{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5QCMAQ4227W2OVHZUJ7K337LBG","short_pith_number":"pith:5QCMAQ42","schema_version":"1.0","canonical_sha256":"ec04c0439ad7eda754f9a27eadefeb09a838a83549a16a4c9ce8fe5f8f4cfe2b","source":{"kind":"arxiv","id":"2606.04177","version":1},"attestation_state":"computed","paper":{"title":"A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Agnieszka Falenska, Esra D\\\"onmez, Maximilian Maurer, Yassir El Attar","submitted_at":"2026-06-02T19:46:22Z","abstract_excerpt":"Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users. However, existing findings on which features reliably indicate LLM-generated text remain fragmented across feature sets, models, and text domains. To address this gap, we conduct a large-scale empirical study assessing the robustness of linguistic signals for characterizing AI-generated text. Our analysis covers 284 interpretable linguistic features across outputs from 27 LLMs and ten text domains under cross-model and cross-domain generaliz"},"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":"2606.04177","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-02T19:46:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d7e88a77dc3c9b3182a96a1ff03f48ac46e243e6401caf077fdddfb2882c073","abstract_canon_sha256":"45059084c82a2c077d022d175d7473b951c097bf202672556ee3a4f0041185e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:19.115748Z","signature_b64":"D/FtYhcpYEAfxUPLPSru6D+IBr5H67JX+BjM7WiyFW8+1PE2tKhkIzWsdAVby0FOixTRQi8zzBhu5ooFDTSHCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec04c0439ad7eda754f9a27eadefeb09a838a83549a16a4c9ce8fe5f8f4cfe2b","last_reissued_at":"2026-06-04T01:08:19.114888Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:19.114888Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Systematic Analysis of Linguistic Features in AI-Generated Text Detection Across Domains and Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Agnieszka Falenska, Esra D\\\"onmez, Maximilian Maurer, Yassir El Attar","submitted_at":"2026-06-02T19:46:22Z","abstract_excerpt":"Interpretable linguistic features offer a promising approach for explaining why a given text appears machine-generated, particularly for non-expert users. However, existing findings on which features reliably indicate LLM-generated text remain fragmented across feature sets, models, and text domains. To address this gap, we conduct a large-scale empirical study assessing the robustness of linguistic signals for characterizing AI-generated text. Our analysis covers 284 interpretable linguistic features across outputs from 27 LLMs and ten text domains under cross-model and cross-domain generaliz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04177","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/2606.04177/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":"2606.04177","created_at":"2026-06-04T01:08:19.114994+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.04177v1","created_at":"2026-06-04T01:08:19.114994+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04177","created_at":"2026-06-04T01:08:19.114994+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QCMAQ4227W2","created_at":"2026-06-04T01:08:19.114994+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QCMAQ4227W2OVHZ","created_at":"2026-06-04T01:08:19.114994+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QCMAQ42","created_at":"2026-06-04T01:08:19.114994+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/5QCMAQ4227W2OVHZUJ7K337LBG","json":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG.json","graph_json":"https://pith.science/api/pith-number/5QCMAQ4227W2OVHZUJ7K337LBG/graph.json","events_json":"https://pith.science/api/pith-number/5QCMAQ4227W2OVHZUJ7K337LBG/events.json","paper":"https://pith.science/paper/5QCMAQ42"},"agent_actions":{"view_html":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG","download_json":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG.json","view_paper":"https://pith.science/paper/5QCMAQ42","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.04177&json=true","fetch_graph":"https://pith.science/api/pith-number/5QCMAQ4227W2OVHZUJ7K337LBG/graph.json","fetch_events":"https://pith.science/api/pith-number/5QCMAQ4227W2OVHZUJ7K337LBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG/action/storage_attestation","attest_author":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG/action/author_attestation","sign_citation":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG/action/citation_signature","submit_replication":"https://pith.science/pith/5QCMAQ4227W2OVHZUJ7K337LBG/action/replication_record"}},"created_at":"2026-06-04T01:08:19.114994+00:00","updated_at":"2026-06-04T01:08:19.114994+00:00"}