{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M2NA7LSMCYBGSZP4AVMBIEQ674","short_pith_number":"pith:M2NA7LSM","schema_version":"1.0","canonical_sha256":"669a0fae4c16026965fc055814121eff191da169444ec58d3f4412ef5070ad04","source":{"kind":"arxiv","id":"2607.20321","version":1},"attestation_state":"computed","paper":{"title":"Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.flu-dyn","authors_text":"Binyang Song, Qingang Zhang, Ruihang Wang, Tianyu Li, Yonggang Wen, Zhiwei Cao","submitted_at":"2026-07-22T16:07:09Z","abstract_excerpt":"Neural surrogates are widely used in scientific machine learning for fast prediction of three-dimensional (3D) thermo-fluid fields. However, generating training data using conventional numerical solvers often incurs substantial computational and storage costs. We propose to train an attention graph neural network by minimizing the finite-volume method (FVM) residuals of the governing equations. These residuals are evaluated directly on the mesh, requiring no labeled data. We evaluate the trained surrogates against computational fluid dynamics (CFD) references and a data-supervised baseline acr"},"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":"2607.20321","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.flu-dyn","submitted_at":"2026-07-22T16:07:09Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b1879e6d204f5a36bd04c7b6bd52cc2974e368245cccb10423f6462e4498b5dd","abstract_canon_sha256":"09ff564f5691c8d7532cb7a98fdb257ead5f130e15d43afc8739ff6f2d481068"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:25:14.188776Z","signature_b64":"ExtFHqvfPAMH9K9C8D0mvbCRtfywzmCVLOrtikHxUedv+xGtIq6QjYS5fq90rosi6AUqhxGsCa724k6rp99eCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669a0fae4c16026965fc055814121eff191da169444ec58d3f4412ef5070ad04","last_reissued_at":"2026-07-23T01:25:14.187919Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:25:14.187919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"physics.flu-dyn","authors_text":"Binyang Song, Qingang Zhang, Ruihang Wang, Tianyu Li, Yonggang Wen, Zhiwei Cao","submitted_at":"2026-07-22T16:07:09Z","abstract_excerpt":"Neural surrogates are widely used in scientific machine learning for fast prediction of three-dimensional (3D) thermo-fluid fields. However, generating training data using conventional numerical solvers often incurs substantial computational and storage costs. We propose to train an attention graph neural network by minimizing the finite-volume method (FVM) residuals of the governing equations. These residuals are evaluated directly on the mesh, requiring no labeled data. We evaluate the trained surrogates against computational fluid dynamics (CFD) references and a data-supervised baseline acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20321","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/2607.20321/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":"2607.20321","created_at":"2026-07-23T01:25:14.188359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20321v1","created_at":"2026-07-23T01:25:14.188359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20321","created_at":"2026-07-23T01:25:14.188359+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2NA7LSMCYBG","created_at":"2026-07-23T01:25:14.188359+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2NA7LSMCYBGSZP4","created_at":"2026-07-23T01:25:14.188359+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2NA7LSM","created_at":"2026-07-23T01:25:14.188359+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/M2NA7LSMCYBGSZP4AVMBIEQ674","json":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674.json","graph_json":"https://pith.science/api/pith-number/M2NA7LSMCYBGSZP4AVMBIEQ674/graph.json","events_json":"https://pith.science/api/pith-number/M2NA7LSMCYBGSZP4AVMBIEQ674/events.json","paper":"https://pith.science/paper/M2NA7LSM"},"agent_actions":{"view_html":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674","download_json":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674.json","view_paper":"https://pith.science/paper/M2NA7LSM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20321&json=true","fetch_graph":"https://pith.science/api/pith-number/M2NA7LSMCYBGSZP4AVMBIEQ674/graph.json","fetch_events":"https://pith.science/api/pith-number/M2NA7LSMCYBGSZP4AVMBIEQ674/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674/action/storage_attestation","attest_author":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674/action/author_attestation","sign_citation":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674/action/citation_signature","submit_replication":"https://pith.science/pith/M2NA7LSMCYBGSZP4AVMBIEQ674/action/replication_record"}},"created_at":"2026-07-23T01:25:14.188359+00:00","updated_at":"2026-07-23T01:25:14.188359+00:00"}