{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DHASQDOC67YM7MOELIP2BJQNNJ","short_pith_number":"pith:DHASQDOC","schema_version":"1.0","canonical_sha256":"19c1280dc2f7f0cfb1c45a1fa0a60d6a63d22c22beb19e418087187904e272a5","source":{"kind":"arxiv","id":"2605.15231","version":1},"attestation_state":"computed","paper":{"title":"Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mask-Morph Graph U-Net uses coarse-graph morphing and masked pretraining to generalise hierarchical GNNs to new mesh geometries in crash simulations.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoran Li, Haosu Zhou, Nan Li, Philipp Stocker, Tobias Lehrer, Tobias Pfaff, Yingxue Zhao","submitted_at":"2026-05-13T18:04:58Z","abstract_excerpt":"Nonlinear finite element crash simulations are accurate but computationally expensive, limiting their use in iterative design optimisation. Machine-learning surrogate models based on graph neural networks (GNNs) offer a faster alternative. Message-passing GNNs are widely used for mesh simulation, and their shared node and edge update functions are relatively generalisable across varying graph structures. By contrast, non-shareable edge-specific aggregation layers can capture nonlinear relationships more accurately but usually require fixed graph connectivity, which limits generalisability. Thi"},"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":"2605.15231","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-13T18:04:58Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"35ee75c903b6a874f2278ff6b9b6c5f25996b3607ef506735779b93d9efbed15","abstract_canon_sha256":"6cbcec7cc9c5c0e4342c9e8696004551992b3ebf4de0fc7d9470ea19468faef1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:47.519887Z","signature_b64":"/81dWfZ2jTJuBPm2xNq+R1T1uGsRm90tvFUockygx2qq44jteGAiuCmbrQctPqaL/wVJbjFTpsc8MVN6jgTBAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19c1280dc2f7f0cfb1c45a1fa0a60d6a63d22c22beb19e418087187904e272a5","last_reissued_at":"2026-05-20T00:00:47.518785Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:47.518785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mask-Morph Graph U-Net: A Generalisable Mesh-Based Surrogate for Crashworthiness Field Prediction under Large Geometric Variation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Mask-Morph Graph U-Net uses coarse-graph morphing and masked pretraining to generalise hierarchical GNNs to new mesh geometries in crash simulations.","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Haoran Li, Haosu Zhou, Nan Li, Philipp Stocker, Tobias Lehrer, Tobias Pfaff, Yingxue Zhao","submitted_at":"2026-05-13T18:04:58Z","abstract_excerpt":"Nonlinear finite element crash simulations are accurate but computationally expensive, limiting their use in iterative design optimisation. Machine-learning surrogate models based on graph neural networks (GNNs) offer a faster alternative. Message-passing GNNs are widely used for mesh simulation, and their shared node and edge update functions are relatively generalisable across varying graph structures. By contrast, non-shareable edge-specific aggregation layers can capture nonlinear relationships more accurately but usually require fixed graph connectivity, which limits generalisability. Thi"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Coarse-graph morphing via feature-aligned barycentric parameterisation improves test accuracy over a fixed-coarse-graph baseline, while masked supervised pretraining reduces train-test discrepancy and improves data efficiency in cross-component transfer settings.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that feature-aligned barycentric parameterisation will produce sufficiently accurate spatial correspondence between the morphed coarse graph and each new input mesh without introducing systematic interpolation errors that propagate through the hierarchical U-Net layers.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMGUNet morphs coarse graph hierarchies with feature-aligned barycentric mapping and uses masked pretraining plus frozen edge layers to improve generalisability of mesh surrogates for crashworthiness prediction under large geometric changes.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mask-Morph Graph U-Net uses coarse-graph morphing and masked pretraining to generalise hierarchical GNNs to new mesh geometries in crash simulations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"adb9946577325cc50c8b7d271fb52d968168a59125d38e98b9ff103db23fd437"},"source":{"id":"2605.15231","kind":"arxiv","version":1},"verdict":{"id":"949bd918-d353-4f04-9f77-360818b58b44","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:34:58.057667Z","strongest_claim":"Coarse-graph morphing via feature-aligned barycentric parameterisation improves test accuracy over a fixed-coarse-graph baseline, while masked supervised pretraining reduces train-test discrepancy and improves data efficiency in cross-component transfer settings.","one_line_summary":"MMGUNet morphs coarse graph hierarchies with feature-aligned barycentric mapping and uses masked pretraining plus frozen edge layers to improve generalisability of mesh surrogates for crashworthiness prediction under large geometric changes.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that feature-aligned barycentric parameterisation will produce sufficiently accurate spatial correspondence between the morphed coarse graph and each new input mesh without introducing systematic interpolation errors that propagate through the hierarchical U-Net layers.","pith_extraction_headline":"Mask-Morph Graph U-Net uses coarse-graph morphing and masked pretraining to generalise hierarchical GNNs to new mesh geometries in crash simulations."},"integrity":{"clean":false,"summary":{"advisory":0,"critical":1,"by_detector":{"doi_compliance":{"total":1,"advisory":0,"critical":1,"informational":0}},"informational":0},"endpoint":"/pith/2605.15231/integrity.json","findings":[{"note":"Identifier '10.1145/2977606' is syntactically valid but the DOI registry (doi.org) returned 404, and Crossref / OpenAlex / internal corpus also have no record. The cited work could not be located through any authoritative source.","detector":"doi_compliance","severity":"critical","ref_index":44,"audited_at":"2026-05-19T16:45:50.378326Z","detected_doi":"10.1145/2977606","finding_type":"unresolvable_identifier","verdict_class":"cross_source","detected_arxiv_id":null}],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T18:01:56.043214Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T17:01:18.471395Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:45:50.378326Z","status":"completed","version":"1.0.0","findings_count":1},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.829476Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"07c2b11044acb83f8d251a688ab9d885c17b0639d4fe7d79b7175dbb19ecfad5"},"references":{"count":55,"sample":[{"doi":"10.4271/2006-01-0672","year":2006,"title":"S. R. Wu, Convergence study on explicit finite element for crashwor- thiness analysis, Tech. Rep. 2006-01-0672, SAE International (2006). doi:10.4271/2006-01-0672","work_id":"13d20550-59ad-4067-a002-f687f3f10592","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.4271/2007-01-0982","year":2007,"title":"J. Chang, T. Tyan, M. El-Bkaily, J. Cheng, A. Marpu, Q. Zeng, J. Santini, Implicit and explicit finite element methods for crash safety analysis, Tech. Rep. 2007-01-0982, SAE International (2007). doi","work_id":"906c7423-d219-47b9-8a2a-52b8fee88b53","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"E. Albak, Optimization design for circular multi-cell thin-walled tubes with discrete and continuous design variables, Mechanics of Advanced Materials and Structures 30 (24) (2023) 5091–5105","work_id":"650860c8-5870-4a30-a825-84b73009c2c6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2018,"title":"F. Xiong, D. Wang, Z.-D. Ma, L. Yang, Z. Li, B. Song, Multi-objective lightweight and crashworthiness optimization for the side structure of an automobile body, Structural and Multidisciplinary Optimi","work_id":"f4a3d349-b850-4589-a786-aa6f0f8890ec","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2019,"title":"A. Ahmadi Dastjerdi, M. Moshref-Javadi, H. Ahmadian, M. Gholam- pour, Crushing analysis and multi-objective optimization of different length bi-thin walled cylindrical structures under axial impact lo","work_id":"b03319da-4261-4250-ab1c-2b092080af3f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":55,"snapshot_sha256":"c5efb8b033b4c3cc5fe5b690cfb5f64d95b1fea270fb49cda63690182c8bf678","internal_anchors":2},"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":"2605.15231","created_at":"2026-05-20T00:00:47.518906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15231v1","created_at":"2026-05-20T00:00:47.518906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15231","created_at":"2026-05-20T00:00:47.518906+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHASQDOC67YM","created_at":"2026-05-20T00:00:47.518906+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHASQDOC67YM7MOE","created_at":"2026-05-20T00:00:47.518906+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHASQDOC","created_at":"2026-05-20T00:00:47.518906+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/DHASQDOC67YM7MOELIP2BJQNNJ","json":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ.json","graph_json":"https://pith.science/api/pith-number/DHASQDOC67YM7MOELIP2BJQNNJ/graph.json","events_json":"https://pith.science/api/pith-number/DHASQDOC67YM7MOELIP2BJQNNJ/events.json","paper":"https://pith.science/paper/DHASQDOC"},"agent_actions":{"view_html":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ","download_json":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ.json","view_paper":"https://pith.science/paper/DHASQDOC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15231&json=true","fetch_graph":"https://pith.science/api/pith-number/DHASQDOC67YM7MOELIP2BJQNNJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DHASQDOC67YM7MOELIP2BJQNNJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ/action/storage_attestation","attest_author":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ/action/author_attestation","sign_citation":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ/action/citation_signature","submit_replication":"https://pith.science/pith/DHASQDOC67YM7MOELIP2BJQNNJ/action/replication_record"}},"created_at":"2026-05-20T00:00:47.518906+00:00","updated_at":"2026-05-20T00:00:47.518906+00:00"}