{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4RB267XWEXBLX37EMMKWFJHUHL","short_pith_number":"pith:4RB267XW","schema_version":"1.0","canonical_sha256":"e443af7ef625c2bbefe4631562a4f43ae7e6ed12388d59cc339e479f1c882e95","source":{"kind":"arxiv","id":"2607.09324","version":1},"attestation_state":"computed","paper":{"title":"Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Catherine Conisbee, Matthew Kidd, Miguel Arana-Catania","submitted_at":"2026-07-10T12:06:18Z","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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.09324","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T12:06:18Z","cross_cats_sorted":["cs.AI","cs.DL","cs.IR","cs.LG"],"title_canon_sha256":"e7f02efe79adde111365a18ccabe8da263b4a491601cc0616c0c3072083da5d9","abstract_canon_sha256":"2fef48325ed1c7e033bef879b22e6a3edbc2beb7672d2cb4665053bddf3591ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:02.533814Z","signature_b64":"efhrKOn+/GFb4DpvDLUgVbI7r5DUutuQNmZZl8gr3e0zoApqknITC7rfQmeuC4jqwSZX9SAl4f5DdUhDJlzvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e443af7ef625c2bbefe4631562a4f43ae7e6ed12388d59cc339e479f1c882e95","last_reissued_at":"2026-07-13T01:19:02.532395Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:02.532395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Letting the Data Speak: Extracting Keywords from Crowdsourced Collections with AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DL","cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Catherine Conisbee, Matthew Kidd, Miguel Arana-Catania","submitted_at":"2026-07-10T12:06:18Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09324","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/2607.09324/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.09324","created_at":"2026-07-13T01:19:02.532928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09324v1","created_at":"2026-07-13T01:19:02.532928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09324","created_at":"2026-07-13T01:19:02.532928+00:00"},{"alias_kind":"pith_short_12","alias_value":"4RB267XWEXBL","created_at":"2026-07-13T01:19:02.532928+00:00"},{"alias_kind":"pith_short_16","alias_value":"4RB267XWEXBLX37E","created_at":"2026-07-13T01:19:02.532928+00:00"},{"alias_kind":"pith_short_8","alias_value":"4RB267XW","created_at":"2026-07-13T01:19:02.532928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL","json":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL.json","graph_json":"https://pith.science/api/pith-number/4RB267XWEXBLX37EMMKWFJHUHL/graph.json","events_json":"https://pith.science/api/pith-number/4RB267XWEXBLX37EMMKWFJHUHL/events.json","paper":"https://pith.science/paper/4RB267XW"},"agent_actions":{"view_html":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL","download_json":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL.json","view_paper":"https://pith.science/paper/4RB267XW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09324&json=true","fetch_graph":"https://pith.science/api/pith-number/4RB267XWEXBLX37EMMKWFJHUHL/graph.json","fetch_events":"https://pith.science/api/pith-number/4RB267XWEXBLX37EMMKWFJHUHL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL/action/storage_attestation","attest_author":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL/action/author_attestation","sign_citation":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL/action/citation_signature","submit_replication":"https://pith.science/pith/4RB267XWEXBLX37EMMKWFJHUHL/action/replication_record"}},"created_at":"2026-07-13T01:19:02.532928+00:00","updated_at":"2026-07-13T01:19:02.532928+00:00"}