{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4RB267XWEXBLX37EMMKWFJHUHL","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":"2fef48325ed1c7e033bef879b22e6a3edbc2beb7672d2cb4665053bddf3591ec","cross_cats_sorted":["cs.AI","cs.DL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T12:06:18Z","title_canon_sha256":"e7f02efe79adde111365a18ccabe8da263b4a491601cc0616c0c3072083da5d9"},"schema_version":"1.0","source":{"id":"2607.09324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09324","created_at":"2026-07-13T01:19:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09324v1","created_at":"2026-07-13T01:19:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09324","created_at":"2026-07-13T01:19:02Z"},{"alias_kind":"pith_short_12","alias_value":"4RB267XWEXBL","created_at":"2026-07-13T01:19:02Z"},{"alias_kind":"pith_short_16","alias_value":"4RB267XWEXBLX37E","created_at":"2026-07-13T01:19:02Z"},{"alias_kind":"pith_short_8","alias_value":"4RB267XW","created_at":"2026-07-13T01:19:02Z"}],"graph_snapshots":[{"event_id":"sha256:86c58e97c94b13e4bdc403ff66f1c7a6b0ef653b56fd856e7b6f95b08c247e24","target":"graph","created_at":"2026-07-13T01:19:02Z","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/2607.09324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Identifying and assigning keywords at scale is a technical, practical, and ethical challenge for crowdsourced collections. This article reports the findings of the \"Extracting Keywords from Crowdsourced Collections\" project, which used the Their Finest Hour Online Archive, a crowdsourced Second World War digital collection hosted by the University of Oxford, as a case study. The project evaluated three Natural Language Processing approaches to automate keyword extraction: Named Entity Recognition, Keyword Extraction, and Topic Modelling. It tested these approaches across a range of artificial ","authors_text":"Catherine Conisbee, Matthew Kidd, Miguel Arana-Catania","cross_cats":["cs.AI","cs.DL","cs.IR","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T12:06:18Z","title":"Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09324","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":"sha256:56b282194511679c555867e92e03783ddef80f019bf78c6a6b0e26760a85122f","target":"record","created_at":"2026-07-13T01:19:02Z","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":"2fef48325ed1c7e033bef879b22e6a3edbc2beb7672d2cb4665053bddf3591ec","cross_cats_sorted":["cs.AI","cs.DL","cs.IR","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T12:06:18Z","title_canon_sha256":"e7f02efe79adde111365a18ccabe8da263b4a491601cc0616c0c3072083da5d9"},"schema_version":"1.0","source":{"id":"2607.09324","kind":"arxiv","version":1}},"canonical_sha256":"e443af7ef625c2bbefe4631562a4f43ae7e6ed12388d59cc339e479f1c882e95","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e443af7ef625c2bbefe4631562a4f43ae7e6ed12388d59cc339e479f1c882e95","first_computed_at":"2026-07-13T01:19:02.532395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-13T01:19:02.532395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"efhrKOn+/GFb4DpvDLUgVbI7r5DUutuQNmZZl8gr3e0zoApqknITC7rfQmeuC4jqwSZX9SAl4f5DdUhDJlzvAg==","signature_status":"signed_v1","signed_at":"2026-07-13T01:19:02.533814Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:56b282194511679c555867e92e03783ddef80f019bf78c6a6b0e26760a85122f","sha256:86c58e97c94b13e4bdc403ff66f1c7a6b0ef653b56fd856e7b6f95b08c247e24"],"state_sha256":"037f775f57957751fcf4fb6e0d67bee496a2235b1e0e76bc3c58d3d5b66d466d"}