{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JESONGUVRAMSWG64GADSRO6MXR","short_pith_number":"pith:JESONGUV","schema_version":"1.0","canonical_sha256":"4924e69a9588192b1bdc300728bbccbc6780a075075ea1e72611dbbd783075c1","source":{"kind":"arxiv","id":"2605.29153","version":1},"attestation_state":"computed","paper":{"title":"Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Haiquan Lu, Michael W. Mahoney, Pu Ren, Tianyu Pang, Xiaokun Zhong, Xiaopeng Wang, Yaoqing Yang, Yuanzhe Hu, Yujun Yan, Yuxin Wang","submitted_at":"2026-05-27T22:33:03Z","abstract_excerpt":"Neural networks trained under different hyperparameter settings can fall into distinct training \"regimes,\" with consistent behavior within regimes and qualitative differences across regimes. In this paper, we study such multi-regime behavior in scientific machine learning (SciML) models through a regime-aware diagnostic framework that jointly analyzes performance, training dynamics, and loss-landscape geometry. We identify three key findings: (i) a consistent three-regime structure emerges across many standard SciML models, different constraint enforcements, and various optimizer designs; (ii)"},"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":"2605.29153","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T22:33:03Z","cross_cats_sorted":["cs.AI","physics.comp-ph"],"title_canon_sha256":"056ac46726c11081c2f362c115e7f5aa98815e4444200100f7b3c053b4703ef5","abstract_canon_sha256":"02f34889040167f194ebd34b08f081305f6132aafdcf4bba7414b4b322f07575"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:21.208444Z","signature_b64":"3KD2g1jK2IZ+VOIJfWOTrArDbmkOjsvbVyQU+HxNvaede4L4zM4YxjGpj3MJUipgT1bNlQEEjPE+RH2RNgAPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4924e69a9588192b1bdc300728bbccbc6780a075075ea1e72611dbbd783075c1","last_reissued_at":"2026-05-29T01:05:21.207518Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:21.207518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unveiling Multi-regime Patterns in SciML: Distinct Failure Modes and Regime-specific Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Haiquan Lu, Michael W. Mahoney, Pu Ren, Tianyu Pang, Xiaokun Zhong, Xiaopeng Wang, Yaoqing Yang, Yuanzhe Hu, Yujun Yan, Yuxin Wang","submitted_at":"2026-05-27T22:33:03Z","abstract_excerpt":"Neural networks trained under different hyperparameter settings can fall into distinct training \"regimes,\" with consistent behavior within regimes and qualitative differences across regimes. In this paper, we study such multi-regime behavior in scientific machine learning (SciML) models through a regime-aware diagnostic framework that jointly analyzes performance, training dynamics, and loss-landscape geometry. We identify three key findings: (i) a consistent three-regime structure emerges across many standard SciML models, different constraint enforcements, and various optimizer designs; (ii)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29153","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/2605.29153/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":"2605.29153","created_at":"2026-05-29T01:05:21.207628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29153v1","created_at":"2026-05-29T01:05:21.207628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29153","created_at":"2026-05-29T01:05:21.207628+00:00"},{"alias_kind":"pith_short_12","alias_value":"JESONGUVRAMS","created_at":"2026-05-29T01:05:21.207628+00:00"},{"alias_kind":"pith_short_16","alias_value":"JESONGUVRAMSWG64","created_at":"2026-05-29T01:05:21.207628+00:00"},{"alias_kind":"pith_short_8","alias_value":"JESONGUV","created_at":"2026-05-29T01:05:21.207628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR","json":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR.json","graph_json":"https://pith.science/api/pith-number/JESONGUVRAMSWG64GADSRO6MXR/graph.json","events_json":"https://pith.science/api/pith-number/JESONGUVRAMSWG64GADSRO6MXR/events.json","paper":"https://pith.science/paper/JESONGUV"},"agent_actions":{"view_html":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR","download_json":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR.json","view_paper":"https://pith.science/paper/JESONGUV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29153&json=true","fetch_graph":"https://pith.science/api/pith-number/JESONGUVRAMSWG64GADSRO6MXR/graph.json","fetch_events":"https://pith.science/api/pith-number/JESONGUVRAMSWG64GADSRO6MXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR/action/storage_attestation","attest_author":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR/action/author_attestation","sign_citation":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR/action/citation_signature","submit_replication":"https://pith.science/pith/JESONGUVRAMSWG64GADSRO6MXR/action/replication_record"}},"created_at":"2026-05-29T01:05:21.207628+00:00","updated_at":"2026-05-29T01:05:21.207628+00:00"}