{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I4GABHR5O65BETLEL3SZ53G2EN","short_pith_number":"pith:I4GABHR5","canonical_record":{"source":{"id":"2507.06515","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-09T03:30:09Z","cross_cats_sorted":[],"title_canon_sha256":"6dbd57d2f987ac61c0e0ecc9e044567c772765627b6d9f80de08bc650f0ddc64","abstract_canon_sha256":"b0a18c9ce8abe3e51718bc9df3491de99518d613de2ea1bc025bae25a4cbbc8c"},"schema_version":"1.0"},"canonical_sha256":"470c009e3d77ba124d645ee59eecda236ec3131c3aa13e51035ffa4eabacdb39","source":{"kind":"arxiv","id":"2507.06515","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06515","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06515v2","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06515","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"I4GABHR5O65B","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"I4GABHR5O65BETLE","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"I4GABHR5","created_at":"2026-07-05T11:35:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I4GABHR5O65BETLEL3SZ53G2EN","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06515","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-09T03:30:09Z","cross_cats_sorted":[],"title_canon_sha256":"6dbd57d2f987ac61c0e0ecc9e044567c772765627b6d9f80de08bc650f0ddc64","abstract_canon_sha256":"b0a18c9ce8abe3e51718bc9df3491de99518d613de2ea1bc025bae25a4cbbc8c"},"schema_version":"1.0"},"canonical_sha256":"470c009e3d77ba124d645ee59eecda236ec3131c3aa13e51035ffa4eabacdb39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:15.028243Z","signature_b64":"rWqsohwLEpSIN7C/pH6OcUYuicAO9rkM40RZkrzq25Qzfh7O6QzQZTvevv/j1BnrQJRNYfBBN6PVzLrVSRAKDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"470c009e3d77ba124d645ee59eecda236ec3131c3aa13e51035ffa4eabacdb39","last_reissued_at":"2026-07-05T11:35:15.027771Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:15.027771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06515","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":"2026-07-05T11:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RYn4gbHeFLkOkS4s/f+I9msRTTr2iXCBFIzqtyXffRWuA42h2CtTUdZYpewVrurmJZuzzmUEB/zIilj+2i8MBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:23:43.116273Z"},"content_sha256":"9b7b59e30d64102e0d64814e7d970b6c8f5f1a80d97e9e67fb21a58a7bb3e007","schema_version":"1.0","event_id":"sha256:9b7b59e30d64102e0d64814e7d970b6c8f5f1a80d97e9e67fb21a58a7bb3e007"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I4GABHR5O65BETLEL3SZ53G2EN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"QUEST: Query Optimization in Unstructured Document Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Chengliang Chai, Guoren Wang, Han Han, Kaisen Jin, Lei Cao, Qiyan Deng, Xinyu Guo, Ye Yuan, Zhaoze Sun","submitted_at":"2025-07-09T03:30:09Z","abstract_excerpt":"Most recently, researchers have started building large language models (LLMs) powered data systems that allow users to analyze unstructured text documents like working with a database because LLMs are very effective in extracting attributes from documents. In such systems, LLM-based extraction operations constitute the performance bottleneck of query execution due to the high monetary cost and slow LLM inference. Existing systems typically borrow the query optimization principles popular in relational databases to produce query execution plans, which unfortunately are ineffective in minimizing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06515","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/2507.06515/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":"2026-07-05T11:35:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ta/WvNuTeJlGmlN4r9LTtRa0EchH3Au6oEQXfnFh10tzvi0ma/ZlHKAV7PJ3+wKaXYFw+ami2Rkt2qkXKONZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:23:43.116854Z"},"content_sha256":"87675735f03449fee3c5a4619b9ceaa6a5ef7b158416ba0c3ad4f616aeb34b76","schema_version":"1.0","event_id":"sha256:87675735f03449fee3c5a4619b9ceaa6a5ef7b158416ba0c3ad4f616aeb34b76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I4GABHR5O65BETLEL3SZ53G2EN/bundle.json","state_url":"https://pith.science/pith/I4GABHR5O65BETLEL3SZ53G2EN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I4GABHR5O65BETLEL3SZ53G2EN/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":"2026-08-08T11:23:43Z","links":{"resolver":"https://pith.science/pith/I4GABHR5O65BETLEL3SZ53G2EN","bundle":"https://pith.science/pith/I4GABHR5O65BETLEL3SZ53G2EN/bundle.json","state":"https://pith.science/pith/I4GABHR5O65BETLEL3SZ53G2EN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I4GABHR5O65BETLEL3SZ53G2EN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I4GABHR5O65BETLEL3SZ53G2EN","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":"b0a18c9ce8abe3e51718bc9df3491de99518d613de2ea1bc025bae25a4cbbc8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-09T03:30:09Z","title_canon_sha256":"6dbd57d2f987ac61c0e0ecc9e044567c772765627b6d9f80de08bc650f0ddc64"},"schema_version":"1.0","source":{"id":"2507.06515","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06515","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06515v2","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06515","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_12","alias_value":"I4GABHR5O65B","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_16","alias_value":"I4GABHR5O65BETLE","created_at":"2026-07-05T11:35:15Z"},{"alias_kind":"pith_short_8","alias_value":"I4GABHR5","created_at":"2026-07-05T11:35:15Z"}],"graph_snapshots":[{"event_id":"sha256:87675735f03449fee3c5a4619b9ceaa6a5ef7b158416ba0c3ad4f616aeb34b76","target":"graph","created_at":"2026-07-05T11:35:15Z","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/2507.06515/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most recently, researchers have started building large language models (LLMs) powered data systems that allow users to analyze unstructured text documents like working with a database because LLMs are very effective in extracting attributes from documents. In such systems, LLM-based extraction operations constitute the performance bottleneck of query execution due to the high monetary cost and slow LLM inference. Existing systems typically borrow the query optimization principles popular in relational databases to produce query execution plans, which unfortunately are ineffective in minimizing","authors_text":"Chengliang Chai, Guoren Wang, Han Han, Kaisen Jin, Lei Cao, Qiyan Deng, Xinyu Guo, Ye Yuan, Zhaoze Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-09T03:30:09Z","title":"QUEST: Query Optimization in Unstructured Document Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06515","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":"sha256:9b7b59e30d64102e0d64814e7d970b6c8f5f1a80d97e9e67fb21a58a7bb3e007","target":"record","created_at":"2026-07-05T11:35:15Z","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":"b0a18c9ce8abe3e51718bc9df3491de99518d613de2ea1bc025bae25a4cbbc8c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2025-07-09T03:30:09Z","title_canon_sha256":"6dbd57d2f987ac61c0e0ecc9e044567c772765627b6d9f80de08bc650f0ddc64"},"schema_version":"1.0","source":{"id":"2507.06515","kind":"arxiv","version":2}},"canonical_sha256":"470c009e3d77ba124d645ee59eecda236ec3131c3aa13e51035ffa4eabacdb39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"470c009e3d77ba124d645ee59eecda236ec3131c3aa13e51035ffa4eabacdb39","first_computed_at":"2026-07-05T11:35:15.027771Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:15.027771Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rWqsohwLEpSIN7C/pH6OcUYuicAO9rkM40RZkrzq25Qzfh7O6QzQZTvevv/j1BnrQJRNYfBBN6PVzLrVSRAKDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:15.028243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06515","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b7b59e30d64102e0d64814e7d970b6c8f5f1a80d97e9e67fb21a58a7bb3e007","sha256:87675735f03449fee3c5a4619b9ceaa6a5ef7b158416ba0c3ad4f616aeb34b76"],"state_sha256":"fd5178666b120437504a218c5e587f387982b043331af7e6fc82abcb32ae5a6b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r2tKWol1IYZRIeLk4r0BY70d4jjhUnebDXMINM80A6ldXdkBYTgLGhNsi4BkaJM41qACUO0++7vyCsO5OkjpCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:23:43.121179Z","bundle_sha256":"9aadcfffb8716b4bd8c74b63104f260adb78b08a5d1ba636f8fe4b4e68bd3b0d"}}