{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LUFT4BSFZQA7VYV3GMMWINSHXX","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":"6f688ccbbea377b351d50a0f44ceab4c47bedf8f76bf489e999faa2cdee1be52","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T21:20:13Z","title_canon_sha256":"9beb33de02a505821d5085913cdb43de9af78b960aadada6171bd07c0b8db74d"},"schema_version":"1.0","source":{"id":"2607.28631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.28631","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"arxiv_version","alias_value":"2607.28631v1","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.28631","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_12","alias_value":"LUFT4BSFZQA7","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_16","alias_value":"LUFT4BSFZQA7VYV3","created_at":"2026-08-03T00:11:51Z"},{"alias_kind":"pith_short_8","alias_value":"LUFT4BSF","created_at":"2026-08-03T00:11:51Z"}],"graph_snapshots":[{"event_id":"sha256:6d4f28db78c3976052133816cdfe3f5a04f32d90d48efed7afe5b80763a6347c","target":"graph","created_at":"2026-08-03T00:11:51Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.28631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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-","authors_text":"Mayank Kejriwal, Vaibhava Lakshmi Ravideshik","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T21:20:13Z","title":"Can AI Evaluate AI Scientists? A Benchmarking Study of Autonomous Research Generation Systems Using Automated Multi-Model Review"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.28631","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e27f711e62665abc8c67731aa8c483fd64e20380725fda1326469ead321f2488","target":"record","created_at":"2026-08-03T00:11:51Z","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":"6f688ccbbea377b351d50a0f44ceab4c47bedf8f76bf489e999faa2cdee1be52","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-18T21:20:13Z","title_canon_sha256":"9beb33de02a505821d5085913cdb43de9af78b960aadada6171bd07c0b8db74d"},"schema_version":"1.0","source":{"id":"2607.28631","kind":"arxiv","version":1}},"canonical_sha256":"5d0b3e0645cc01fae2bb3319643647bde66e55cf8bd6394de382f3485b63effa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d0b3e0645cc01fae2bb3319643647bde66e55cf8bd6394de382f3485b63effa","first_computed_at":"2026-08-03T00:11:51.154886Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-03T00:11:51.154886Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"15B13dXctxpzK+ELieoy0wtzzVj80kZaI68S03oe4uUgW91wbuPYOLRdS7al9ucWJzHx4R6+mHLr4dzdSKVTAA==","signature_status":"signed_v1","signed_at":"2026-08-03T00:11:51.157258Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.28631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e27f711e62665abc8c67731aa8c483fd64e20380725fda1326469ead321f2488","sha256:6d4f28db78c3976052133816cdfe3f5a04f32d90d48efed7afe5b80763a6347c"],"state_sha256":"48ef866732709158d39650b06eb3f68bdb5d84ad26a75b3a51355ab5a3d505f7"}