{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:GHX4G5UAOD5TIRBWQAW6BQYW2Q","short_pith_number":"pith:GHX4G5UA","canonical_record":{"source":{"id":"2608.08261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T17:47:31Z","cross_cats_sorted":[],"title_canon_sha256":"a4858b6bd854b5b39c46edb694f2b4f2e5caf424c69f3e29de6881c9fd281cc5","abstract_canon_sha256":"447542a3d200332139cb7730a39aabf7267651d89e225ac956c5f081328fa12d"},"schema_version":"1.0"},"canonical_sha256":"31efc3768070fb344436802de0c316d40b180076a97a0fa0cfb427887112d522","source":{"kind":"arxiv","id":"2608.08261","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08261","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08261v1","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08261","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"GHX4G5UAOD5T","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"GHX4G5UAOD5TIRBW","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"GHX4G5UA","created_at":"2026-08-11T01:22:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:GHX4G5UAOD5TIRBWQAW6BQYW2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2608.08261","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T17:47:31Z","cross_cats_sorted":[],"title_canon_sha256":"a4858b6bd854b5b39c46edb694f2b4f2e5caf424c69f3e29de6881c9fd281cc5","abstract_canon_sha256":"447542a3d200332139cb7730a39aabf7267651d89e225ac956c5f081328fa12d"},"schema_version":"1.0"},"canonical_sha256":"31efc3768070fb344436802de0c316d40b180076a97a0fa0cfb427887112d522","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-11T01:22:09.244601Z","signature_b64":"YSevYZN3ZzdDLHexbyqCkpvKiL0SgeB9Wf/4AionKQ/U3wLR74zdKwdU4jx+CyV5CLWCn02TevcG2wm8gT4nBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31efc3768070fb344436802de0c316d40b180076a97a0fa0cfb427887112d522","last_reissued_at":"2026-08-11T01:22:09.242240Z","signature_status":"signed_v1","first_computed_at":"2026-08-11T01:22:09.242240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.08261","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-11T01:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H6zMTPmenSx1rhMEiy0/oZUr77jduC3AVXzldTvSLy8GYtHTit1O1Qo9i3TG4DuwplavAeBTrnrdp9HrEEx3Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:05:52.669771Z"},"content_sha256":"8a9fa399b3012fa4ba7ea40e6f70867b20c3c2c909b8dab537de98fa53777ea2","schema_version":"1.0","event_id":"sha256:8a9fa399b3012fa4ba7ea40e6f70867b20c3c2c909b8dab537de98fa53777ea2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:GHX4G5UAOD5TIRBWQAW6BQYW2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scout: Scalable Document Extraction via Data Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Aditya G. Parameswaran, Chiyu Hao, Shreya Shankar, Yiming Lin","submitted_at":"2026-08-08T17:47:31Z","abstract_excerpt":"Extracting values from large document collections powers data analysis across many domains. Frontier LLMs extract such values accurately, but processing an\n  entire collection with one is prohibitively costly. Yet this cost is largely avoidable: real-world collections exhibit rich similarity, so for the same query\n  over similar documents, the answer tends to recur in similar locations; an LLM need only read that small span, not the whole document. Prior methods that\n  exploit this similarity fall short: they either assume a rigid document structure, or assume the answer is a set of substrings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08261","kind":"arxiv","version":1},"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/2608.08261/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":"2026-08-11T01:22:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8p8j5KIw4+f5moCjdG3OaFtKc0Iur5IGtyyK/o3tzN1F3PBS7kKQmszgt7RoXA1nvmt6mn7WDyLtKl1lWKDFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:05:52.670142Z"},"content_sha256":"a1b9fba5befd9abbd92419ebe6f81da6129e754e471490ea222134a7b561758e","schema_version":"1.0","event_id":"sha256:a1b9fba5befd9abbd92419ebe6f81da6129e754e471490ea222134a7b561758e"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:GHX4G5UAOD5TIRBWQAW6BQYW2Q","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1038/s41597-022-01899-x) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Alistair E. W. Johnson, Lucas Bulgarelli, Lu Shen, Alvin Gayles, Ayad Shammout, Steven Horng, Tom J. Pollard, Sicheng Hao, Benjamin Moody, Brian Gow, Li wei H. Lehman, Leo A. Celi, and Roger G. Mark. 2023. MIMIC-IV, a freely accessible elec","arxiv_id":"2608.08261","detector":"doi_compliance","evidence":{"ref_index":25,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1038/s41597-","reconstructed_doi":"10.1038/s41597-022-01899-x"},"severity":"advisory","ref_index":25,"audited_at":"2026-08-12T00:28:29.771971Z","event_type":"pith.integrity.v1","detected_doi":"10.1038/s41597-022-01899-x","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"1e65b69976189cb57ee6069f0e2c835257ebab9adce4e96e692aa99a8fe84d24","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":19184,"payload_sha256":"ed4f3393c216c5c46c68d4f9b6556a20a7e784235c2b2a84bee9337fd79e8579","signature_b64":"SLNlzAvZMnt77kWx//LbO80Jta899Urk2iQYMRclXUWSWnqaGas8eFTBEsXh+I1sGCjWQlcBviAu1qxeHrIeCg==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-12T00:28:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vPILllhs3Zjgk9SqfupWtBltWtcbPbvORDwmV4slai7BiluEiITYPz7vCQSHws1HXScHtJcc9j4mSEFIc8LzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:05:52.671515Z"},"content_sha256":"e30551269148629d2f93db62e08c8785ed38be8825b16f936daf6dd51c58298b","schema_version":"1.0","event_id":"sha256:e30551269148629d2f93db62e08c8785ed38be8825b16f936daf6dd51c58298b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q/bundle.json","state_url":"https://pith.science/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q/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":"2026-08-13T01:05:52Z","links":{"resolver":"https://pith.science/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q","bundle":"https://pith.science/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q/bundle.json","state":"https://pith.science/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GHX4G5UAOD5TIRBWQAW6BQYW2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GHX4G5UAOD5TIRBWQAW6BQYW2Q","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"447542a3d200332139cb7730a39aabf7267651d89e225ac956c5f081328fa12d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T17:47:31Z","title_canon_sha256":"a4858b6bd854b5b39c46edb694f2b4f2e5caf424c69f3e29de6881c9fd281cc5"},"schema_version":"1.0","source":{"id":"2608.08261","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08261","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08261v1","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08261","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"pith_short_12","alias_value":"GHX4G5UAOD5T","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"pith_short_16","alias_value":"GHX4G5UAOD5TIRBW","created_at":"2026-08-11T01:22:09Z"},{"alias_kind":"pith_short_8","alias_value":"GHX4G5UA","created_at":"2026-08-11T01:22:09Z"}],"graph_snapshots":[{"event_id":"sha256:a1b9fba5befd9abbd92419ebe6f81da6129e754e471490ea222134a7b561758e","target":"graph","created_at":"2026-08-11T01:22:09Z","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/2608.08261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting values from large document collections powers data analysis across many domains. Frontier LLMs extract such values accurately, but processing an\n  entire collection with one is prohibitively costly. Yet this cost is largely avoidable: real-world collections exhibit rich similarity, so for the same query\n  over similar documents, the answer tends to recur in similar locations; an LLM need only read that small span, not the whole document. Prior methods that\n  exploit this similarity fall short: they either assume a rigid document structure, or assume the answer is a set of substrings","authors_text":"Aditya G. Parameswaran, Chiyu Hao, Shreya Shankar, Yiming Lin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T17:47:31Z","title":"Scout: Scalable Document Extraction via Data Similarity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08261","kind":"arxiv","version":1},"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":"sha256:8a9fa399b3012fa4ba7ea40e6f70867b20c3c2c909b8dab537de98fa53777ea2","target":"record","created_at":"2026-08-11T01:22:09Z","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":"447542a3d200332139cb7730a39aabf7267651d89e225ac956c5f081328fa12d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-08-08T17:47:31Z","title_canon_sha256":"a4858b6bd854b5b39c46edb694f2b4f2e5caf424c69f3e29de6881c9fd281cc5"},"schema_version":"1.0","source":{"id":"2608.08261","kind":"arxiv","version":1}},"canonical_sha256":"31efc3768070fb344436802de0c316d40b180076a97a0fa0cfb427887112d522","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"31efc3768070fb344436802de0c316d40b180076a97a0fa0cfb427887112d522","first_computed_at":"2026-08-11T01:22:09.242240Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:22:09.242240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YSevYZN3ZzdDLHexbyqCkpvKiL0SgeB9Wf/4AionKQ/U3wLR74zdKwdU4jx+CyV5CLWCn02TevcG2wm8gT4nBg==","signature_status":"signed_v1","signed_at":"2026-08-11T01:22:09.244601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08261","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a9fa399b3012fa4ba7ea40e6f70867b20c3c2c909b8dab537de98fa53777ea2","sha256:a1b9fba5befd9abbd92419ebe6f81da6129e754e471490ea222134a7b561758e","sha256:e30551269148629d2f93db62e08c8785ed38be8825b16f936daf6dd51c58298b"],"state_sha256":"c3ce5071ebefa4b83af3457051aff475ddbbc8dcba5fe0a8f3d7528622b02ccd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CaqQ8b3eMjtz2Yb7joR1Xr5c8kjAeWxi/lN2nFqjt1mJhtH5TdaoxmdleQwAPESFuQEj20iB//alXezYxtEuBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:05:52.673012Z","bundle_sha256":"bde68ae1f2573423e73578e7b4c561d7cc75cea463a6fddab29a1e82274d4f06"}}