{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P3XJIKG3GSJS2VPRIQKEBVLG4C","short_pith_number":"pith:P3XJIKG3","schema_version":"1.0","canonical_sha256":"7eee9428db34932d55f1441440d566e0a846ad64c4fc4ca9319157bbf22f1be0","source":{"kind":"arxiv","id":"2412.03025","version":1},"attestation_state":"computed","paper":{"title":"Human Variability vs. Machine Consistency: A Linguistic Analysis of Texts Generated by Humans and Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Segun Aroyehun, Sergio E. Zanotto","submitted_at":"2024-12-04T04:38:35Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. Recent research has predominantly focused on using LLMs to classify text as either human-written or machine-generated. In our study, we adopt a different approach by profiling texts spanning four domains based on 250 distinct linguistic features. We select the M4 dataset from the Subtask B of SemEval 2024 Task 8. We automatically calculate various linguistic features with the LFTK t"},"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":"2412.03025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-04T04:38:35Z","cross_cats_sorted":[],"title_canon_sha256":"d037c56d8ac6fd32deacf88816f32f6d774f1f66255438c3d6e043aaa1f08590","abstract_canon_sha256":"8d076d96e5c78ff6f04efd77cb25101577e2ca14ebe1faf0c1e6655a20e872e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:44:23.894965Z","signature_b64":"QH8lMriq6Opr6CDzmd8ZPYxp9vcHomLd2vh+FkcU3zORDBfzFFHdcyAK+uOsBzq09zlBqRQCdfPrkeHce+pcDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eee9428db34932d55f1441440d566e0a846ad64c4fc4ca9319157bbf22f1be0","last_reissued_at":"2026-07-05T09:44:23.894480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:44:23.894480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human Variability vs. Machine Consistency: A Linguistic Analysis of Texts Generated by Humans and Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Segun Aroyehun, Sergio E. Zanotto","submitted_at":"2024-12-04T04:38:35Z","abstract_excerpt":"The rapid advancements in large language models (LLMs) have significantly improved their ability to generate natural language, making texts generated by LLMs increasingly indistinguishable from human-written texts. Recent research has predominantly focused on using LLMs to classify text as either human-written or machine-generated. In our study, we adopt a different approach by profiling texts spanning four domains based on 250 distinct linguistic features. We select the M4 dataset from the Subtask B of SemEval 2024 Task 8. We automatically calculate various linguistic features with the LFTK t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.03025","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/2412.03025/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":"2412.03025","created_at":"2026-07-05T09:44:23.894539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.03025v1","created_at":"2026-07-05T09:44:23.894539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.03025","created_at":"2026-07-05T09:44:23.894539+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3XJIKG3GSJS","created_at":"2026-07-05T09:44:23.894539+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3XJIKG3GSJS2VPR","created_at":"2026-07-05T09:44:23.894539+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3XJIKG3","created_at":"2026-07-05T09:44:23.894539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04924","citing_title":"Can Crowdsourcing Survive the LLM Era? A Community Survey on Human Data Collection","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23651","citing_title":"How Human-Like Are Large Language Models? A Register-Aware Linguistic Evaluation Framework","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20602","citing_title":"Self-Training Doesn't Flatten Language -- It Restructures It: Surface Markers Amplify While Deep Syntax Dies","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19936","citing_title":"What Are LLMs Doing to Scientific Communication? Measuring Changes in Writing Practices and Reading Experience","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23676","citing_title":"Directional Alignment and Narrative Agency in Human-LLM Co-Writing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14111","citing_title":"Interpretable Stylistic Variation in Human and LLM Writing Across Genres, Models, and Decoding Strategies","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C","json":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C.json","graph_json":"https://pith.science/api/pith-number/P3XJIKG3GSJS2VPRIQKEBVLG4C/graph.json","events_json":"https://pith.science/api/pith-number/P3XJIKG3GSJS2VPRIQKEBVLG4C/events.json","paper":"https://pith.science/paper/P3XJIKG3"},"agent_actions":{"view_html":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C","download_json":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C.json","view_paper":"https://pith.science/paper/P3XJIKG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.03025&json=true","fetch_graph":"https://pith.science/api/pith-number/P3XJIKG3GSJS2VPRIQKEBVLG4C/graph.json","fetch_events":"https://pith.science/api/pith-number/P3XJIKG3GSJS2VPRIQKEBVLG4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C/action/storage_attestation","attest_author":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C/action/author_attestation","sign_citation":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C/action/citation_signature","submit_replication":"https://pith.science/pith/P3XJIKG3GSJS2VPRIQKEBVLG4C/action/replication_record"}},"created_at":"2026-07-05T09:44:23.894539+00:00","updated_at":"2026-07-05T09:44:23.894539+00:00"}