{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:DPDJZBC7EEMLGFWYALVY47AS3O","short_pith_number":"pith:DPDJZBC7","schema_version":"1.0","canonical_sha256":"1bc69c845f2118b316d802eb8e7c12db95f5a67b512428ee1917731cf2d6e71e","source":{"kind":"arxiv","id":"2106.03843","version":2},"attestation_state":"computed","paper":{"title":"Equivariant Graph Neural Networks for 3D Macromolecular Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bowen Jing, Pratham N. Soni, Ron O. Dror, Stephan Eismann","submitted_at":"2021-06-07T17:57:04Z","abstract_excerpt":"Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide range of tasks from structural biology. Our method outperforms all reference architectures on three out of eight tasks in the ATOM3D benchmark, is tied for first on two others, and is competitive with equivariant networks using higher-order representations and spherical harmonic convolutions. In addition, we demonstrate that transfer learning can further improve"},"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":"2106.03843","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T17:57:04Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"6f88a5c1a06a4c4313bb72adc3e34e74b16945aed2ab09536a760ef5ac26cb1e","abstract_canon_sha256":"fd348f2daf830931d602ccf89152621113cd87af0c7f39a07ec14f2d5010e9ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:57:22.840098Z","signature_b64":"Wbe8R4FmoO0IdQnv2xbP2yyaATPED7JQFketDAkmp/2n9/12Am8JFRhV1/ZW+0V6rMBhpZG6ZYhbTPetoaleBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bc69c845f2118b316d802eb8e7c12db95f5a67b512428ee1917731cf2d6e71e","last_reissued_at":"2026-07-05T02:57:22.839622Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:57:22.839622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equivariant Graph Neural Networks for 3D Macromolecular Structure","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Bowen Jing, Pratham N. Soni, Ron O. Dror, Stephan Eismann","submitted_at":"2021-06-07T17:57:04Z","abstract_excerpt":"Representing and reasoning about 3D structures of macromolecules is emerging as a distinct challenge in machine learning. Here, we extend recent work on geometric vector perceptrons and apply equivariant graph neural networks to a wide range of tasks from structural biology. Our method outperforms all reference architectures on three out of eight tasks in the ATOM3D benchmark, is tied for first on two others, and is competitive with equivariant networks using higher-order representations and spherical harmonic convolutions. In addition, we demonstrate that transfer learning can further improve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03843","kind":"arxiv","version":2},"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/2106.03843/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":"2106.03843","created_at":"2026-07-05T02:57:22.839681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03843v2","created_at":"2026-07-05T02:57:22.839681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03843","created_at":"2026-07-05T02:57:22.839681+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPDJZBC7EEML","created_at":"2026-07-05T02:57:22.839681+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPDJZBC7EEMLGFWY","created_at":"2026-07-05T02:57:22.839681+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPDJZBC7","created_at":"2026-07-05T02:57:22.839681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.15495","citing_title":"Contrastive learning of dynamical representations for enhanced molecular sampling","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11243","citing_title":"ProHiFlo: Hierarchical Flow Matching with Functional Guidance for De Novo Protein Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31498","citing_title":"Scalable Inference-Time Annealing with Surrogate Likelihood Estimators","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2410.19471","citing_title":"Improving Inverse Folding for Peptide Design with Diversity-regularized Direct Preference Optimization","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23134","citing_title":"h-MINT: Modeling Pocket-Ligand Binding with Hierarchical Molecular Interaction Network","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O","json":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O.json","graph_json":"https://pith.science/api/pith-number/DPDJZBC7EEMLGFWYALVY47AS3O/graph.json","events_json":"https://pith.science/api/pith-number/DPDJZBC7EEMLGFWYALVY47AS3O/events.json","paper":"https://pith.science/paper/DPDJZBC7"},"agent_actions":{"view_html":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O","download_json":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O.json","view_paper":"https://pith.science/paper/DPDJZBC7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03843&json=true","fetch_graph":"https://pith.science/api/pith-number/DPDJZBC7EEMLGFWYALVY47AS3O/graph.json","fetch_events":"https://pith.science/api/pith-number/DPDJZBC7EEMLGFWYALVY47AS3O/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O/action/storage_attestation","attest_author":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O/action/author_attestation","sign_citation":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O/action/citation_signature","submit_replication":"https://pith.science/pith/DPDJZBC7EEMLGFWYALVY47AS3O/action/replication_record"}},"created_at":"2026-07-05T02:57:22.839681+00:00","updated_at":"2026-07-05T02:57:22.839681+00:00"}