{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:BTQ5RES4LXDAFAVF7OI6KXSUO7","short_pith_number":"pith:BTQ5RES4","schema_version":"1.0","canonical_sha256":"0ce1d8925c5dc60282a5fb91e55e5477f4dc6dd8d9fdb0a78da769bc561d304c","source":{"kind":"arxiv","id":"2310.08123","version":1},"attestation_state":"computed","paper":{"title":"Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Yu Hung, Roy Ka-Wei Lee, Yujia Hu, Zhiqiang Hu","submitted_at":"2023-10-12T08:24:15Z","abstract_excerpt":"Authorship verification (AV) is a fundamental task in natural language processing (NLP) and computational linguistics, with applications in forensic analysis, plagiarism detection, and identification of deceptive content. Existing AV techniques, including traditional stylometric and deep learning approaches, face limitations in terms of data requirements and lack of explainability. To address these limitations, this paper proposes PromptAV, a novel technique that leverages Large-Language Models (LLMs) for AV by providing step-by-step stylometric explanation prompts. PromptAV outperforms state-"},"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":"2310.08123","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-12T08:24:15Z","cross_cats_sorted":[],"title_canon_sha256":"bb96ef9a2164f19acdfdadb8590cb6f872b6392d0d272be26530cc289d50135c","abstract_canon_sha256":"b314df79b76bab7d2d4aa1d16e6c435d2878b14f21151529b758e8e7805f3940"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:00:10.414831Z","signature_b64":"SmUvXfTG4VlBjin9mSnZIDYv+qjJ1LuHWjBteOuFZ/f+S/2OPdX674lezSYB6R+gip4hwn3wwMg5wYSqas02BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ce1d8925c5dc60282a5fb91e55e5477f4dc6dd8d9fdb0a78da769bc561d304c","last_reissued_at":"2026-07-05T07:00:10.414370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:00:10.414370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Who Wrote it and Why? Prompting Large-Language Models for Authorship Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chia-Yu Hung, Roy Ka-Wei Lee, Yujia Hu, Zhiqiang Hu","submitted_at":"2023-10-12T08:24:15Z","abstract_excerpt":"Authorship verification (AV) is a fundamental task in natural language processing (NLP) and computational linguistics, with applications in forensic analysis, plagiarism detection, and identification of deceptive content. Existing AV techniques, including traditional stylometric and deep learning approaches, face limitations in terms of data requirements and lack of explainability. To address these limitations, this paper proposes PromptAV, a novel technique that leverages Large-Language Models (LLMs) for AV by providing step-by-step stylometric explanation prompts. PromptAV outperforms state-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.08123","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/2310.08123/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":"2310.08123","created_at":"2026-07-05T07:00:10.414427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.08123v1","created_at":"2026-07-05T07:00:10.414427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.08123","created_at":"2026-07-05T07:00:10.414427+00:00"},{"alias_kind":"pith_short_12","alias_value":"BTQ5RES4LXDA","created_at":"2026-07-05T07:00:10.414427+00:00"},{"alias_kind":"pith_short_16","alias_value":"BTQ5RES4LXDAFAVF","created_at":"2026-07-05T07:00:10.414427+00:00"},{"alias_kind":"pith_short_8","alias_value":"BTQ5RES4","created_at":"2026-07-05T07:00:10.414427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04080","citing_title":"Connecting online criminal behavior with machine learning: Using authorship attribution to analyze and link potential online traffickers","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7","json":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7.json","graph_json":"https://pith.science/api/pith-number/BTQ5RES4LXDAFAVF7OI6KXSUO7/graph.json","events_json":"https://pith.science/api/pith-number/BTQ5RES4LXDAFAVF7OI6KXSUO7/events.json","paper":"https://pith.science/paper/BTQ5RES4"},"agent_actions":{"view_html":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7","download_json":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7.json","view_paper":"https://pith.science/paper/BTQ5RES4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.08123&json=true","fetch_graph":"https://pith.science/api/pith-number/BTQ5RES4LXDAFAVF7OI6KXSUO7/graph.json","fetch_events":"https://pith.science/api/pith-number/BTQ5RES4LXDAFAVF7OI6KXSUO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7/action/storage_attestation","attest_author":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7/action/author_attestation","sign_citation":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7/action/citation_signature","submit_replication":"https://pith.science/pith/BTQ5RES4LXDAFAVF7OI6KXSUO7/action/replication_record"}},"created_at":"2026-07-05T07:00:10.414427+00:00","updated_at":"2026-07-05T07:00:10.414427+00:00"}