{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UMXWL5UKMC4EGOPF4IH3EOOVCD","short_pith_number":"pith:UMXWL5UK","schema_version":"1.0","canonical_sha256":"a32f65f68a60b84339e5e20fb239d510f06cbc6731411c6848022ff50778669a","source":{"kind":"arxiv","id":"2605.14179","version":1},"attestation_state":"computed","paper":{"title":"A Neural-Network Framework to Learn History-Dependent Constitutive Laws and Identifiability of Internal Variables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Neural networks can learn history-dependent constitutive laws for materials while guaranteeing consistency with the second law of thermodynamics and stability under extreme strain.","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Andrew Stuart, Kaushik Bhattacharya, Lianghao Cao, Mayank Raj","submitted_at":"2026-05-13T22:59:58Z","abstract_excerpt":"The identification of constitutive laws is ubiquitous in engineering: in modeling of materials where experimental data are fitted to mathematical models or learning surrogate models to beat the FE\\textsuperscript{2} computational cost of multiscale numerical simulations. However, these models of constitutive laws, unless equipped with a potential formulation, are not necessarily consistent with (a) the second law of thermodynamics; (b) stability of the material under extreme applied strain; and (c) the mathematical theory underpinning the existence of solutions of the governing equation. In th"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.14179","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.mtrl-sci","submitted_at":"2026-05-13T22:59:58Z","cross_cats_sorted":[],"title_canon_sha256":"b7db76b375000e11a50d96c35a9b77ace9447f20ae96eb4cda129fb1c6909548","abstract_canon_sha256":"cefa29523992f05d29473f10c8194cf8c1d8b6ce0298dacec2a754ad0519e9b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:11.264568Z","signature_b64":"kj0xQfdIhJv9HFFT6eH+f44qejSvX7df/LsX1B+Th6rKlOmypRdhZCFHUsar/YEVk25KA0pDpfiWVuPoduCgAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a32f65f68a60b84339e5e20fb239d510f06cbc6731411c6848022ff50778669a","last_reissued_at":"2026-05-17T23:39:11.264032Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:11.264032Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Neural-Network Framework to Learn History-Dependent Constitutive Laws and Identifiability of Internal Variables","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Neural networks can learn history-dependent constitutive laws for materials while guaranteeing consistency with the second law of thermodynamics and stability under extreme strain.","cross_cats":[],"primary_cat":"cond-mat.mtrl-sci","authors_text":"Andrew Stuart, Kaushik Bhattacharya, Lianghao Cao, Mayank Raj","submitted_at":"2026-05-13T22:59:58Z","abstract_excerpt":"The identification of constitutive laws is ubiquitous in engineering: in modeling of materials where experimental data are fitted to mathematical models or learning surrogate models to beat the FE\\textsuperscript{2} computational cost of multiscale numerical simulations. However, these models of constitutive laws, unless equipped with a potential formulation, are not necessarily consistent with (a) the second law of thermodynamics; (b) stability of the material under extreme applied strain; and (c) the mathematical theory underpinning the existence of solutions of the governing equation. In th"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that the internal variables that are learned from the data are unique up to a linear transform. The framework is deployed to learn the Taylor-averaged response of a polycrystalline magnesium unit cell. We achieve 2% relative error in the prediction of the Taylor-averaged response.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a neural network can be formulated in a causal and energetic manner to guarantee consistency with the second law of thermodynamics, stability under extreme strain, and existence of solutions to the governing equations while retaining sufficient expressiveness for real material data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A causal energetic neural network framework learns thermodynamically consistent history-dependent constitutive laws, proving internal variables are unique up to linear transformation and achieving 2% error on polycrystalline magnesium data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Neural networks can learn history-dependent constitutive laws for materials while guaranteeing consistency with the second law of thermodynamics and stability under extreme strain.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a67ab8184ab269283c98111a00f9d9456c9bc7c120d696d03d37d431ed93859e"},"source":{"id":"2605.14179","kind":"arxiv","version":1},"verdict":{"id":"e2f943f2-0ade-4104-a81c-fa756198926d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:48:32.783266Z","strongest_claim":"We show that the internal variables that are learned from the data are unique up to a linear transform. The framework is deployed to learn the Taylor-averaged response of a polycrystalline magnesium unit cell. We achieve 2% relative error in the prediction of the Taylor-averaged response.","one_line_summary":"A causal energetic neural network framework learns thermodynamically consistent history-dependent constitutive laws, proving internal variables are unique up to linear transformation and achieving 2% error on polycrystalline magnesium data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a neural network can be formulated in a causal and energetic manner to guarantee consistency with the second law of thermodynamics, stability under extreme strain, and existence of solutions to the governing equations while retaining sufficient expressiveness for real material data.","pith_extraction_headline":"Neural networks can learn history-dependent constitutive laws for materials while guaranteeing consistency with the second law of thermodynamics and stability under extreme strain."},"references":{"count":37,"sample":[{"doi":"","year":2017,"title":"Brandon Amos, Lei Xu, and J. Zico Kolter. Input convex neural networks, 2017","work_id":"c854d2a5-b229-4cbc-aee5-c9eb773f54c9","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1002/nme.6957","year":2022,"title":"A mechanics-informed artificial neural network approach in data-driven constitutive modeling.International Journal for Numerical Methods in Engineering, 123 20 (12):2738–2759, 2022","work_id":"8eafda40-7347-438d-b0f2-7f2949c3fe82","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.cma.2023.116463","year":2023,"title":"A mechanics-informed deep learning framework for data-driven non- linear viscoelasticity.Computer Methods in Applied Mechanics and Engineering, 417:116463, 2023","work_id":"23301735-4455-41da-b25d-08728ad53a11","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1016/j.cma.2025.118666","year":2026,"title":"Faisal As’ad and Charbel Farhat. A staggered training framework for mechanics-informed neu- ral networks in tractable multiscale homogenization with application to woven fabrics.Computer Methods in Ap","work_id":"c1ec53a9-2a63-4189-8a8d-a3f838609de7","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1977,"title":"J. M. Ball. Constitutive inequalities and existence theorems in nonlinear elastostat- ics.Nonlinear Analysis and Mechanics, Heriot-Watt Symposium Vol. 1, 1977. URL https://people.maths.ox.ac.uk/~ball/","work_id":"8c1d7c7b-b0d2-4b36-8cca-624e19f1761d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"2aabcdab47b06aaee6c1a25ee370b3cec2fb1a9154356ff3512c2133ddd5009e","internal_anchors":1},"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":"2605.14179","created_at":"2026-05-17T23:39:11.264130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14179v1","created_at":"2026-05-17T23:39:11.264130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14179","created_at":"2026-05-17T23:39:11.264130+00:00"},{"alias_kind":"pith_short_12","alias_value":"UMXWL5UKMC4E","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"UMXWL5UKMC4EGOPF","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"UMXWL5UK","created_at":"2026-05-18T12:33:37.589309+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/UMXWL5UKMC4EGOPF4IH3EOOVCD","json":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD.json","graph_json":"https://pith.science/api/pith-number/UMXWL5UKMC4EGOPF4IH3EOOVCD/graph.json","events_json":"https://pith.science/api/pith-number/UMXWL5UKMC4EGOPF4IH3EOOVCD/events.json","paper":"https://pith.science/paper/UMXWL5UK"},"agent_actions":{"view_html":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD","download_json":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD.json","view_paper":"https://pith.science/paper/UMXWL5UK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14179&json=true","fetch_graph":"https://pith.science/api/pith-number/UMXWL5UKMC4EGOPF4IH3EOOVCD/graph.json","fetch_events":"https://pith.science/api/pith-number/UMXWL5UKMC4EGOPF4IH3EOOVCD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD/action/storage_attestation","attest_author":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD/action/author_attestation","sign_citation":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD/action/citation_signature","submit_replication":"https://pith.science/pith/UMXWL5UKMC4EGOPF4IH3EOOVCD/action/replication_record"}},"created_at":"2026-05-17T23:39:11.264130+00:00","updated_at":"2026-05-17T23:39:11.264130+00:00"}