{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KPTUWT5PVEXSJPU4HX7TPJUE7A","short_pith_number":"pith:KPTUWT5P","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"},"canonical_sha256":"53e74b4fafa92f24be9c3dff37a684f81482fb73c1de33a3815e0ad503399afe","source":{"kind":"arxiv","id":"2605.07855","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07855","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07855v2","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07855","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"KPTUWT5PVEXS","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"KPTUWT5PVEXSJPU4","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"KPTUWT5P","created_at":"2026-05-20T00:05:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KPTUWT5PVEXSJPU4HX7TPJUE7A","target":"record","payload":{"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"},"canonical_sha256":"53e74b4fafa92f24be9c3dff37a684f81482fb73c1de33a3815e0ad503399afe","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"},"source_kind":"arxiv","source_id":"2605.07855","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZNEyhZcIv5rtiAKzEGbIWlD1qFNOPdPTOr4cQcLtKWP43ahwWdLLuVadDcm2nQDvcr/CTNFIX29tKFns7naACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:09:50.850552Z"},"content_sha256":"7486dcc243ef14d1698e920985f36e42b654ccb664f9e31b7b6496b229ed96e1","schema_version":"1.0","event_id":"sha256:7486dcc243ef14d1698e920985f36e42b654ccb664f9e31b7b6496b229ed96e1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KPTUWT5PVEXSJPU4HX7TPJUE7A","target":"graph","payload":{"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"},"verdict_id":"93f579c8-28e5-4938-95e7-cdb7b13c8ad8"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:05:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L1QgscE8Ib0L13DOcd6obTVeYqHoev24dfm7HYLQgYCPG5grlAzIxc9CEt86aGUrSU3GYUR3bzM5ud6YzW0ZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:09:50.851055Z"},"content_sha256":"21358fa0cdfdc941eca1cee735049245c7b2e12782b8b8dd9c7012e7395f9d0c","schema_version":"1.0","event_id":"sha256:21358fa0cdfdc941eca1cee735049245c7b2e12782b8b8dd9c7012e7395f9d0c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/bundle.json","state_url":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-03T00:09:50Z","links":{"resolver":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A","bundle":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/bundle.json","state":"https://pith.science/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPTUWT5PVEXSJPU4HX7TPJUE7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KPTUWT5PVEXSJPU4HX7TPJUE7A","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7274d62c7fd667135b959d4e7bfe91cfddc244e803c740f6bd4979525232139a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-08T15:17:29Z","title_canon_sha256":"e3292a929adb128f339ad421fbb49ee86a7651eca0c1f608784c14a871aa9dc3"},"schema_version":"1.0","source":{"id":"2605.07855","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.07855","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"arxiv_version","alias_value":"2605.07855v2","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.07855","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_12","alias_value":"KPTUWT5PVEXS","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_16","alias_value":"KPTUWT5PVEXSJPU4","created_at":"2026-05-20T00:05:46Z"},{"alias_kind":"pith_short_8","alias_value":"KPTUWT5P","created_at":"2026-05-20T00:05:46Z"}],"graph_snapshots":[{"event_id":"sha256:21358fa0cdfdc941eca1cee735049245c7b2e12782b8b8dd9c7012e7395f9d0c","target":"graph","created_at":"2026-05-20T00:05:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks."}],"snapshot_sha256":"1addfa079faabeba7a4fffca6686e72f1102f03704b0007eb694b27f360aa986"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.07855/integrity.json","findings":[],"snapshot_sha256":"d35f8b8a3de6c0dfffdff882e474240b41c0c319f50e0d1523662ae48d00dd93","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Edward L. Ionides, Jin Wook Lee, William Szegda, Zhisheng Song","cross_cats":[],"headline":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-08T15:17:29Z","title":"Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.07855","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-11T02:08:11.885846Z","id":"93f579c8-28e5-4938-95e7-cdb7b13c8ad8","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"AI reviewers catch technical errors in POMP analyses that humans miss but fall short on interpretive and narrative checks.","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.","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."}},"verdict_id":"93f579c8-28e5-4938-95e7-cdb7b13c8ad8"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7486dcc243ef14d1698e920985f36e42b654ccb664f9e31b7b6496b229ed96e1","target":"record","created_at":"2026-05-20T00:05:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7274d62c7fd667135b959d4e7bfe91cfddc244e803c740f6bd4979525232139a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.AP","submitted_at":"2026-05-08T15:17:29Z","title_canon_sha256":"e3292a929adb128f339ad421fbb49ee86a7651eca0c1f608784c14a871aa9dc3"},"schema_version":"1.0","source":{"id":"2605.07855","kind":"arxiv","version":2}},"canonical_sha256":"53e74b4fafa92f24be9c3dff37a684f81482fb73c1de33a3815e0ad503399afe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53e74b4fafa92f24be9c3dff37a684f81482fb73c1de33a3815e0ad503399afe","first_computed_at":"2026-05-20T00:05:46.622215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:05:46.622215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JhkjzkGCnvRLTg5t/BRWlIjzMdwoyC6hLEFBj8XS8aCp+R3DOoKHoE3jsk/EcyuND3iKlCBpMK3D4xGOznoBBA==","signature_status":"signed_v1","signed_at":"2026-05-20T00:05:46.622852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.07855","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7486dcc243ef14d1698e920985f36e42b654ccb664f9e31b7b6496b229ed96e1","sha256:21358fa0cdfdc941eca1cee735049245c7b2e12782b8b8dd9c7012e7395f9d0c"],"state_sha256":"4a47037632c830f25631780ba88da322540c1c36ebdab27308d130c6c5eae054"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7n28Mp4snVcmFrI//UH8vGybnyDHR4XI2X6z2yK+e1xIYzW93joeYCADL6tmUNfKT76hQNOgcvr1OFKKTfjJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:09:50.853473Z","bundle_sha256":"32f07842581f2bb966024e1d454365dda42431625be1dab5a955c0b589710944"}}