{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7WNAJ25MA6VOMYG26OIVKP5473","short_pith_number":"pith:7WNAJ25M","schema_version":"1.0","canonical_sha256":"fd9a04ebac07aae660daf391553fbcfec28166ec53f14e6044fc7c31845d39f1","source":{"kind":"arxiv","id":"2310.16746","version":1},"attestation_state":"computed","paper":{"title":"HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adaku Uchendu, Dongwon Lee, Fosca Giannotti, Mattia Setzu, Nafis Irtiza Tripto, Thai Le","submitted_at":"2023-10-25T16:23:17Z","abstract_excerpt":"Authorship Analysis, also known as stylometry, has been an essential aspect of Natural Language Processing (NLP) for a long time. Likewise, the recent advancement of Large Language Models (LLMs) has made authorship analysis increasingly crucial for distinguishing between human-written and AI-generated texts. However, these authorship analysis tasks have primarily been focused on written texts, not considering spoken texts. Thus, we introduce the largest benchmark for spoken texts - HANSEN (Human ANd ai Spoken tExt beNchmark). HANSEN encompasses meticulous curation of existing speech datasets a"},"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":"2310.16746","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T16:23:17Z","cross_cats_sorted":[],"title_canon_sha256":"c00054ad56d56f055a0abae043a606000379c66aa4f0644906c2958f98a81aa0","abstract_canon_sha256":"a9bc4b0b60279fe952d34565db9ab1598a067eb39d588df298c696eb8b177541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:05:02.416090Z","signature_b64":"nkdx7pVAiKdVRxN/4pi8a/NXysHBpLbPdd9an8nSh7vXStd80+abIKgZ8r+fphSZCQ4D+9R9yBW7ClhwtNDwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd9a04ebac07aae660daf391553fbcfec28166ec53f14e6044fc7c31845d39f1","last_reissued_at":"2026-07-05T07:05:02.415514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:05:02.415514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HANSEN: Human and AI Spoken Text Benchmark for Authorship Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adaku Uchendu, Dongwon Lee, Fosca Giannotti, Mattia Setzu, Nafis Irtiza Tripto, Thai Le","submitted_at":"2023-10-25T16:23:17Z","abstract_excerpt":"Authorship Analysis, also known as stylometry, has been an essential aspect of Natural Language Processing (NLP) for a long time. Likewise, the recent advancement of Large Language Models (LLMs) has made authorship analysis increasingly crucial for distinguishing between human-written and AI-generated texts. However, these authorship analysis tasks have primarily been focused on written texts, not considering spoken texts. Thus, we introduce the largest benchmark for spoken texts - HANSEN (Human ANd ai Spoken tExt beNchmark). HANSEN encompasses meticulous curation of existing speech datasets a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16746","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/2310.16746/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":"2310.16746","created_at":"2026-07-05T07:05:02.415593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.16746v1","created_at":"2026-07-05T07:05:02.415593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16746","created_at":"2026-07-05T07:05:02.415593+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WNAJ25MA6VO","created_at":"2026-07-05T07:05:02.415593+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WNAJ25MA6VOMYG2","created_at":"2026-07-05T07:05:02.415593+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WNAJ25M","created_at":"2026-07-05T07:05:02.415593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07287","citing_title":"Paladin: Defending LLM-enabled Phishing Emails with a New Trigger-Tag Paradigm","ref_index":66,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473","json":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473.json","graph_json":"https://pith.science/api/pith-number/7WNAJ25MA6VOMYG26OIVKP5473/graph.json","events_json":"https://pith.science/api/pith-number/7WNAJ25MA6VOMYG26OIVKP5473/events.json","paper":"https://pith.science/paper/7WNAJ25M"},"agent_actions":{"view_html":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473","download_json":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473.json","view_paper":"https://pith.science/paper/7WNAJ25M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.16746&json=true","fetch_graph":"https://pith.science/api/pith-number/7WNAJ25MA6VOMYG26OIVKP5473/graph.json","fetch_events":"https://pith.science/api/pith-number/7WNAJ25MA6VOMYG26OIVKP5473/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473/action/storage_attestation","attest_author":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473/action/author_attestation","sign_citation":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473/action/citation_signature","submit_replication":"https://pith.science/pith/7WNAJ25MA6VOMYG26OIVKP5473/action/replication_record"}},"created_at":"2026-07-05T07:05:02.415593+00:00","updated_at":"2026-07-05T07:05:02.415593+00:00"}