{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XJSA6LVJFOLNXFKYVHM4PFIDI2","short_pith_number":"pith:XJSA6LVJ","schema_version":"1.0","canonical_sha256":"ba640f2ea92b96db9558a9d9c7950346b52b6ce2c47be7636bbc1adcbfd35ffb","source":{"kind":"arxiv","id":"2605.25358","version":1},"attestation_state":"computed","paper":{"title":"AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Thomas Stephan Juzek","submitted_at":"2026-05-25T02:24:46Z","abstract_excerpt":"AI-associated lexical shifts have been documented mainly in Scientific English. We extend this work to 34 languages in the WMT News Crawl corpus, refining a split-halves continuation diagnostic that compares GPT-4.1 continuations with matched human gold-standard text. For each language, we derive ranked AI-overused lemmas using log prevalence ratios. We find substantial cross-lingual semantic convergence: semantically related concepts recur across typologically diverse languages, with 'emphasize'-type verbs appearing in 24 of 34 languages. Embedding-based and manual analyses support this patte"},"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":"2605.25358","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T02:24:46Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"19665ed19f47107c181a29bf4537347c8fd25e6b0163af523fac6123df6f70ed","abstract_canon_sha256":"30c3cd48196012a0bfad179a07d1ce5d4a3590954e0580f784f4cdacdfe74d9f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:30.788169Z","signature_b64":"MkSRL05MK8m6tlS9InTwyEVqzKbO9G/BMlLA/8iw+s+NQtHbo4l99nm/RAU2oxNbm4AJWppP3/TTUawh/YJ5BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ba640f2ea92b96db9558a9d9c7950346b52b6ce2c47be7636bbc1adcbfd35ffb","last_reissued_at":"2026-05-26T02:04:30.787673Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:30.787673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AI-Associated Lexical Shifts Across 34 Languages: Cross-Lingual Convergence and Diachronic Uptake in News Writing","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Thomas Stephan Juzek","submitted_at":"2026-05-25T02:24:46Z","abstract_excerpt":"AI-associated lexical shifts have been documented mainly in Scientific English. We extend this work to 34 languages in the WMT News Crawl corpus, refining a split-halves continuation diagnostic that compares GPT-4.1 continuations with matched human gold-standard text. For each language, we derive ranked AI-overused lemmas using log prevalence ratios. We find substantial cross-lingual semantic convergence: semantically related concepts recur across typologically diverse languages, with 'emphasize'-type verbs appearing in 24 of 34 languages. Embedding-based and manual analyses support this patte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25358","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/2605.25358/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":"2605.25358","created_at":"2026-05-26T02:04:30.787746+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25358v1","created_at":"2026-05-26T02:04:30.787746+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25358","created_at":"2026-05-26T02:04:30.787746+00:00"},{"alias_kind":"pith_short_12","alias_value":"XJSA6LVJFOLN","created_at":"2026-05-26T02:04:30.787746+00:00"},{"alias_kind":"pith_short_16","alias_value":"XJSA6LVJFOLNXFKY","created_at":"2026-05-26T02:04:30.787746+00:00"},{"alias_kind":"pith_short_8","alias_value":"XJSA6LVJ","created_at":"2026-05-26T02:04:30.787746+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2","json":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2.json","graph_json":"https://pith.science/api/pith-number/XJSA6LVJFOLNXFKYVHM4PFIDI2/graph.json","events_json":"https://pith.science/api/pith-number/XJSA6LVJFOLNXFKYVHM4PFIDI2/events.json","paper":"https://pith.science/paper/XJSA6LVJ"},"agent_actions":{"view_html":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2","download_json":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2.json","view_paper":"https://pith.science/paper/XJSA6LVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25358&json=true","fetch_graph":"https://pith.science/api/pith-number/XJSA6LVJFOLNXFKYVHM4PFIDI2/graph.json","fetch_events":"https://pith.science/api/pith-number/XJSA6LVJFOLNXFKYVHM4PFIDI2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2/action/storage_attestation","attest_author":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2/action/author_attestation","sign_citation":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2/action/citation_signature","submit_replication":"https://pith.science/pith/XJSA6LVJFOLNXFKYVHM4PFIDI2/action/replication_record"}},"created_at":"2026-05-26T02:04:30.787746+00:00","updated_at":"2026-05-26T02:04:30.787746+00:00"}