{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:DX2TFTK2NMI5K6HCNU5MVXPXKG","short_pith_number":"pith:DX2TFTK2","schema_version":"1.0","canonical_sha256":"1df532cd5a6b11d578e26d3acaddf7518513ea6294cb8909fa1e20dabdd09cf2","source":{"kind":"arxiv","id":"2204.02782","version":3},"attestation_state":"computed","paper":{"title":"GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.chem-ph","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Anuroop Sriram, C. Lawrence Zitnick, Johannes Gasteiger, Muhammed Shuaibi, Stephan G\\\"unnemann, Zachary Ulissi","submitted_at":"2022-04-06T12:52:34Z","abstract_excerpt":"Recent years have seen the advent of molecular simulation datasets that are orders of magnitude larger and more diverse. These new datasets differ substantially in four aspects of complexity: 1. Chemical diversity (number of different elements), 2. system size (number of atoms per sample), 3. dataset size (number of data samples), and 4. domain shift (similarity of the training and test set). Despite these large differences, benchmarks on small and narrow datasets remain the predominant method of demonstrating progress in graph neural networks (GNNs) for molecular simulation, likely due to che"},"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":"2204.02782","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-06T12:52:34Z","cross_cats_sorted":["cond-mat.mtrl-sci","physics.chem-ph","physics.comp-ph"],"title_canon_sha256":"3472cb7563f6c22112b1a344da04f83b387e8796075b22318bc519efb39cde6b","abstract_canon_sha256":"654f842eb603c7e828a3d733deba876fb633ee6fa09d349d0114f3eac64873d2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:11.371385Z","signature_b64":"yftc2Y26MRqBCggy3cOvT2jjIobioqkL8vYnFPKA2blZ/7oVatEUzh0lU9uQTv1u3dWngetsEFMDBeuzXYHOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1df532cd5a6b11d578e26d3acaddf7518513ea6294cb8909fa1e20dabdd09cf2","last_reissued_at":"2026-07-05T05:02:11.370853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:11.370853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GemNet-OC: Developing Graph Neural Networks for Large and Diverse Molecular Simulation Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.chem-ph","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Anuroop Sriram, C. Lawrence Zitnick, Johannes Gasteiger, Muhammed Shuaibi, Stephan G\\\"unnemann, Zachary Ulissi","submitted_at":"2022-04-06T12:52:34Z","abstract_excerpt":"Recent years have seen the advent of molecular simulation datasets that are orders of magnitude larger and more diverse. These new datasets differ substantially in four aspects of complexity: 1. Chemical diversity (number of different elements), 2. system size (number of atoms per sample), 3. dataset size (number of data samples), and 4. domain shift (similarity of the training and test set). Despite these large differences, benchmarks on small and narrow datasets remain the predominant method of demonstrating progress in graph neural networks (GNNs) for molecular simulation, likely due to che"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.02782","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/2204.02782/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":"2204.02782","created_at":"2026-07-05T05:02:11.370920+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.02782v3","created_at":"2026-07-05T05:02:11.370920+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.02782","created_at":"2026-07-05T05:02:11.370920+00:00"},{"alias_kind":"pith_short_12","alias_value":"DX2TFTK2NMI5","created_at":"2026-07-05T05:02:11.370920+00:00"},{"alias_kind":"pith_short_16","alias_value":"DX2TFTK2NMI5K6HC","created_at":"2026-07-05T05:02:11.370920+00:00"},{"alias_kind":"pith_short_8","alias_value":"DX2TFTK2","created_at":"2026-07-05T05:02:11.370920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24983","citing_title":"ConSolv: Solvent-Conditional Machine Learning Implicit Solvent Potential","ref_index":236,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02419","citing_title":"DPA4: Pushing the Accuracy-Cost Frontier of Interatomic Potentials with EMFA SO(2) Convolution","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14154","citing_title":"TSAgent: An Agentic Workflow for Autonomous Transition State Search","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08988","citing_title":"Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07714","citing_title":"Selectivity- and Activity-Aware Catalyst Descriptors for CO$_2$ Hydrogenation on Alloy Nanocatalysts using Machine-Learned Force Fields","ref_index":108,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG","json":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG.json","graph_json":"https://pith.science/api/pith-number/DX2TFTK2NMI5K6HCNU5MVXPXKG/graph.json","events_json":"https://pith.science/api/pith-number/DX2TFTK2NMI5K6HCNU5MVXPXKG/events.json","paper":"https://pith.science/paper/DX2TFTK2"},"agent_actions":{"view_html":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG","download_json":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG.json","view_paper":"https://pith.science/paper/DX2TFTK2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.02782&json=true","fetch_graph":"https://pith.science/api/pith-number/DX2TFTK2NMI5K6HCNU5MVXPXKG/graph.json","fetch_events":"https://pith.science/api/pith-number/DX2TFTK2NMI5K6HCNU5MVXPXKG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG/action/storage_attestation","attest_author":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG/action/author_attestation","sign_citation":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG/action/citation_signature","submit_replication":"https://pith.science/pith/DX2TFTK2NMI5K6HCNU5MVXPXKG/action/replication_record"}},"created_at":"2026-07-05T05:02:11.370920+00:00","updated_at":"2026-07-05T05:02:11.370920+00:00"}