{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XOFGWRT62X4G4GEIO34W5YYNZT","short_pith_number":"pith:XOFGWRT6","schema_version":"1.0","canonical_sha256":"bb8a6b467ed5f86e188876f96ee30dccc89689d8ca29ef3f2f6ab58e80166489","source":{"kind":"arxiv","id":"2308.09067","version":3},"attestation_state":"computed","paper":{"title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Mu\\~noz-Ortiz, Carlos G\\'omez-Rodr\\'iguez, David Vilares","submitted_at":"2023-08-17T15:54:38Z","abstract_excerpt":"We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric, and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Human texts exhibit more scattered sentence length distributions, more variety of vocabulary, a distinct use of dependency and constituent types, shorter cons"},"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":"2308.09067","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-17T15:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"a535ff9c52c2e63c633689d7fd3c586379d1ae544cd11c74ec23d8a80a2efdbd","abstract_canon_sha256":"ad7ac409e6c8760a47decf16112917622f4da9a2383417e8584752edecbda97f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:25.370999Z","signature_b64":"25Nise5iNILgqVc8ubf9jLojLSbRkXBJEuUX0KcWfKzvkjrOra/qi9HH84qx0a+OYSdZ57IizbayRANQ4UYTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb8a6b467ed5f86e188876f96ee30dccc89689d8ca29ef3f2f6ab58e80166489","last_reissued_at":"2026-07-05T09:01:25.370552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:25.370552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Contrasting Linguistic Patterns in Human and LLM-Generated News Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Mu\\~noz-Ortiz, Carlos G\\'omez-Rodr\\'iguez, David Vilares","submitted_at":"2023-08-17T15:54:38Z","abstract_excerpt":"We conduct a quantitative analysis contrasting human-written English news text with comparable large language model (LLM) output from six different LLMs that cover three different families and four sizes in total. Our analysis spans several measurable linguistic dimensions, including morphological, syntactic, psychometric, and sociolinguistic aspects. The results reveal various measurable differences between human and AI-generated texts. Human texts exhibit more scattered sentence length distributions, more variety of vocabulary, a distinct use of dependency and constituent types, shorter cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.09067","kind":"arxiv","version":3},"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/2308.09067/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":"2308.09067","created_at":"2026-07-05T09:01:25.370621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.09067v3","created_at":"2026-07-05T09:01:25.370621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.09067","created_at":"2026-07-05T09:01:25.370621+00:00"},{"alias_kind":"pith_short_12","alias_value":"XOFGWRT62X4G","created_at":"2026-07-05T09:01:25.370621+00:00"},{"alias_kind":"pith_short_16","alias_value":"XOFGWRT62X4G4GEI","created_at":"2026-07-05T09:01:25.370621+00:00"},{"alias_kind":"pith_short_8","alias_value":"XOFGWRT6","created_at":"2026-07-05T09:01:25.370621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.05385","citing_title":"EduCoder: An Open-Source Annotation System for Education Transcript Data","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18153","citing_title":"Leveraging AI for Direct Bystander Intervention Against Cyberbullying","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT","json":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT.json","graph_json":"https://pith.science/api/pith-number/XOFGWRT62X4G4GEIO34W5YYNZT/graph.json","events_json":"https://pith.science/api/pith-number/XOFGWRT62X4G4GEIO34W5YYNZT/events.json","paper":"https://pith.science/paper/XOFGWRT6"},"agent_actions":{"view_html":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT","download_json":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT.json","view_paper":"https://pith.science/paper/XOFGWRT6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.09067&json=true","fetch_graph":"https://pith.science/api/pith-number/XOFGWRT62X4G4GEIO34W5YYNZT/graph.json","fetch_events":"https://pith.science/api/pith-number/XOFGWRT62X4G4GEIO34W5YYNZT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT/action/storage_attestation","attest_author":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT/action/author_attestation","sign_citation":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT/action/citation_signature","submit_replication":"https://pith.science/pith/XOFGWRT62X4G4GEIO34W5YYNZT/action/replication_record"}},"created_at":"2026-07-05T09:01:25.370621+00:00","updated_at":"2026-07-05T09:01:25.370621+00:00"}