{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GCETK23F3WFQYWI7FON7TSHL6E","short_pith_number":"pith:GCETK23F","schema_version":"1.0","canonical_sha256":"3089356b65dd8b0c591f2b9bf9c8ebf1131a284287a0dee9d140f735c2a21377","source":{"kind":"arxiv","id":"2306.12059","version":3},"attestation_state":"computed","paper":{"title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Brandon Wood, Tess Smidt, Yi-Lun Liao","submitted_at":"2023-06-21T07:01:38Z","abstract_excerpt":"Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying Transformers to the domain of 3D atomistic systems. However, they are limited to small degrees of equivariant representations due to their computational complexity. In this paper, we investigate whether these architectures can scale well to higher degrees. Starting from Equiformer, we first replace $SO(3)$ convolutions with eSCN convolutions to efficiently incorporate higher-degree tensors. Then, to better leverage the power of higher degrees, we propose three architectural improvements -- attention re-norma"},"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":"2306.12059","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-21T07:01:38Z","cross_cats_sorted":["cs.AI","physics.comp-ph"],"title_canon_sha256":"1f0127396421ff9c2ef86d3e62cea2f0f1c234dfea2169ac3a8cd305efefb4d2","abstract_canon_sha256":"0f3317fcb5d3a6249c7b7858e983fe0fb28a07639d801a3b17bf58e6c9e14f0f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:08.826475Z","signature_b64":"Sc9A65PSKqoLArhfDC5PA2xE4AuBiRXZsg3VFdPTQsGK7sL1V9tOp7EiDyVL5pxZOl/YIGA0UETZTe/Lf7ctAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3089356b65dd8b0c591f2b9bf9c8ebf1131a284287a0dee9d140f735c2a21377","last_reissued_at":"2026-07-05T07:53:08.825945Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:08.825945Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","physics.comp-ph"],"primary_cat":"cs.LG","authors_text":"Abhishek Das, Brandon Wood, Tess Smidt, Yi-Lun Liao","submitted_at":"2023-06-21T07:01:38Z","abstract_excerpt":"Equivariant Transformers such as Equiformer have demonstrated the efficacy of applying Transformers to the domain of 3D atomistic systems. However, they are limited to small degrees of equivariant representations due to their computational complexity. In this paper, we investigate whether these architectures can scale well to higher degrees. Starting from Equiformer, we first replace $SO(3)$ convolutions with eSCN convolutions to efficiently incorporate higher-degree tensors. Then, to better leverage the power of higher degrees, we propose three architectural improvements -- attention re-norma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12059","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/2306.12059/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":"2306.12059","created_at":"2026-07-05T07:53:08.826013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.12059v3","created_at":"2026-07-05T07:53:08.826013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12059","created_at":"2026-07-05T07:53:08.826013+00:00"},{"alias_kind":"pith_short_12","alias_value":"GCETK23F3WFQ","created_at":"2026-07-05T07:53:08.826013+00:00"},{"alias_kind":"pith_short_16","alias_value":"GCETK23F3WFQYWI7","created_at":"2026-07-05T07:53:08.826013+00:00"},{"alias_kind":"pith_short_8","alias_value":"GCETK23F","created_at":"2026-07-05T07:53:08.826013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25318","citing_title":"REViT: Roto-reflection Equivariant Convolutional Vision Transformer","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17445","citing_title":"Toward Controllable Catalyst Inverse Design via Large-Scale Autoregressive Pretraining","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07327","citing_title":"Six Open Questions in Machine-Learned Interatomic Potential Foundation Models","ref_index":144,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04154","citing_title":"EpiFormer: Learning Antigen-Antibody Interactions for Epitope Prediction via Geometric Deep Learning","ref_index":218,"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":199,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17254","citing_title":"CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29919","citing_title":"High-order tensor neural network for iteration-free structure relaxation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30220","citing_title":"TriSearch: Learning to Optimize Triangulations via Bistellar Flips","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2410.18151","citing_title":"Music102: An $D_{12}$-equivariant transformer for chord progression accompaniment","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12771","citing_title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17254","citing_title":"CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16214","citing_title":"Bridging Atomistic Simulation and Experimental Processing Timescales with Goal-Directed Deep Reinforcement Learning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17254","citing_title":"CatalyticMLLM: A Graph-Text Multimodal Large Language Model for Catalytic Materials","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2507.18847","citing_title":"Equivariant Volumetric Grasping","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03046","citing_title":"Bayesian E(3)-Equivariant Interatomic Potential with Iterative Restratification of Many-body Message Passing","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12771","citing_title":"Open Materials 2024 (OMat24) Inorganic Materials Dataset and Models","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10791","citing_title":"OmniMol: Transferring Particle Physics Knowledge to Molecular Dynamics with Point-Edge Transformers","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2602.17709","citing_title":"UBio-MolFM: A Universal Molecular Foundation Model for Bio-Systems","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15073","citing_title":"Fast contracted Clebsch--Gordan tensor products for equivariant graph neural networks","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14154","citing_title":"TSAgent: An Agentic Workflow for Autonomous Transition State Search","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21942","citing_title":"Suiren-1.0 Technical Report: A Family of Molecular Foundation Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2603.25980","citing_title":"A Priori Sampling of Transition States with Guided Diffusion","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2604.01642","citing_title":"Benchmarking Chemically Scalable Machine-Learning Interatomic Potentials for Large-Scale Simulations of Multicomponent Alloys","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08988","citing_title":"Benchmarking Compositional Generalisation for Machine Learning Interatomic Potentials","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00640","citing_title":"Knowing when to trust machine-learned interatomic potentials","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E","json":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E.json","graph_json":"https://pith.science/api/pith-number/GCETK23F3WFQYWI7FON7TSHL6E/graph.json","events_json":"https://pith.science/api/pith-number/GCETK23F3WFQYWI7FON7TSHL6E/events.json","paper":"https://pith.science/paper/GCETK23F"},"agent_actions":{"view_html":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E","download_json":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E.json","view_paper":"https://pith.science/paper/GCETK23F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.12059&json=true","fetch_graph":"https://pith.science/api/pith-number/GCETK23F3WFQYWI7FON7TSHL6E/graph.json","fetch_events":"https://pith.science/api/pith-number/GCETK23F3WFQYWI7FON7TSHL6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E/action/storage_attestation","attest_author":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E/action/author_attestation","sign_citation":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E/action/citation_signature","submit_replication":"https://pith.science/pith/GCETK23F3WFQYWI7FON7TSHL6E/action/replication_record"}},"created_at":"2026-07-05T07:53:08.826013+00:00","updated_at":"2026-07-05T07:53:08.826013+00:00"}