{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y6QLESE7CD7MIMIU53AYQP6N74","short_pith_number":"pith:Y6QLESE7","schema_version":"1.0","canonical_sha256":"c7a0b2489f10fec43114eec1883fcdff148b3a25faf41f5a66fe67b37218ace7","source":{"kind":"arxiv","id":"2505.11855","version":1},"attestation_state":"computed","paper":{"title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gon\\c{c}alo Paulo, Guijin Son, Heejeong Nam, Honglu Fan, Hyunwoo Ko, Jinha Choi, Jinyeop Song, Jiwoo Hong, Seungwon Lim, Stella Biderman, Youngjae Yu","submitted_at":"2025-05-17T05:45:16Z","abstract_excerpt":"Recent advances in large language models (LLMs) have fueled the vision of automated scientific discovery, often called AI Co-Scientists. To date, prior work casts these systems as generative co-authors responsible for crafting hypotheses, synthesizing code, or drafting manuscripts. In this work, we explore a complementary application: using LLMs as verifiers to automate the \\textbf{academic verification of scientific manuscripts}. To that end, we introduce SPOT, a dataset of 83 published papers paired with 91 errors significant enough to prompt errata or retraction, cross-validated with actual"},"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":"2505.11855","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-17T05:45:16Z","cross_cats_sorted":[],"title_canon_sha256":"b0e01c82198b3d1fae630f781a2399ac6a809f8e8141d4d5048f9513e19008e8","abstract_canon_sha256":"d872a0a9e477ecfa02ee4f0d3757be25458e7b15388d38aba519b60c6e0305ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:53.272994Z","signature_b64":"tcVsOShPKZrQMyIOa9O0qxKAcis8wR12YbL478/52Mpgp2KizpcOf0MvTfv2A6TTkomdIiQ4vSRUKM3Xt10JBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7a0b2489f10fec43114eec1883fcdff148b3a25faf41f5a66fe67b37218ace7","last_reissued_at":"2026-07-05T11:04:53.272499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:53.272499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gon\\c{c}alo Paulo, Guijin Son, Heejeong Nam, Honglu Fan, Hyunwoo Ko, Jinha Choi, Jinyeop Song, Jiwoo Hong, Seungwon Lim, Stella Biderman, Youngjae Yu","submitted_at":"2025-05-17T05:45:16Z","abstract_excerpt":"Recent advances in large language models (LLMs) have fueled the vision of automated scientific discovery, often called AI Co-Scientists. To date, prior work casts these systems as generative co-authors responsible for crafting hypotheses, synthesizing code, or drafting manuscripts. In this work, we explore a complementary application: using LLMs as verifiers to automate the \\textbf{academic verification of scientific manuscripts}. To that end, we introduce SPOT, a dataset of 83 published papers paired with 91 errors significant enough to prompt errata or retraction, cross-validated with actual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11855","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/2505.11855/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":"2505.11855","created_at":"2026-07-05T11:04:53.272562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11855v1","created_at":"2026-07-05T11:04:53.272562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11855","created_at":"2026-07-05T11:04:53.272562+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y6QLESE7CD7M","created_at":"2026-07-05T11:04:53.272562+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y6QLESE7CD7MIMIU","created_at":"2026-07-05T11:04:53.272562+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y6QLESE7","created_at":"2026-07-05T11:04:53.272562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24177","citing_title":"Agon: An Autonomous Large-Scale Omnidisciplinary Research System Built on Prompt Economy","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28277","citing_title":"Towards Automating Scientific Review with Google's Paper Assistant Tool","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18237","citing_title":"ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12910","citing_title":"SciCoQA: Quality Assurance for Scientific Paper--Code Alignment","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10425","citing_title":"Toward an Engineering of Science: Rebalancing Generation and Verification in the Age of AI","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12198","citing_title":"Grounded autonomous scrutiny at scale: emergent critique from reproduction of published computational physics papers","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74","json":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74.json","graph_json":"https://pith.science/api/pith-number/Y6QLESE7CD7MIMIU53AYQP6N74/graph.json","events_json":"https://pith.science/api/pith-number/Y6QLESE7CD7MIMIU53AYQP6N74/events.json","paper":"https://pith.science/paper/Y6QLESE7"},"agent_actions":{"view_html":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74","download_json":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74.json","view_paper":"https://pith.science/paper/Y6QLESE7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11855&json=true","fetch_graph":"https://pith.science/api/pith-number/Y6QLESE7CD7MIMIU53AYQP6N74/graph.json","fetch_events":"https://pith.science/api/pith-number/Y6QLESE7CD7MIMIU53AYQP6N74/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74/action/storage_attestation","attest_author":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74/action/author_attestation","sign_citation":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74/action/citation_signature","submit_replication":"https://pith.science/pith/Y6QLESE7CD7MIMIU53AYQP6N74/action/replication_record"}},"created_at":"2026-07-05T11:04:53.272562+00:00","updated_at":"2026-07-05T11:04:53.272562+00:00"}