{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LR7DXXV3UHOEUP5OPFZHV4G55H","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":"4509dbd44e5e1f81ad902a54d12b5046cf8746be5790fb9e7bca23aa3a0d888f","cross_cats_sorted":["cs.HC","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T13:07:22Z","title_canon_sha256":"6e3f3996c7b46edf5184e8720e412a9d616b12df154e2774a0f9636a1a935025"},"schema_version":"1.0","source":{"id":"2302.09324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.09324","created_at":"2026-07-05T05:43:24Z"},{"alias_kind":"arxiv_version","alias_value":"2302.09324v1","created_at":"2026-07-05T05:43:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.09324","created_at":"2026-07-05T05:43:24Z"},{"alias_kind":"pith_short_12","alias_value":"LR7DXXV3UHOE","created_at":"2026-07-05T05:43:24Z"},{"alias_kind":"pith_short_16","alias_value":"LR7DXXV3UHOEUP5O","created_at":"2026-07-05T05:43:24Z"},{"alias_kind":"pith_short_8","alias_value":"LR7DXXV3","created_at":"2026-07-05T05:43:24Z"}],"graph_snapshots":[{"event_id":"sha256:aafc82a0f9ab9db2b42d9f3d4006f848794340a805f5ee4dcc801af961e8896a","target":"graph","created_at":"2026-07-05T05:43:24Z","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/2302.09324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While humans can extract information from unstructured text with high precision and recall, this is often too time-consuming to be practical. Automated approaches, on the other hand, produce nearly-immediate results, but may not be reliable enough for high-stakes applications where precision is essential. In this work, we consider the benefits and drawbacks of various human-only, human-machine, and machine-only information extraction approaches. We argue for the utility of a human-in-the-loop approach in applications where high precision is required, but purely manual extraction is infeasible.","authors_text":"Adrian Weller, Bradley Butcher, Darren Cook, Jiri Hron, Miri Zilka","cross_cats":["cs.HC","cs.IR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T13:07:22Z","title":"Optimising Human-Machine Collaboration for Efficient High-Precision Information Extraction from Text Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.09324","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":"sha256:7d2b4a74d9e78715df182ae8cd9573a10c035e5760939cecfa3f86ca5030c1ec","target":"record","created_at":"2026-07-05T05:43:24Z","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":"4509dbd44e5e1f81ad902a54d12b5046cf8746be5790fb9e7bca23aa3a0d888f","cross_cats_sorted":["cs.HC","cs.IR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-18T13:07:22Z","title_canon_sha256":"6e3f3996c7b46edf5184e8720e412a9d616b12df154e2774a0f9636a1a935025"},"schema_version":"1.0","source":{"id":"2302.09324","kind":"arxiv","version":1}},"canonical_sha256":"5c7e3bdebba1dc4a3fae79727af0dde9d77c06e351fa912119111e604a2e5ebc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5c7e3bdebba1dc4a3fae79727af0dde9d77c06e351fa912119111e604a2e5ebc","first_computed_at":"2026-07-05T05:43:24.207290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:43:24.207290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HpWmT+UbzFyUBJQihfbunxO3Wjcq39fBFvoGvWOpbP7lB7veE84Dd/GovbmTWo7s+qI+4UJ80eSl9565WcKBBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:43:24.207840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.09324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7d2b4a74d9e78715df182ae8cd9573a10c035e5760939cecfa3f86ca5030c1ec","sha256:aafc82a0f9ab9db2b42d9f3d4006f848794340a805f5ee4dcc801af961e8896a"],"state_sha256":"57b229eaa10560efc9fa1f8d105646b439297335c92437fd78919fd38da5783d"}