{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:WU6EP4XX7KGQL5LWTLEOMIRRXV","short_pith_number":"pith:WU6EP4XX","schema_version":"1.0","canonical_sha256":"b53c47f2f7fa8d05f5769ac8e62231bd7a9f43a927b829c1e59ce83ff0479a5a","source":{"kind":"arxiv","id":"2203.01874","version":3},"attestation_state":"computed","paper":{"title":"Thermodynamics-informed graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","math.DS"],"primary_cat":"cs.LG","authors_text":"Alberto Bad\\'ias, El\\'ias Cueto, Francisco Chinesta, Quercus Hern\\'andez","submitted_at":"2022-03-03T17:30:44Z","abstract_excerpt":"In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases to improve accuracy and generalization of the resulting integration scheme. The first is achieved with Graph Neural Networks, which induces a non-Euclidean geometrical prior with permutation invariant node and edge update functions. The second bias is forced by learning the GENERIC structure of the problem, an extension of the Hamiltonian formalism, to model more general non-conservative dynamics. Several examples 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":"2203.01874","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-03T17:30:44Z","cross_cats_sorted":["cs.CE","math.DS"],"title_canon_sha256":"4fce9943136dad7fc10ef356d0de3936764538af2533409a5a50dedbef28461e","abstract_canon_sha256":"f64a323438d0ac4d6d0eef722df2ba6ded32218a01044d2990f303dcb6dbd85f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:54.395979Z","signature_b64":"iZa359f5sUotdN9VDsDOkJ5GGx7DYQXdX3n9gUOVk9MB+9vTj040vOvHo//MkGpt6bQzNxIOBAjE0Mpwk7LkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b53c47f2f7fa8d05f5769ac8e62231bd7a9f43a927b829c1e59ce83ff0479a5a","last_reissued_at":"2026-07-05T04:28:54.395530Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:54.395530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thermodynamics-informed graph neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CE","math.DS"],"primary_cat":"cs.LG","authors_text":"Alberto Bad\\'ias, El\\'ias Cueto, Francisco Chinesta, Quercus Hern\\'andez","submitted_at":"2022-03-03T17:30:44Z","abstract_excerpt":"In this paper we present a deep learning method to predict the temporal evolution of dissipative dynamic systems. We propose using both geometric and thermodynamic inductive biases to improve accuracy and generalization of the resulting integration scheme. The first is achieved with Graph Neural Networks, which induces a non-Euclidean geometrical prior with permutation invariant node and edge update functions. The second bias is forced by learning the GENERIC structure of the problem, an extension of the Hamiltonian formalism, to model more general non-conservative dynamics. Several examples a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.01874","kind":"arxiv","version":3},"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/2203.01874/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":"2203.01874","created_at":"2026-07-05T04:28:54.395591+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.01874v3","created_at":"2026-07-05T04:28:54.395591+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.01874","created_at":"2026-07-05T04:28:54.395591+00:00"},{"alias_kind":"pith_short_12","alias_value":"WU6EP4XX7KGQ","created_at":"2026-07-05T04:28:54.395591+00:00"},{"alias_kind":"pith_short_16","alias_value":"WU6EP4XX7KGQL5LW","created_at":"2026-07-05T04:28:54.395591+00:00"},{"alias_kind":"pith_short_8","alias_value":"WU6EP4XX","created_at":"2026-07-05T04:28:54.395591+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/WU6EP4XX7KGQL5LWTLEOMIRRXV","json":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV.json","graph_json":"https://pith.science/api/pith-number/WU6EP4XX7KGQL5LWTLEOMIRRXV/graph.json","events_json":"https://pith.science/api/pith-number/WU6EP4XX7KGQL5LWTLEOMIRRXV/events.json","paper":"https://pith.science/paper/WU6EP4XX"},"agent_actions":{"view_html":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV","download_json":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV.json","view_paper":"https://pith.science/paper/WU6EP4XX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.01874&json=true","fetch_graph":"https://pith.science/api/pith-number/WU6EP4XX7KGQL5LWTLEOMIRRXV/graph.json","fetch_events":"https://pith.science/api/pith-number/WU6EP4XX7KGQL5LWTLEOMIRRXV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV/action/storage_attestation","attest_author":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV/action/author_attestation","sign_citation":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV/action/citation_signature","submit_replication":"https://pith.science/pith/WU6EP4XX7KGQL5LWTLEOMIRRXV/action/replication_record"}},"created_at":"2026-07-05T04:28:54.395591+00:00","updated_at":"2026-07-05T04:28:54.395591+00:00"}