{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OC4PLRYDTL7ZSI7GTTWZDO5ESR","short_pith_number":"pith:OC4PLRYD","schema_version":"1.0","canonical_sha256":"70b8f5c7039aff9923e69ced91bba49461651755cb94d3c5becc34951a4c8d59","source":{"kind":"arxiv","id":"2606.31074","version":1},"attestation_state":"computed","paper":{"title":"Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangsheng Bao, Lihua Rong, Qiji Zhou, Xiao Yu, Yanbin Zhao, Yue Zhang","submitted_at":"2026-06-30T03:02:42Z","abstract_excerpt":"Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the "},"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":"2606.31074","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-30T03:02:42Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ed41faf4930e8a1cdfa572f2fe1e6d1f6ec41cb6164f87f74ab17953010b7045","abstract_canon_sha256":"d774ee381350a9039773b964ca2c88cbb34dcd5fd0e40410ff3422a18bd54b37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-01T01:17:28.348504Z","signature_b64":"Y3rqplErrw1zL0uI8zgiTa/ZbdDopbO3NeVseJcEpQwvqgwUasyqi1t6Mg24uU28DidPbxQOr/Ge59Gv5ox6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70b8f5c7039aff9923e69ced91bba49461651755cb94d3c5becc34951a4c8d59","last_reissued_at":"2026-07-01T01:17:28.348090Z","signature_status":"signed_v1","first_computed_at":"2026-07-01T01:17:28.348090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Triospect: A Three-Dimensional Framework for Robust Statistical AI-Generated Text Detection Against Diverse Attacks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Guangsheng Bao, Lihua Rong, Qiji Zhou, Xiao Yu, Yanbin Zhao, Yue Zhang","submitted_at":"2026-06-30T03:02:42Z","abstract_excerpt":"Existing AI-generated text detectors are vulnerable to attacks that manipulate textual characteristics. In this study, we propose a novel Triospect Detection Framework by using additional perspectives of content (core ideas) and expression (stylistic elements) within a given text. Experiments on two benchmarks involving 17 attacks, 12 domains, and 17 source models demonstrate that Triospect is robust against these attacks. It improves the strong baseline by a significant margin of 22.3% (AUROC) and 13% (TPR01) on the Humanize-16K after-attack subset, and by 9.1% (AUROC) and 22% (TPR01) on the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.31074","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/2606.31074/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":"2606.31074","created_at":"2026-07-01T01:17:28.348147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.31074v1","created_at":"2026-07-01T01:17:28.348147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.31074","created_at":"2026-07-01T01:17:28.348147+00:00"},{"alias_kind":"pith_short_12","alias_value":"OC4PLRYDTL7Z","created_at":"2026-07-01T01:17:28.348147+00:00"},{"alias_kind":"pith_short_16","alias_value":"OC4PLRYDTL7ZSI7G","created_at":"2026-07-01T01:17:28.348147+00:00"},{"alias_kind":"pith_short_8","alias_value":"OC4PLRYD","created_at":"2026-07-01T01:17:28.348147+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/OC4PLRYDTL7ZSI7GTTWZDO5ESR","json":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR.json","graph_json":"https://pith.science/api/pith-number/OC4PLRYDTL7ZSI7GTTWZDO5ESR/graph.json","events_json":"https://pith.science/api/pith-number/OC4PLRYDTL7ZSI7GTTWZDO5ESR/events.json","paper":"https://pith.science/paper/OC4PLRYD"},"agent_actions":{"view_html":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR","download_json":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR.json","view_paper":"https://pith.science/paper/OC4PLRYD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.31074&json=true","fetch_graph":"https://pith.science/api/pith-number/OC4PLRYDTL7ZSI7GTTWZDO5ESR/graph.json","fetch_events":"https://pith.science/api/pith-number/OC4PLRYDTL7ZSI7GTTWZDO5ESR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR/action/storage_attestation","attest_author":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR/action/author_attestation","sign_citation":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR/action/citation_signature","submit_replication":"https://pith.science/pith/OC4PLRYDTL7ZSI7GTTWZDO5ESR/action/replication_record"}},"created_at":"2026-07-01T01:17:28.348147+00:00","updated_at":"2026-07-01T01:17:28.348147+00:00"}