{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JVRCF4SJPGI422JRIPGZALZS64","short_pith_number":"pith:JVRCF4SJ","schema_version":"1.0","canonical_sha256":"4d6222f2497991cd693143cd902f32f716cc5de3db69fa7f30fc6272eb4307bf","source":{"kind":"arxiv","id":"2312.01672","version":1},"attestation_state":"computed","paper":{"title":"STADEE: STAtistics-based DEEp Detection of Machine Generated Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huming Liu, Zheng Chen","submitted_at":"2023-12-04T06:45:47Z","abstract_excerpt":"We present STADEE, a \\textbf{STA}tistics-based \\textbf{DEE}p detection method to identify machine-generated text, addressing the limitations of current methods that rely heavily on fine-tuning pre-trained language models (PLMs). STADEE integrates key statistical text features with a deep classifier, focusing on aspects like token probability and cumulative probability, crucial for handling nucleus sampling. Tested across diverse datasets and scenarios (in-domain, out-of-domain, and in-the-wild), STADEE demonstrates superior performance, achieving an 87.05% F1 score in-domain and outperforming "},"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":"2312.01672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-04T06:45:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f29a76b5731f7354811d19fc78d20b1f9fcfaac2c23255ad503a9d1169a5dd6f","abstract_canon_sha256":"f2c65a7142f0846ecdf2fb2bb8720481fc23a860fc080e635fb0020e54021a28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:58.020593Z","signature_b64":"DIU/N6EiE2tbsRg22oB3/84VbQDuH84rXoza/0RSn01gEaPtVmP3T319Now4XZmfBEmjaLlrAHi+YL6T3N6hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d6222f2497991cd693143cd902f32f716cc5de3db69fa7f30fc6272eb4307bf","last_reissued_at":"2026-07-05T07:19:58.020201Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:58.020201Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STADEE: STAtistics-based DEEp Detection of Machine Generated Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huming Liu, Zheng Chen","submitted_at":"2023-12-04T06:45:47Z","abstract_excerpt":"We present STADEE, a \\textbf{STA}tistics-based \\textbf{DEE}p detection method to identify machine-generated text, addressing the limitations of current methods that rely heavily on fine-tuning pre-trained language models (PLMs). STADEE integrates key statistical text features with a deep classifier, focusing on aspects like token probability and cumulative probability, crucial for handling nucleus sampling. Tested across diverse datasets and scenarios (in-domain, out-of-domain, and in-the-wild), STADEE demonstrates superior performance, achieving an 87.05% F1 score in-domain and outperforming "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.01672","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/2312.01672/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":"2312.01672","created_at":"2026-07-05T07:19:58.020254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.01672v1","created_at":"2026-07-05T07:19:58.020254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.01672","created_at":"2026-07-05T07:19:58.020254+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVRCF4SJPGI4","created_at":"2026-07-05T07:19:58.020254+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVRCF4SJPGI422JR","created_at":"2026-07-05T07:19:58.020254+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVRCF4SJ","created_at":"2026-07-05T07:19:58.020254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.18621","citing_title":"The Anatomy of Speech Persuasion: Linguistic Shifts in LLM-Modified Speeches","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64","json":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64.json","graph_json":"https://pith.science/api/pith-number/JVRCF4SJPGI422JRIPGZALZS64/graph.json","events_json":"https://pith.science/api/pith-number/JVRCF4SJPGI422JRIPGZALZS64/events.json","paper":"https://pith.science/paper/JVRCF4SJ"},"agent_actions":{"view_html":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64","download_json":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64.json","view_paper":"https://pith.science/paper/JVRCF4SJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.01672&json=true","fetch_graph":"https://pith.science/api/pith-number/JVRCF4SJPGI422JRIPGZALZS64/graph.json","fetch_events":"https://pith.science/api/pith-number/JVRCF4SJPGI422JRIPGZALZS64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64/action/storage_attestation","attest_author":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64/action/author_attestation","sign_citation":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64/action/citation_signature","submit_replication":"https://pith.science/pith/JVRCF4SJPGI422JRIPGZALZS64/action/replication_record"}},"created_at":"2026-07-05T07:19:58.020254+00:00","updated_at":"2026-07-05T07:19:58.020254+00:00"}