{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OZIW3C3VNBSSRC2JPPPI4TZ6SE","short_pith_number":"pith:OZIW3C3V","schema_version":"1.0","canonical_sha256":"76516d8b756865288b497bde8e4f3e911f5581a7ee5a1fc19c50ada9c721b162","source":{"kind":"arxiv","id":"2407.07218","version":1},"attestation_state":"computed","paper":{"title":"Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","physics.flu-dyn"],"primary_cat":"math.NA","authors_text":"Ammar Hakim, Nick McGreivy","submitted_at":"2024-07-09T20:28:03Z","abstract_excerpt":"One of the most promising applications of machine learning (ML) in computational physics is to accelerate the solution of partial differential equations (PDEs). The key objective of ML-based PDE solvers is to output a sufficiently accurate solution faster than standard numerical methods, which are used as a baseline comparison. We first perform a systematic review of the ML-for-PDE solving literature. Of articles that use ML to solve a fluid-related PDE and claim to outperform a standard numerical method, we determine that 79% (60/76) compare to a weak baseline. Second, we find evidence that r"},"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":"2407.07218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"math.NA","submitted_at":"2024-07-09T20:28:03Z","cross_cats_sorted":["cs.LG","cs.NA","physics.flu-dyn"],"title_canon_sha256":"5dbf13b70da2841abb22a50eda2a2f9a7e3c7f8a8dcbad4f8cad6feb0a2cd4de","abstract_canon_sha256":"b741fa4d65564e708e0f351f12f4f93894a92b1cb19d7a03aa44b996d041933c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:24.406408Z","signature_b64":"jnsYC+DkZ17oFEFWr9074r8kyp5iDUyrWfbYbi+MPRG9UcOL0TtcjQwX2y7juEtBSQ/khkXBOZGTcCk50gLHAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76516d8b756865288b497bde8e4f3e911f5581a7ee5a1fc19c50ada9c721b162","last_reissued_at":"2026-07-05T09:20:24.405885Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:24.405885Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","physics.flu-dyn"],"primary_cat":"math.NA","authors_text":"Ammar Hakim, Nick McGreivy","submitted_at":"2024-07-09T20:28:03Z","abstract_excerpt":"One of the most promising applications of machine learning (ML) in computational physics is to accelerate the solution of partial differential equations (PDEs). The key objective of ML-based PDE solvers is to output a sufficiently accurate solution faster than standard numerical methods, which are used as a baseline comparison. We first perform a systematic review of the ML-for-PDE solving literature. Of articles that use ML to solve a fluid-related PDE and claim to outperform a standard numerical method, we determine that 79% (60/76) compare to a weak baseline. Second, we find evidence that r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07218","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/2407.07218/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":"2407.07218","created_at":"2026-07-05T09:20:24.405951+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07218v1","created_at":"2026-07-05T09:20:24.405951+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07218","created_at":"2026-07-05T09:20:24.405951+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZIW3C3VNBSS","created_at":"2026-07-05T09:20:24.405951+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZIW3C3VNBSSRC2J","created_at":"2026-07-05T09:20:24.405951+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZIW3C3V","created_at":"2026-07-05T09:20:24.405951+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.06933","citing_title":"Neural equilibria for long-term prediction of nonlinear conservation laws","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2509.12483","citing_title":"Benchmarking Physics-Informed Neural Networks and Boundary Elements Methods for Wave Scattering","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE","json":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE.json","graph_json":"https://pith.science/api/pith-number/OZIW3C3VNBSSRC2JPPPI4TZ6SE/graph.json","events_json":"https://pith.science/api/pith-number/OZIW3C3VNBSSRC2JPPPI4TZ6SE/events.json","paper":"https://pith.science/paper/OZIW3C3V"},"agent_actions":{"view_html":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE","download_json":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE.json","view_paper":"https://pith.science/paper/OZIW3C3V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07218&json=true","fetch_graph":"https://pith.science/api/pith-number/OZIW3C3VNBSSRC2JPPPI4TZ6SE/graph.json","fetch_events":"https://pith.science/api/pith-number/OZIW3C3VNBSSRC2JPPPI4TZ6SE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE/action/storage_attestation","attest_author":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE/action/author_attestation","sign_citation":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE/action/citation_signature","submit_replication":"https://pith.science/pith/OZIW3C3VNBSSRC2JPPPI4TZ6SE/action/replication_record"}},"created_at":"2026-07-05T09:20:24.405951+00:00","updated_at":"2026-07-05T09:20:24.405951+00:00"}