{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KPTUWT5PVEXSJPU4HX7TPJUE7A","short_pith_number":"pith:KPTUWT5P","schema_version":"1.0","canonical_sha256":"53e74b4fafa92f24be9c3dff37a684f81482fb73c1de33a3815e0ad503399afe","source":{"kind":"arxiv","id":"2605.07855","version":2},"attestation_state":"computed","paper":{"title":"Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks.","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Edward L. Ionides, Jin Wook Lee, William Szegda, Zhisheng Song","submitted_at":"2026-05-08T15:17:29Z","abstract_excerpt":"Despite their growing use in academic writing and statistical analysis, the performance of artificial intelligence (AI) tools in scientific peer review remains a largely unexplored area. A key challenge is jagged AI, a phenomenon where AI exhibits strong ability spikes in some domains while remaining deficient in others. To study this jaggedness in a practical data science context, we considered the task of reviewing partially observed Markov process (POMP) data analyses. POMP models, also known as state-space models or hidden Markov models, are used to fit mechanistic dynamic models to time s"},"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":"2605.07855","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-08T15:17:29Z","cross_cats_sorted":[],"title_canon_sha256":"e3292a929adb128f339ad421fbb49ee86a7651eca0c1f608784c14a871aa9dc3","abstract_canon_sha256":"7274d62c7fd667135b959d4e7bfe91cfddc244e803c740f6bd4979525232139a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:46.622852Z","signature_b64":"JhkjzkGCnvRLTg5t/BRWlIjzMdwoyC6hLEFBj8XS8aCp+R3DOoKHoE3jsk/EcyuND3iKlCBpMK3D4xGOznoBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53e74b4fafa92f24be9c3dff37a684f81482fb73c1de33a3815e0ad503399afe","last_reissued_at":"2026-05-20T00:05:46.622215Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:46.622215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks.","cross_cats":[],"primary_cat":"stat.AP","authors_text":"Edward L. Ionides, Jin Wook Lee, William Szegda, Zhisheng Song","submitted_at":"2026-05-08T15:17:29Z","abstract_excerpt":"Despite their growing use in academic writing and statistical analysis, the performance of artificial intelligence (AI) tools in scientific peer review remains a largely unexplored area. A key challenge is jagged AI, a phenomenon where AI exhibits strong ability spikes in some domains while remaining deficient in others. To study this jaggedness in a practical data science context, we considered the task of reviewing partially observed Markov process (POMP) data analyses. POMP models, also known as state-space models or hidden Markov models, are used to fit mechanistic dynamic models to time s"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AI reviewers exhibited a jagged capability profile, proficiently catching human-overlooked technical errors and invalid inference methodology, while failing to match human standards in checking interpretive errors, narrative coherence, and domain-informed model critique. The jaggedness was found to be similar for all agents, consistent with it being primarily a property of the underlying AI model rather than the specific instructions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 72 anonymized student POMP projects and their human peer reviews form a representative and unbiased testbed for general AI performance in scientific peer review of mechanistic dynamic models.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AI reviewers of POMP data analyses detect technical and methodological errors effectively but underperform humans on interpretive, narrative, and domain-informed critique, showing consistent jaggedness.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"1addfa079faabeba7a4fffca6686e72f1102f03704b0007eb694b27f360aa986"},"source":{"id":"2605.07855","kind":"arxiv","version":2},"verdict":{"id":"93f579c8-28e5-4938-95e7-cdb7b13c8ad8","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-11T02:08:11.885846Z","strongest_claim":"AI reviewers exhibited a jagged capability profile, proficiently catching human-overlooked technical errors and invalid inference methodology, while failing to match human standards in checking interpretive errors, narrative coherence, and domain-informed model critique. The jaggedness was found to be similar for all agents, consistent with it being primarily a property of the underlying AI model rather than the specific instructions.","one_line_summary":"AI reviewers of POMP data analyses detect technical and methodological errors effectively but underperform humans on interpretive, narrative, and domain-informed critique, showing consistent jaggedness.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 72 anonymized student POMP projects and their human peer reviews form a representative and unbiased testbed for general AI performance in scientific peer review of mechanistic dynamic models.","pith_extraction_headline":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.07855/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T15:31:18.602322Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T11:28:32.297449Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"d35f8b8a3de6c0dfffdff882e474240b41c0c319f50e0d1523662ae48d00dd93"},"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":"2605.07855","created_at":"2026-05-20T00:05:46.622309+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.07855v2","created_at":"2026-05-20T00:05:46.622309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07855","created_at":"2026-05-20T00:05:46.622309+00:00"},{"alias_kind":"pith_short_12","alias_value":"KPTUWT5PVEXS","created_at":"2026-05-20T00:05:46.622309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KPTUWT5PVEXSJPU4","created_at":"2026-05-20T00:05:46.622309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KPTUWT5P","created_at":"2026-05-20T00:05:46.622309+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/KPTUWT5PVEXSJPU4HX7TPJUE7A","json":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A.json","graph_json":"https://pith.science/api/pith-number/KPTUWT5PVEXSJPU4HX7TPJUE7A/graph.json","events_json":"https://pith.science/api/pith-number/KPTUWT5PVEXSJPU4HX7TPJUE7A/events.json","paper":"https://pith.science/paper/KPTUWT5P"},"agent_actions":{"view_html":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A","download_json":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A.json","view_paper":"https://pith.science/paper/KPTUWT5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.07855&json=true","fetch_graph":"https://pith.science/api/pith-number/KPTUWT5PVEXSJPU4HX7TPJUE7A/graph.json","fetch_events":"https://pith.science/api/pith-number/KPTUWT5PVEXSJPU4HX7TPJUE7A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/action/storage_attestation","attest_author":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/action/author_attestation","sign_citation":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/action/citation_signature","submit_replication":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/action/replication_record"}},"created_at":"2026-05-20T00:05:46.622309+00:00","updated_at":"2026-05-20T00:05:46.622309+00:00"}