{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YKEJF4PFJSOW5AWAM6WY6MMQC6","short_pith_number":"pith:YKEJF4PF","schema_version":"1.0","canonical_sha256":"c28892f1e54c9d6e82c067ad8f3190179fb6df5079c928e10c7667e08b296438","source":{"kind":"arxiv","id":"2405.06919","version":1},"attestation_state":"computed","paper":{"title":"Automating Thematic Analysis: How LLMs Analyse Controversial Topics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Awais Hameed Khan, Daniel Whelan-Shamy, Hiruni Kegalle, Liam Magee, Lida Ghahremanlou, Ned Watt, Rhea D'Silva","submitted_at":"2024-05-11T05:28:25Z","abstract_excerpt":"Large Language Models (LLMs) are promising analytical tools. They can augment human epistemic, cognitive and reasoning abilities, and support 'sensemaking', making sense of a complex environment or subject by analysing large volumes of data with a sensitivity to context and nuance absent in earlier text processing systems. This paper presents a pilot experiment that explores how LLMs can support thematic analysis of controversial topics. We compare how human researchers and two LLMs GPT-4 and Llama 2 categorise excerpts from media coverage of the controversial Australian Robodebt scandal. Our "},"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":"2405.06919","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CY","submitted_at":"2024-05-11T05:28:25Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"681658fbced39c4e26582a843e5767bde989f3584ab49b0aa5e40705bb463f5f","abstract_canon_sha256":"63484ee2c261902257b2e58a55d2d22a52b4b6ca10c13b6feafbb0aeedecc598"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:25.547164Z","signature_b64":"Z+VASDJtKvfRSeNtv5nn8KmltztslDFExickkOXBphJN4y29MIFSpARFgnWP/yOTKEUutdNicSsImEFM7p0fCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c28892f1e54c9d6e82c067ad8f3190179fb6df5079c928e10c7667e08b296438","last_reissued_at":"2026-07-05T09:08:25.546525Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:25.546525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Automating Thematic Analysis: How LLMs Analyse Controversial Topics","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CY","authors_text":"Awais Hameed Khan, Daniel Whelan-Shamy, Hiruni Kegalle, Liam Magee, Lida Ghahremanlou, Ned Watt, Rhea D'Silva","submitted_at":"2024-05-11T05:28:25Z","abstract_excerpt":"Large Language Models (LLMs) are promising analytical tools. They can augment human epistemic, cognitive and reasoning abilities, and support 'sensemaking', making sense of a complex environment or subject by analysing large volumes of data with a sensitivity to context and nuance absent in earlier text processing systems. This paper presents a pilot experiment that explores how LLMs can support thematic analysis of controversial topics. We compare how human researchers and two LLMs GPT-4 and Llama 2 categorise excerpts from media coverage of the controversial Australian Robodebt scandal. Our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.06919","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/2405.06919/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":"2405.06919","created_at":"2026-07-05T09:08:25.546629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.06919v1","created_at":"2026-07-05T09:08:25.546629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.06919","created_at":"2026-07-05T09:08:25.546629+00:00"},{"alias_kind":"pith_short_12","alias_value":"YKEJF4PFJSOW","created_at":"2026-07-05T09:08:25.546629+00:00"},{"alias_kind":"pith_short_16","alias_value":"YKEJF4PFJSOW5AWA","created_at":"2026-07-05T09:08:25.546629+00:00"},{"alias_kind":"pith_short_8","alias_value":"YKEJF4PF","created_at":"2026-07-05T09:08:25.546629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.11198","citing_title":"Temperature and Persona Shape LLM Agent Consensus With Minimal Accuracy Gains in Qualitative Coding","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6","json":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6.json","graph_json":"https://pith.science/api/pith-number/YKEJF4PFJSOW5AWAM6WY6MMQC6/graph.json","events_json":"https://pith.science/api/pith-number/YKEJF4PFJSOW5AWAM6WY6MMQC6/events.json","paper":"https://pith.science/paper/YKEJF4PF"},"agent_actions":{"view_html":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6","download_json":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6.json","view_paper":"https://pith.science/paper/YKEJF4PF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.06919&json=true","fetch_graph":"https://pith.science/api/pith-number/YKEJF4PFJSOW5AWAM6WY6MMQC6/graph.json","fetch_events":"https://pith.science/api/pith-number/YKEJF4PFJSOW5AWAM6WY6MMQC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6/action/storage_attestation","attest_author":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6/action/author_attestation","sign_citation":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6/action/citation_signature","submit_replication":"https://pith.science/pith/YKEJF4PFJSOW5AWAM6WY6MMQC6/action/replication_record"}},"created_at":"2026-07-05T09:08:25.546629+00:00","updated_at":"2026-07-05T09:08:25.546629+00:00"}