{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HCAQQIW7KKCX25GIDVEIXQCJTD","short_pith_number":"pith:HCAQQIW7","schema_version":"1.0","canonical_sha256":"38810822df52857d74c81d488bc04998fd61e78c6c22c9e36101876734a91462","source":{"kind":"arxiv","id":"2203.06442","version":1},"attestation_state":"computed","paper":{"title":"Equivariant Graph Mechanics Networks with Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fuchun Sun, Jiaqi Han, Junzhou Huang, Tingyang Xu, Wenbing Huang, Yu Rong","submitted_at":"2022-03-12T14:22:14Z","abstract_excerpt":"Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and commonly geometrically-constrained. Current methods, particularly the ones based on equivariant Graph Neural Networks (GNNs), have targeted on the first two challenges but remain immature for constrained systems. In this paper, we propose Graph Mechanics Network (GMN) which is combinatorially efficient, equivariant and constraint-aware. The core of GMN is that "},"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":"2203.06442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T14:22:14Z","cross_cats_sorted":[],"title_canon_sha256":"725f362c739a6fc8faca6553dc04b46af3087d65faa6811e3df1992c0c992db1","abstract_canon_sha256":"ef7ee607256b9f1925743c9cb84e3536d58117bb424797b0030799bb560cfa59"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:50.802860Z","signature_b64":"nN2+CMe1rvs6ki3MlsR/paqx6+5cvIElvZwwEskR+CkRTAMVjRT75oFSSwLU4/EtIom7NpQg3DOJMam3m4ONAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38810822df52857d74c81d488bc04998fd61e78c6c22c9e36101876734a91462","last_reissued_at":"2026-07-05T04:04:50.802335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:50.802335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Graph Mechanics Networks with Constraints","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fuchun Sun, Jiaqi Han, Junzhou Huang, Tingyang Xu, Wenbing Huang, Yu Rong","submitted_at":"2022-03-12T14:22:14Z","abstract_excerpt":"Learning to reason about relations and dynamics over multiple interacting objects is a challenging topic in machine learning. The challenges mainly stem from that the interacting systems are exponentially-compositional, symmetrical, and commonly geometrically-constrained. Current methods, particularly the ones based on equivariant Graph Neural Networks (GNNs), have targeted on the first two challenges but remain immature for constrained systems. In this paper, we propose Graph Mechanics Network (GMN) which is combinatorially efficient, equivariant and constraint-aware. The core of GMN is that "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06442","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/2203.06442/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":"2203.06442","created_at":"2026-07-05T04:04:50.802410+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06442v1","created_at":"2026-07-05T04:04:50.802410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06442","created_at":"2026-07-05T04:04:50.802410+00:00"},{"alias_kind":"pith_short_12","alias_value":"HCAQQIW7KKCX","created_at":"2026-07-05T04:04:50.802410+00:00"},{"alias_kind":"pith_short_16","alias_value":"HCAQQIW7KKCX25GI","created_at":"2026-07-05T04:04:50.802410+00:00"},{"alias_kind":"pith_short_8","alias_value":"HCAQQIW7","created_at":"2026-07-05T04:04:50.802410+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.04233","citing_title":"PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10723","citing_title":"Generalized Spherical Neural Operators: Green's Function Formulation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19806","citing_title":"Improving Molecular Force Fields with Minimal Temporal Information","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD","json":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD.json","graph_json":"https://pith.science/api/pith-number/HCAQQIW7KKCX25GIDVEIXQCJTD/graph.json","events_json":"https://pith.science/api/pith-number/HCAQQIW7KKCX25GIDVEIXQCJTD/events.json","paper":"https://pith.science/paper/HCAQQIW7"},"agent_actions":{"view_html":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD","download_json":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD.json","view_paper":"https://pith.science/paper/HCAQQIW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06442&json=true","fetch_graph":"https://pith.science/api/pith-number/HCAQQIW7KKCX25GIDVEIXQCJTD/graph.json","fetch_events":"https://pith.science/api/pith-number/HCAQQIW7KKCX25GIDVEIXQCJTD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD/action/storage_attestation","attest_author":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD/action/author_attestation","sign_citation":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD/action/citation_signature","submit_replication":"https://pith.science/pith/HCAQQIW7KKCX25GIDVEIXQCJTD/action/replication_record"}},"created_at":"2026-07-05T04:04:50.802410+00:00","updated_at":"2026-07-05T04:04:50.802410+00:00"}