{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:DSXJPTXOLDY4RQHU54XU4PLNAH","short_pith_number":"pith:DSXJPTXO","schema_version":"1.0","canonical_sha256":"1cae97ceee58f1c8c0f4ef2f4e3d6d01c51ee631cdb27816441159a2543cb410","source":{"kind":"arxiv","id":"2008.08461","version":4},"attestation_state":"computed","paper":{"title":"Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Kurt Miller, Frank No\\'e, Mario Geiger, Tess E. Smidt","submitted_at":"2020-08-19T14:07:36Z","abstract_excerpt":"Equivariant neural networks (ENNs) are graph neural networks embedded in $\\mathbb{R}^3$ and are well suited for predicting molecular properties. The ENN library e3nn has customizable convolutions, which can be designed to depend only on distances between points, or also on angular features, making them rotationally invariant, or equivariant, respectively. This paper studies the practical value of including angular dependencies for molecular property prediction directly via an ablation study with \\texttt{e3nn} and the QM9 data set. We find that, for fixed network depth and parameter count, addi"},"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":"2008.08461","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-19T14:07:36Z","cross_cats_sorted":["physics.chem-ph","physics.comp-ph","stat.ML"],"title_canon_sha256":"ccd66ac1d8e0acbfdc1beff0814b19214650173b3cabcba3fca11cfb8eb4573d","abstract_canon_sha256":"fda70f852c28459ff8b7ece4693b44e673ba3df3e1dd121dfb5ba6e02056961b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:53:55.446002Z","signature_b64":"W/em2A20NE4W2hhJ1jCocMdZq4Vwv3GpI2ltmnuip+KlK2Y0w8yIsDVurObM/oNkdCCIqfHnG132LHoVGjb2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cae97ceee58f1c8c0f4ef2f4e3d6d01c51ee631cdb27816441159a2543cb410","last_reissued_at":"2026-07-05T01:53:55.445515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:53:55.445515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.chem-ph","physics.comp-ph","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Kurt Miller, Frank No\\'e, Mario Geiger, Tess E. Smidt","submitted_at":"2020-08-19T14:07:36Z","abstract_excerpt":"Equivariant neural networks (ENNs) are graph neural networks embedded in $\\mathbb{R}^3$ and are well suited for predicting molecular properties. The ENN library e3nn has customizable convolutions, which can be designed to depend only on distances between points, or also on angular features, making them rotationally invariant, or equivariant, respectively. This paper studies the practical value of including angular dependencies for molecular property prediction directly via an ablation study with \\texttt{e3nn} and the QM9 data set. We find that, for fixed network depth and parameter count, addi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.08461","kind":"arxiv","version":4},"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/2008.08461/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":"2008.08461","created_at":"2026-07-05T01:53:55.445574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.08461v4","created_at":"2026-07-05T01:53:55.445574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.08461","created_at":"2026-07-05T01:53:55.445574+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSXJPTXOLDY4","created_at":"2026-07-05T01:53:55.445574+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSXJPTXOLDY4RQHU","created_at":"2026-07-05T01:53:55.445574+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSXJPTXO","created_at":"2026-07-05T01:53:55.445574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05218","citing_title":"A 3D Machine Learning based Volume Of Fluid scheme without explicit interface reconstruction","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH","json":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH.json","graph_json":"https://pith.science/api/pith-number/DSXJPTXOLDY4RQHU54XU4PLNAH/graph.json","events_json":"https://pith.science/api/pith-number/DSXJPTXOLDY4RQHU54XU4PLNAH/events.json","paper":"https://pith.science/paper/DSXJPTXO"},"agent_actions":{"view_html":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH","download_json":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH.json","view_paper":"https://pith.science/paper/DSXJPTXO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.08461&json=true","fetch_graph":"https://pith.science/api/pith-number/DSXJPTXOLDY4RQHU54XU4PLNAH/graph.json","fetch_events":"https://pith.science/api/pith-number/DSXJPTXOLDY4RQHU54XU4PLNAH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH/action/storage_attestation","attest_author":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH/action/author_attestation","sign_citation":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH/action/citation_signature","submit_replication":"https://pith.science/pith/DSXJPTXOLDY4RQHU54XU4PLNAH/action/replication_record"}},"created_at":"2026-07-05T01:53:55.445574+00:00","updated_at":"2026-07-05T01:53:55.445574+00:00"}