{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JZKWUJSSAMMZTVNFNCAMEPDJBW","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":"a318282550144abeef4b9ae2db40b387bab634de312cd6f423c42abfe23a4469","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:57:37Z","title_canon_sha256":"a8071c47ef5ec31c87e73e7671d2f29264ddff1b49c60322dadddd2f4aa30a5a"},"schema_version":"1.0","source":{"id":"2605.30329","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30329","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30329v1","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30329","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_12","alias_value":"JZKWUJSSAMMZ","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_16","alias_value":"JZKWUJSSAMMZTVNF","created_at":"2026-05-29T02:06:16Z"},{"alias_kind":"pith_short_8","alias_value":"JZKWUJSS","created_at":"2026-05-29T02:06:16Z"}],"graph_snapshots":[{"event_id":"sha256:8d308542480fa523c3bb04ed2cada525b88e634b47e037ecd16424a9a486f74b","target":"graph","created_at":"2026-05-29T02:06:16Z","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/2605.30329/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Autonomous AI research agents aim to accelerate scientific discovery by automating the research pipeline, from hypothesis generation to peer review. However, existing benchmarks rarely test a fundamental bottleneck: whether Large Language Models can judge the methodological viability of a research idea before expending time and computational resources. We introduce SoundnessBench, a curated benchmark of 1,099 machine-learning research proposals reconstructed from ICLR submissions, labeled with reviewer soundness sub-scores, and audited against source papers. SoundnessBench should be interprete","authors_text":"Furong Huang, Huy Nghiem, Minghui Liu, Sy-Tuyen Ho","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:57:37Z","title":"SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30329","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:b21a27e0779eccfcf41fa187ac668ef681ea1555e5ea8670ac25759b7850f40d","target":"record","created_at":"2026-05-29T02:06:16Z","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":"a318282550144abeef4b9ae2db40b387bab634de312cd6f423c42abfe23a4469","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:57:37Z","title_canon_sha256":"a8071c47ef5ec31c87e73e7671d2f29264ddff1b49c60322dadddd2f4aa30a5a"},"schema_version":"1.0","source":{"id":"2605.30329","kind":"arxiv","version":1}},"canonical_sha256":"4e556a2652031999d5a56880c23c690d8e1114c507fc3b53b228e3cd472abd00","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4e556a2652031999d5a56880c23c690d8e1114c507fc3b53b228e3cd472abd00","first_computed_at":"2026-05-29T02:06:16.706967Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:16.706967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0HxZJ7JtgemB4S6xkO5Z7tWbU7mKxCt/05WsD25d9j+2nkEgVM+3N1ebz1Jny4nmBO9koTsdO7LmsB0WJ6lTAw==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:16.707362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30329","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b21a27e0779eccfcf41fa187ac668ef681ea1555e5ea8670ac25759b7850f40d","sha256:8d308542480fa523c3bb04ed2cada525b88e634b47e037ecd16424a9a486f74b"],"state_sha256":"30fcfe1a1543a034689cefed157fd9d8362131b0728012390447ffdbec58fa36"}