{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:G2M57VXICQSOEJQAP4HIYNNHZI","short_pith_number":"pith:G2M57VXI","schema_version":"1.0","canonical_sha256":"3699dfd6e81424e226007f0e8c35a7ca37ef377d7638ee2b26864ae767a07be9","source":{"kind":"arxiv","id":"2605.26911","version":1},"attestation_state":"computed","paper":{"title":"TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanqi Duan, Xiang Li","submitted_at":"2026-05-26T12:07:44Z","abstract_excerpt":"LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Existing work either classifies authorship without judging quality, or scores quality with features designed for human-written reviews; no prior system detects deficiencies in LLM-generated reviews at the level of individual defect types. To bridge the gap, we introduce TADDLE, a Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews, together with the first expert-annotated benchmark for this task. Our benchmark c"},"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":"2605.26911","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-26T12:07:44Z","cross_cats_sorted":[],"title_canon_sha256":"4436056580d6411032fef0a185aebd261afcb55c2300782117b89c560293e86c","abstract_canon_sha256":"307242be9192a56eae4538d146983e09fc89c6e97a304d845f96616fca324384"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:19.359242Z","signature_b64":"1sMCxD85U7NU+RZwWYPoTlQAAnMxCXvl27jdY0Nsm9kSk3qmhwIlxfMnbP1e2mUtlc3OV6daGCAVSp7gHcn9Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3699dfd6e81424e226007f0e8c35a7ca37ef377d7638ee2b26864ae767a07be9","last_reissued_at":"2026-05-27T01:06:19.358301Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:19.358301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TADDLE: A Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hanqi Duan, Xiang Li","submitted_at":"2026-05-26T12:07:44Z","abstract_excerpt":"LLM-generated peer reviews are increasingly common at major venues, yet their deficiencies are hard to detect because they are uniformly fluent and well-structured. Existing work either classifies authorship without judging quality, or scores quality with features designed for human-written reviews; no prior system detects deficiencies in LLM-generated reviews at the level of individual defect types. To bridge the gap, we introduce TADDLE, a Tool-Augmented Agent for Detecting Deficient LLM-Generated Peer Reviews, together with the first expert-annotated benchmark for this task. Our benchmark c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26911","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/2605.26911/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":"2605.26911","created_at":"2026-05-27T01:06:19.358445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26911v1","created_at":"2026-05-27T01:06:19.358445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26911","created_at":"2026-05-27T01:06:19.358445+00:00"},{"alias_kind":"pith_short_12","alias_value":"G2M57VXICQSO","created_at":"2026-05-27T01:06:19.358445+00:00"},{"alias_kind":"pith_short_16","alias_value":"G2M57VXICQSOEJQA","created_at":"2026-05-27T01:06:19.358445+00:00"},{"alias_kind":"pith_short_8","alias_value":"G2M57VXI","created_at":"2026-05-27T01:06:19.358445+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/G2M57VXICQSOEJQAP4HIYNNHZI","json":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI.json","graph_json":"https://pith.science/api/pith-number/G2M57VXICQSOEJQAP4HIYNNHZI/graph.json","events_json":"https://pith.science/api/pith-number/G2M57VXICQSOEJQAP4HIYNNHZI/events.json","paper":"https://pith.science/paper/G2M57VXI"},"agent_actions":{"view_html":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI","download_json":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI.json","view_paper":"https://pith.science/paper/G2M57VXI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26911&json=true","fetch_graph":"https://pith.science/api/pith-number/G2M57VXICQSOEJQAP4HIYNNHZI/graph.json","fetch_events":"https://pith.science/api/pith-number/G2M57VXICQSOEJQAP4HIYNNHZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI/action/storage_attestation","attest_author":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI/action/author_attestation","sign_citation":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI/action/citation_signature","submit_replication":"https://pith.science/pith/G2M57VXICQSOEJQAP4HIYNNHZI/action/replication_record"}},"created_at":"2026-05-27T01:06:19.358445+00:00","updated_at":"2026-05-27T01:06:19.358445+00:00"}