{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LUFT4BSFZQA7VYV3GMMWINSHXX","short_pith_number":"pith:LUFT4BSF","schema_version":"1.0","canonical_sha256":"5d0b3e0645cc01fae2bb3319643647bde66e55cf8bd6394de382f3485b63effa","source":{"kind":"arxiv","id":"2607.28631","version":1},"attestation_state":"computed","paper":{"title":"Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Mayank Kejriwal, Vaibhava Lakshmi Ravideshik","submitted_at":"2026-04-18T21:20:13Z","abstract_excerpt":"AI Scientist systems capable of autonomous research have the potential to significantly accelerate scientific discovery. However, evaluating and comparing the quality of AI-generated papers remains an open challenge. We propose and implement a rigorous benchmarking protocol using an automated peer-review system that harnesses frontier large language models to assess scientific papers across four core dimensions: originality, scientific rigor, clarity, and significance. We evaluate four leading AI Scientist frameworks: \\textit{Sakana AI (v1 & v2)}, \\textit{CycleResearcher}, and \\textit{Data-to-"},"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":"2607.28631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T21:20:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"9beb33de02a505821d5085913cdb43de9af78b960aadada6171bd07c0b8db74d","abstract_canon_sha256":"6f688ccbbea377b351d50a0f44ceab4c47bedf8f76bf489e999faa2cdee1be52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T00:11:51.157258Z","signature_b64":"15B13dXctxpzK+ELieoy0wtzzVj80kZaI68S03oe4uUgW91wbuPYOLRdS7al9ucWJzHx4R6+mHLr4dzdSKVTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d0b3e0645cc01fae2bb3319643647bde66e55cf8bd6394de382f3485b63effa","last_reissued_at":"2026-08-03T00:11:51.154886Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T00:11:51.154886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Mayank Kejriwal, Vaibhava Lakshmi Ravideshik","submitted_at":"2026-04-18T21:20:13Z","abstract_excerpt":"AI Scientist systems capable of autonomous research have the potential to significantly accelerate scientific discovery. However, evaluating and comparing the quality of AI-generated papers remains an open challenge. We propose and implement a rigorous benchmarking protocol using an automated peer-review system that harnesses frontier large language models to assess scientific papers across four core dimensions: originality, scientific rigor, clarity, and significance. We evaluate four leading AI Scientist frameworks: \\textit{Sakana AI (v1 & v2)}, \\textit{CycleResearcher}, and \\textit{Data-to-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28631","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/2607.28631/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":"2607.28631","created_at":"2026-08-03T00:11:51.156455+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.28631v1","created_at":"2026-08-03T00:11:51.156455+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28631","created_at":"2026-08-03T00:11:51.156455+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUFT4BSFZQA7","created_at":"2026-08-03T00:11:51.156455+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUFT4BSFZQA7VYV3","created_at":"2026-08-03T00:11:51.156455+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUFT4BSF","created_at":"2026-08-03T00:11:51.156455+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/LUFT4BSFZQA7VYV3GMMWINSHXX","json":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX.json","graph_json":"https://pith.science/api/pith-number/LUFT4BSFZQA7VYV3GMMWINSHXX/graph.json","events_json":"https://pith.science/api/pith-number/LUFT4BSFZQA7VYV3GMMWINSHXX/events.json","paper":"https://pith.science/paper/LUFT4BSF"},"agent_actions":{"view_html":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX","download_json":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX.json","view_paper":"https://pith.science/paper/LUFT4BSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.28631&json=true","fetch_graph":"https://pith.science/api/pith-number/LUFT4BSFZQA7VYV3GMMWINSHXX/graph.json","fetch_events":"https://pith.science/api/pith-number/LUFT4BSFZQA7VYV3GMMWINSHXX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX/action/storage_attestation","attest_author":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX/action/author_attestation","sign_citation":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX/action/citation_signature","submit_replication":"https://pith.science/pith/LUFT4BSFZQA7VYV3GMMWINSHXX/action/replication_record"}},"created_at":"2026-08-03T00:11:51.156455+00:00","updated_at":"2026-08-03T00:11:51.156455+00:00"}