{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WKSBFAXBAQUVFDRBPPEEBBFXP3","short_pith_number":"pith:WKSBFAXB","schema_version":"1.0","canonical_sha256":"b2a41282e10429528e217bc84084b77ed941f1294d1daf90ab690d3e41a43c50","source":{"kind":"arxiv","id":"2310.18729","version":1},"attestation_state":"computed","paper":{"title":"Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Hannes Westermann, Jakub Dr\\'apal, Jaromir Savelka","submitted_at":"2023-10-28T15:20:44Z","abstract_excerpt":"Thematic analysis and other variants of inductive coding are widely used qualitative analytic methods within empirical legal studies (ELS). We propose a novel framework facilitating effective collaboration of a legal expert with a large language model (LLM) for generating initial codes (phase 2 of thematic analysis), searching for themes (phase 3), and classifying the data in terms of the themes (to kick-start phase 4). We employed the framework for an analysis of a dataset (n=785) of facts descriptions from criminal court opinions regarding thefts. The goal of the analysis was to discover cla"},"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":"2310.18729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-10-28T15:20:44Z","cross_cats_sorted":["cs.CL","cs.HC"],"title_canon_sha256":"4d12e73cc01d2472879cac771c0332bfb11c35f094c0bed88e229c66fab78f72","abstract_canon_sha256":"29dad736f4b67a41dd8e338f0f1dc95d9b3872ed1a281f5ca42b93d6c1d23265"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:40.232666Z","signature_b64":"LjKMYHe4o2tnhr1NQbB7swbbBCupZBWvX5AgQnKcQVzQ3KgtsQwG7W3RVG0EcP05SDle5YiJk1EPquiIFAKQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2a41282e10429528e217bc84084b77ed941f1294d1daf90ab690d3e41a43c50","last_reissued_at":"2026-07-05T07:06:40.232239Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:40.232239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Large Language Models to Support Thematic Analysis in Empirical Legal Studies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.HC"],"primary_cat":"cs.AI","authors_text":"Hannes Westermann, Jakub Dr\\'apal, Jaromir Savelka","submitted_at":"2023-10-28T15:20:44Z","abstract_excerpt":"Thematic analysis and other variants of inductive coding are widely used qualitative analytic methods within empirical legal studies (ELS). We propose a novel framework facilitating effective collaboration of a legal expert with a large language model (LLM) for generating initial codes (phase 2 of thematic analysis), searching for themes (phase 3), and classifying the data in terms of the themes (to kick-start phase 4). We employed the framework for an analysis of a dataset (n=785) of facts descriptions from criminal court opinions regarding thefts. The goal of the analysis was to discover cla"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.18729","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/2310.18729/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":"2310.18729","created_at":"2026-07-05T07:06:40.232296+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.18729v1","created_at":"2026-07-05T07:06:40.232296+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.18729","created_at":"2026-07-05T07:06:40.232296+00:00"},{"alias_kind":"pith_short_12","alias_value":"WKSBFAXBAQUV","created_at":"2026-07-05T07:06:40.232296+00:00"},{"alias_kind":"pith_short_16","alias_value":"WKSBFAXBAQUVFDRB","created_at":"2026-07-05T07:06:40.232296+00:00"},{"alias_kind":"pith_short_8","alias_value":"WKSBFAXB","created_at":"2026-07-05T07:06:40.232296+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3","json":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3.json","graph_json":"https://pith.science/api/pith-number/WKSBFAXBAQUVFDRBPPEEBBFXP3/graph.json","events_json":"https://pith.science/api/pith-number/WKSBFAXBAQUVFDRBPPEEBBFXP3/events.json","paper":"https://pith.science/paper/WKSBFAXB"},"agent_actions":{"view_html":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3","download_json":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3.json","view_paper":"https://pith.science/paper/WKSBFAXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.18729&json=true","fetch_graph":"https://pith.science/api/pith-number/WKSBFAXBAQUVFDRBPPEEBBFXP3/graph.json","fetch_events":"https://pith.science/api/pith-number/WKSBFAXBAQUVFDRBPPEEBBFXP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3/action/storage_attestation","attest_author":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3/action/author_attestation","sign_citation":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3/action/citation_signature","submit_replication":"https://pith.science/pith/WKSBFAXBAQUVFDRBPPEEBBFXP3/action/replication_record"}},"created_at":"2026-07-05T07:06:40.232296+00:00","updated_at":"2026-07-05T07:06:40.232296+00:00"}