{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JZKWUJSSAMMZTVNFNCAMEPDJBW","short_pith_number":"pith:JZKWUJSS","schema_version":"1.0","canonical_sha256":"4e556a2652031999d5a56880c23c690d8e1114c507fc3b53b228e3cd472abd00","source":{"kind":"arxiv","id":"2605.30329","version":1},"attestation_state":"computed","paper":{"title":"SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, Huy Nghiem, Minghui Liu, Sy-Tuyen Ho","submitted_at":"2026-05-28T17:57:37Z","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"},"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":"2605.30329","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T17:57:37Z","cross_cats_sorted":[],"title_canon_sha256":"a8071c47ef5ec31c87e73e7671d2f29264ddff1b49c60322dadddd2f4aa30a5a","abstract_canon_sha256":"a318282550144abeef4b9ae2db40b387bab634de312cd6f423c42abfe23a4469"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:16.707362Z","signature_b64":"0HxZJ7JtgemB4S6xkO5Z7tWbU7mKxCt/05WsD25d9j+2nkEgVM+3N1ebz1Jny4nmBO9koTsdO7LmsB0WJ6lTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e556a2652031999d5a56880c23c690d8e1114c507fc3b53b228e3cd472abd00","last_reissued_at":"2026-05-29T02:06:16.706967Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:16.706967Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Furong Huang, Huy Nghiem, Minghui Liu, Sy-Tuyen Ho","submitted_at":"2026-05-28T17:57:37Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30329","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/2605.30329/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":"2605.30329","created_at":"2026-05-29T02:06:16.707027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30329v1","created_at":"2026-05-29T02:06:16.707027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30329","created_at":"2026-05-29T02:06:16.707027+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZKWUJSSAMMZ","created_at":"2026-05-29T02:06:16.707027+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZKWUJSSAMMZTVNF","created_at":"2026-05-29T02:06:16.707027+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZKWUJSS","created_at":"2026-05-29T02:06:16.707027+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/JZKWUJSSAMMZTVNFNCAMEPDJBW","json":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW.json","graph_json":"https://pith.science/api/pith-number/JZKWUJSSAMMZTVNFNCAMEPDJBW/graph.json","events_json":"https://pith.science/api/pith-number/JZKWUJSSAMMZTVNFNCAMEPDJBW/events.json","paper":"https://pith.science/paper/JZKWUJSS"},"agent_actions":{"view_html":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW","download_json":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW.json","view_paper":"https://pith.science/paper/JZKWUJSS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30329&json=true","fetch_graph":"https://pith.science/api/pith-number/JZKWUJSSAMMZTVNFNCAMEPDJBW/graph.json","fetch_events":"https://pith.science/api/pith-number/JZKWUJSSAMMZTVNFNCAMEPDJBW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW/action/storage_attestation","attest_author":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW/action/author_attestation","sign_citation":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW/action/citation_signature","submit_replication":"https://pith.science/pith/JZKWUJSSAMMZTVNFNCAMEPDJBW/action/replication_record"}},"created_at":"2026-05-29T02:06:16.707027+00:00","updated_at":"2026-05-29T02:06:16.707027+00:00"}