{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SQNMKGXM2LV7NTHVHUZBIOY5OO","short_pith_number":"pith:SQNMKGXM","schema_version":"1.0","canonical_sha256":"941ac51aecd2ebf6ccf53d32143b1d7384e081790fe7402faf036ba146c2387b","source":{"kind":"arxiv","id":"2409.11363","version":2},"attestation_state":"computed","paper":{"title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Arvind Narayanan, Benedikt Stroebl, Nitya Nadgir, Sayash Kapoor, Zachary S. Siegel","submitted_at":"2024-09-17T17:13:19Z","abstract_excerpt":"AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly correspond to real-world tasks of interest. This paper introduces such a benchmark, designed to measure the accuracy of AI agents in tackling a crucial yet surprisingly challenging aspect of scientific research: computational reproducibility. This task, fundamental to the scientific process, involves reproducing the results of a study using the provided code and da"},"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":"2409.11363","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-17T17:13:19Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"c24d6d2df40f0c5e53a80e16e17056eaebaea7c3a1036105b6d5045d69c94783","abstract_canon_sha256":"8f87499f968fbbc6c602eced5ea3412b1c075e7e51195e5c8b06eb9bc0d8049c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T00:14:20.108486Z","signature_b64":"8PuXi+QEytd1ZhbEV1Pr8d1CZ1UvYysqiNbyOw9ynCFFKXEZkvhdCxzzSFV1XOLrp4fJsGhqRBe5ld69OOxhAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"941ac51aecd2ebf6ccf53d32143b1d7384e081790fe7402faf036ba146c2387b","last_reissued_at":"2026-06-24T00:14:20.107923Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T00:14:20.107923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CORE-Bench: Fostering the Credibility of Published Research Through a Computational Reproducibility Agent Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Arvind Narayanan, Benedikt Stroebl, Nitya Nadgir, Sayash Kapoor, Zachary S. Siegel","submitted_at":"2024-09-17T17:13:19Z","abstract_excerpt":"AI agents have the potential to aid users on a variety of consequential tasks, including conducting scientific research. To spur the development of useful agents, we need benchmarks that are challenging, but more crucially, directly correspond to real-world tasks of interest. This paper introduces such a benchmark, designed to measure the accuracy of AI agents in tackling a crucial yet surprisingly challenging aspect of scientific research: computational reproducibility. This task, fundamental to the scientific process, involves reproducing the results of a study using the provided code and da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.11363","kind":"arxiv","version":2},"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/2409.11363/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":"2409.11363","created_at":"2026-06-24T00:14:20.107993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.11363v2","created_at":"2026-06-24T00:14:20.107993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.11363","created_at":"2026-06-24T00:14:20.107993+00:00"},{"alias_kind":"pith_short_12","alias_value":"SQNMKGXM2LV7","created_at":"2026-06-24T00:14:20.107993+00:00"},{"alias_kind":"pith_short_16","alias_value":"SQNMKGXM2LV7NTHV","created_at":"2026-06-24T00:14:20.107993+00:00"},{"alias_kind":"pith_short_8","alias_value":"SQNMKGXM","created_at":"2026-06-24T00:14:20.107993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":12,"sample":[{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":125,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16616","citing_title":"MLReplicate: Benchmarking Autonomous Research Systems for Machine Learning Reproducibility","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19156","citing_title":"How Far Are We From True Auto-Research?","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16902","citing_title":"ArtifactLinker: Linking Scientific Artifacts for Automatic State-of-the-Art Discovery","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2509.20374","citing_title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2602.08561","citing_title":"Automating Computational Reproducibility in Social Science: Comparing Prompt-Based and Agent-Based Approaches","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2602.11354","citing_title":"ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13950","citing_title":"Collider-Bench: Benchmarking AI Agents with Particle Physics Analysis Reproduction","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12808","citing_title":"Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12808","citing_title":"Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13275","citing_title":"ReproScore: Separating Readiness from Outcome in Research Software Reproducibility Assessment","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11270","citing_title":"Evaluating LLM Agents on Automated Software Analysis Tasks","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO","json":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO.json","graph_json":"https://pith.science/api/pith-number/SQNMKGXM2LV7NTHVHUZBIOY5OO/graph.json","events_json":"https://pith.science/api/pith-number/SQNMKGXM2LV7NTHVHUZBIOY5OO/events.json","paper":"https://pith.science/paper/SQNMKGXM"},"agent_actions":{"view_html":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO","download_json":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO.json","view_paper":"https://pith.science/paper/SQNMKGXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.11363&json=true","fetch_graph":"https://pith.science/api/pith-number/SQNMKGXM2LV7NTHVHUZBIOY5OO/graph.json","fetch_events":"https://pith.science/api/pith-number/SQNMKGXM2LV7NTHVHUZBIOY5OO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO/action/storage_attestation","attest_author":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO/action/author_attestation","sign_citation":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO/action/citation_signature","submit_replication":"https://pith.science/pith/SQNMKGXM2LV7NTHVHUZBIOY5OO/action/replication_record"}},"created_at":"2026-06-24T00:14:20.107993+00:00","updated_at":"2026-06-24T00:14:20.107993+00:00"}