{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7FNV5UPX2MWXTTVY6A5PC2LFZ5","short_pith_number":"pith:7FNV5UPX","schema_version":"1.0","canonical_sha256":"f95b5ed1f7d32d79ceb8f03af16965cf755c4711ab1097f46f318da29224d0d8","source":{"kind":"arxiv","id":"2502.00902","version":2},"attestation_state":"computed","paper":{"title":"More Rigorous Software Engineering Would Improve Reproducibility in Machine Learning Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Charles Tapley Hoyt, Lokesh Veeramacheneni, Moritz Wolter","submitted_at":"2025-02-02T20:29:09Z","abstract_excerpt":"While experimental reproduction remains a pillar of the scientific method, we observe that the software best practices supporting the reproduction of machine learning ( ML ) research are often undervalued or overlooked, leading both to poor reproducibility and damage to trust in the ML community. We quantify these concerns by surveying the usage of software best practices in software repositories associated with publications at major ML conferences and journals such as NeurIPS, ICML, ICLR, TMLR, and MLOSS within the last decade. We report the results of this survey that identify areas where so"},"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":"2502.00902","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-02-02T20:29:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2236c5554b369712184b7b9aca1d0703b9dd71f1bb96c3786a05b1cc46eaa729","abstract_canon_sha256":"0a82bb57949a0bdb484d182e3e7c1a3587d36de9b022031dfd6d550fd9fd7f52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:24.401108Z","signature_b64":"S+e8JPmyufFbhpIsLKdOiZZkF90NzejjAp9NdeEw9eXWHS9FmBarkmPXcvVvI27ZAT7JNZbrInw/Tde3Sg6ADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f95b5ed1f7d32d79ceb8f03af16965cf755c4711ab1097f46f318da29224d0d8","last_reissued_at":"2026-07-05T12:03:24.400608Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:24.400608Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"More Rigorous Software Engineering Would Improve Reproducibility in Machine Learning Research","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Charles Tapley Hoyt, Lokesh Veeramacheneni, Moritz Wolter","submitted_at":"2025-02-02T20:29:09Z","abstract_excerpt":"While experimental reproduction remains a pillar of the scientific method, we observe that the software best practices supporting the reproduction of machine learning ( ML ) research are often undervalued or overlooked, leading both to poor reproducibility and damage to trust in the ML community. We quantify these concerns by surveying the usage of software best practices in software repositories associated with publications at major ML conferences and journals such as NeurIPS, ICML, ICLR, TMLR, and MLOSS within the last decade. We report the results of this survey that identify areas where so"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00902","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/2502.00902/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":"2502.00902","created_at":"2026-07-05T12:03:24.400668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.00902v2","created_at":"2026-07-05T12:03:24.400668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00902","created_at":"2026-07-05T12:03:24.400668+00:00"},{"alias_kind":"pith_short_12","alias_value":"7FNV5UPX2MWX","created_at":"2026-07-05T12:03:24.400668+00:00"},{"alias_kind":"pith_short_16","alias_value":"7FNV5UPX2MWXTTVY","created_at":"2026-07-05T12:03:24.400668+00:00"},{"alias_kind":"pith_short_8","alias_value":"7FNV5UPX","created_at":"2026-07-05T12:03:24.400668+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00803","citing_title":"Can Coding Agents Reproduce Findings in Computational Materials Science?","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5","json":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5.json","graph_json":"https://pith.science/api/pith-number/7FNV5UPX2MWXTTVY6A5PC2LFZ5/graph.json","events_json":"https://pith.science/api/pith-number/7FNV5UPX2MWXTTVY6A5PC2LFZ5/events.json","paper":"https://pith.science/paper/7FNV5UPX"},"agent_actions":{"view_html":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5","download_json":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5.json","view_paper":"https://pith.science/paper/7FNV5UPX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.00902&json=true","fetch_graph":"https://pith.science/api/pith-number/7FNV5UPX2MWXTTVY6A5PC2LFZ5/graph.json","fetch_events":"https://pith.science/api/pith-number/7FNV5UPX2MWXTTVY6A5PC2LFZ5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5/action/storage_attestation","attest_author":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5/action/author_attestation","sign_citation":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5/action/citation_signature","submit_replication":"https://pith.science/pith/7FNV5UPX2MWXTTVY6A5PC2LFZ5/action/replication_record"}},"created_at":"2026-07-05T12:03:24.400668+00:00","updated_at":"2026-07-05T12:03:24.400668+00:00"}