{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VM7KHPSC2VQD67EQFLT5QV7NBT","short_pith_number":"pith:VM7KHPSC","schema_version":"1.0","canonical_sha256":"ab3ea3be42d5603f7c902ae7d857ed0cdcea3d46050f367ab20816852e801918","source":{"kind":"arxiv","id":"2505.11491","version":2},"attestation_state":"computed","paper":{"title":"Potential failures of physics-informed machine learning in traffic flow modeling: theoretical and experimental analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Dianwei Chen, Xianfeng Terry Yang, Yaobang Gong, Yao Cheng, Yuan-Zheng Lei","submitted_at":"2025-05-16T17:55:06Z","abstract_excerpt":"This study investigates why physics-informed machine learning (PIML) can fail in macroscopic traffic flow modeling. We define failure as cases where a PIML model underperforms both purely data-driven and purely physics-based baselines by a given threshold. Unlike in other fields, physics residuals themselves do not hinder optimization in this setting. Instead, effective updates require both data and physics gradients to form acute angles with the true gradient, a condition difficult to satisfy with low-resolution loop data. In such cases, neural networks cannot accurately approximate density a"},"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":"2505.11491","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T17:55:06Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"73e79aac87554fa1b3558236e8f4d76a6767207341c40b5859c1344dfc05a722","abstract_canon_sha256":"eaae0abb85d9d2f2cad9e8d26323a0ffa3d16e6f2ba350630519cdf6975a9cb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:17.923161Z","signature_b64":"s7dHps31SK423PjiJIWagbv9quNaSYe4L3mBSUgrNuJYxjfgw9FnF8LU+6Q78qSsDBH9DiiUxghtt2gzQLmpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab3ea3be42d5603f7c902ae7d857ed0cdcea3d46050f367ab20816852e801918","last_reissued_at":"2026-07-05T12:11:17.922603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:17.922603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Potential failures of physics-informed machine learning in traffic flow modeling: theoretical and experimental analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Dianwei Chen, Xianfeng Terry Yang, Yaobang Gong, Yao Cheng, Yuan-Zheng Lei","submitted_at":"2025-05-16T17:55:06Z","abstract_excerpt":"This study investigates why physics-informed machine learning (PIML) can fail in macroscopic traffic flow modeling. We define failure as cases where a PIML model underperforms both purely data-driven and purely physics-based baselines by a given threshold. Unlike in other fields, physics residuals themselves do not hinder optimization in this setting. Instead, effective updates require both data and physics gradients to form acute angles with the true gradient, a condition difficult to satisfy with low-resolution loop data. In such cases, neural networks cannot accurately approximate density a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11491","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/2505.11491/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":"2505.11491","created_at":"2026-07-05T12:11:17.922665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11491v2","created_at":"2026-07-05T12:11:17.922665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11491","created_at":"2026-07-05T12:11:17.922665+00:00"},{"alias_kind":"pith_short_12","alias_value":"VM7KHPSC2VQD","created_at":"2026-07-05T12:11:17.922665+00:00"},{"alias_kind":"pith_short_16","alias_value":"VM7KHPSC2VQD67EQ","created_at":"2026-07-05T12:11:17.922665+00:00"},{"alias_kind":"pith_short_8","alias_value":"VM7KHPSC","created_at":"2026-07-05T12:11:17.922665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.08028","citing_title":"Adaptive Domain Decomposition Physics-Informed Neural Networks for Traffic State Estimation with Sparse Sensor Data","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT","json":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT.json","graph_json":"https://pith.science/api/pith-number/VM7KHPSC2VQD67EQFLT5QV7NBT/graph.json","events_json":"https://pith.science/api/pith-number/VM7KHPSC2VQD67EQFLT5QV7NBT/events.json","paper":"https://pith.science/paper/VM7KHPSC"},"agent_actions":{"view_html":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT","download_json":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT.json","view_paper":"https://pith.science/paper/VM7KHPSC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11491&json=true","fetch_graph":"https://pith.science/api/pith-number/VM7KHPSC2VQD67EQFLT5QV7NBT/graph.json","fetch_events":"https://pith.science/api/pith-number/VM7KHPSC2VQD67EQFLT5QV7NBT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT/action/storage_attestation","attest_author":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT/action/author_attestation","sign_citation":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT/action/citation_signature","submit_replication":"https://pith.science/pith/VM7KHPSC2VQD67EQFLT5QV7NBT/action/replication_record"}},"created_at":"2026-07-05T12:11:17.922665+00:00","updated_at":"2026-07-05T12:11:17.922665+00:00"}