{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ONGTOAKYHX3LCAKJ3WQB4N4EOL","short_pith_number":"pith:ONGTOAKY","schema_version":"1.0","canonical_sha256":"734d3701583df6b10149dda01e378472d06c38ca3d10467cf6a5a27f335b801d","source":{"kind":"arxiv","id":"2310.15100","version":1},"attestation_state":"computed","paper":{"title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aiping Xiong, Lun-Wei Ku, Shih-Chieh Dai","submitted_at":"2023-10-23T17:05:59Z","abstract_excerpt":"Thematic analysis (TA) has been widely used for analyzing qualitative data in many disciplines and fields. To ensure reliable analysis, the same piece of data is typically assigned to at least two human coders. Moreover, to produce meaningful and useful analysis, human coders develop and deepen their data interpretation and coding over multiple iterations, making TA labor-intensive and time-consuming. Recently the emerging field of large language models (LLMs) research has shown that LLMs have the potential replicate human-like behavior in various tasks: in particular, LLMs outperform crowd wo"},"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":"2310.15100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-23T17:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"4dac5a8a9291639cebf7fb41fe7d3e7614fe4f2e79c0c1ff45203c5d88f20701","abstract_canon_sha256":"006751afc1bfd634fdee9712cd032a89c14a20150c2d4847f58fbbbb8cb01b02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:06.082109Z","signature_b64":"qVruTqKSrQxeU/OU4Bgo7Lb12Eh62PlmEnP7uz8k5DN5PAZP3+VpwCaEsiGNq4UhdXc33t9B3k760w5yYZY9AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"734d3701583df6b10149dda01e378472d06c38ca3d10467cf6a5a27f335b801d","last_reissued_at":"2026-07-05T07:04:06.081686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:06.081686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM-in-the-loop: Leveraging Large Language Model for Thematic Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aiping Xiong, Lun-Wei Ku, Shih-Chieh Dai","submitted_at":"2023-10-23T17:05:59Z","abstract_excerpt":"Thematic analysis (TA) has been widely used for analyzing qualitative data in many disciplines and fields. To ensure reliable analysis, the same piece of data is typically assigned to at least two human coders. Moreover, to produce meaningful and useful analysis, human coders develop and deepen their data interpretation and coding over multiple iterations, making TA labor-intensive and time-consuming. Recently the emerging field of large language models (LLMs) research has shown that LLMs have the potential replicate human-like behavior in various tasks: in particular, LLMs outperform crowd wo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15100","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/2310.15100/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":"2310.15100","created_at":"2026-07-05T07:04:06.081740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15100v1","created_at":"2026-07-05T07:04:06.081740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15100","created_at":"2026-07-05T07:04:06.081740+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONGTOAKYHX3L","created_at":"2026-07-05T07:04:06.081740+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONGTOAKYHX3LCAKJ","created_at":"2026-07-05T07:04:06.081740+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONGTOAKY","created_at":"2026-07-05T07:04:06.081740+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2506.21582","citing_title":"VIDEE: Visual and Interactive Decomposition, Execution, and Evaluation of Text Analytics with Intelligent Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10834","citing_title":"LLMs for Qualitative Data Analysis Fail on Security-specificComments in Human Experiments","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07562","citing_title":"Reasoning-Based Refinement of Unsupervised Text Clusters with LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20131","citing_title":"Whose Story Gets Told? Positionality and Bias in LLM Summaries of Life Narratives","ref_index":46,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL","json":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL.json","graph_json":"https://pith.science/api/pith-number/ONGTOAKYHX3LCAKJ3WQB4N4EOL/graph.json","events_json":"https://pith.science/api/pith-number/ONGTOAKYHX3LCAKJ3WQB4N4EOL/events.json","paper":"https://pith.science/paper/ONGTOAKY"},"agent_actions":{"view_html":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL","download_json":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL.json","view_paper":"https://pith.science/paper/ONGTOAKY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15100&json=true","fetch_graph":"https://pith.science/api/pith-number/ONGTOAKYHX3LCAKJ3WQB4N4EOL/graph.json","fetch_events":"https://pith.science/api/pith-number/ONGTOAKYHX3LCAKJ3WQB4N4EOL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL/action/storage_attestation","attest_author":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL/action/author_attestation","sign_citation":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL/action/citation_signature","submit_replication":"https://pith.science/pith/ONGTOAKYHX3LCAKJ3WQB4N4EOL/action/replication_record"}},"created_at":"2026-07-05T07:04:06.081740+00:00","updated_at":"2026-07-05T07:04:06.081740+00:00"}