha256":"78a04a2fe22b6facadb6f3143e6ae0ba676b2118f8ddc6c9bfb6da7e347f0bd4"},"schema_version":"1.0","source":{"id":"2410.12189","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.12189","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"arxiv_version","alias_value":"2410.12189v3","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.12189","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_12","alias_value":"23NNQ6EODBKE","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_16","alias_value":"23NNQ6EODBKEEREP","created_at":"2026-07-05T10:43:02Z"},{"alias_kind":"pith_short_8","alias_value":"23NNQ6EO","created_at":"2026-07-05T10:43:02Z"}],"graph_snapshots":[{"event_id":"sha256:999745faebb16644677c63293ad168012cdd9d8f611df2c52a76153663b80206","target":"graph","created_at":"2026-07-05T10:43:02Z","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/2410.12189/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Analyzing unstructured data has been a persistent challenge in data processing. Large Language Models (LLMs) have shown promise in this regard, leading to recent proposals for declarative frameworks for LLM-powered processing of unstructured data. However, these frameworks focus on reducing cost when executing user-specified operations using LLMs, rather than improving accuracy, executing most operations as-is (in a single LLM call). This is problematic for complex tasks and data, where LLM outputs for user-defined operations are often inaccurate, even with optimized prompts. For example, an L","authors_text":"Aditya G. Parameswaran, Eugene Wu, Shreya Shankar, Tarak Shah, Tristan Chambers","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-16T03:22:35Z","title":"DocETL: Agentic Query Rewriting and Evaluation for Complex Document Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.12189","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":"sha256:1296be350331b3b1fc0284f6f53ecc5bd8e18b42398b7743e1680766fd7a7ce2","target":"record","created_at":"2026-07-05T10:43:02Z","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":"ca26eec14157c174ff7f9c3d4ec712e27dd820e9f8bdc9219d268fb27c370245","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2024-10-16T03:22:35Z","title_canon_sha256":"78a04a2fe22b6facadb6f3143e6ae0ba676b2118f8ddc6c9bfb6da7e347f0bd4"},"schema_version":"1.0","source":{"id":"2410.12189","kind":"arxiv","version":3}},"canonical_sha256":"d6dad8788e185442448f1a49abd5cbadb7d2eb922f040bf07ed2610b6fb97d4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6dad8788e185442448f1a49abd5cbadb7d2eb922f040bf07ed2610b6fb97d4e","first_computed_at":"2026-07-05T10:43:02.386819Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:43:02.386819Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aKO3Sz15x3RvINgDLuInOwDBEub1k7KvYm6hAk5JC0wLgRS+tk6f7RKtrLM1fBaIwxa3KM8fT1RN00Ep4TQMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:43:02.387254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.12189","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1296be350331b3b1fc0284f6f53ecc5bd8e18b42398b7743e1680766fd7a7ce2","sha256:999745faebb16644677c63293ad168012cdd9d8f611df2c52a76153663b80206"],"state_sha256":"4c825f986c62552d111fff5457062ce0256606a07d0df49655117d25c1e44da3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V5r2c1VDxr6W45cazR6LyLl8YFLFkWvuU1PhakunLcUchXAgc5vV5eA3BoyLlTn+ZXofdxyqNyDkp3LTVqpXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T07:36:24.174180Z","bundle_sha256":"ef43e706337a2101279eed841a478102bd392ba856e8bd70c43657b8e62c5588"}}