{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:UQ3632TEETXF7CY3TM26DSZR6R","short_pith_number":"pith:UQ3632TE","schema_version":"1.0","canonical_sha256":"a437edea6424ee5f8b1b9b35e1cb31f46ad7693a1c6a3b7a53ed9a7358aea0ae","source":{"kind":"arxiv","id":"2012.12901","version":2},"attestation_state":"computed","paper":{"title":"Lattice gauge equivariant convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ph","hep-th","stat.ML"],"primary_cat":"hep-lat","authors_text":"Andreas Ipp, Daniel Schuh, David I. M\\\"uller, Matteo Favoni","submitted_at":"2020-12-23T19:00:01Z","abstract_excerpt":"We propose Lattice gauge equivariant Convolutional Neural Networks (L-CNNs) for generic machine learning applications on lattice gauge theoretical problems. At the heart of this network structure is a novel convolutional layer that preserves gauge equivariance while forming arbitrarily shaped Wilson loops in successive bilinear layers. Together with topological information, for example from Polyakov loops, such a network can in principle approximate any gauge covariant function on the lattice. We demonstrate that L-CNNs can learn and generalize gauge invariant quantities that traditional convo"},"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":"2012.12901","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-lat","submitted_at":"2020-12-23T19:00:01Z","cross_cats_sorted":["cs.LG","hep-ph","hep-th","stat.ML"],"title_canon_sha256":"a5a46f871b009ee1f7792780bd289d2d8b4fe7cec5582b0b38d4461a89a44ad8","abstract_canon_sha256":"15d97d6766860c9259d8b42407ac9f85d9b2aabaf7965e3d272537e07bbaba53"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:33.197760Z","signature_b64":"PQh94zrb5K83sz7vLWrjZ1NpFZfqH13rtNq6VxnWxT6ki04G/ppRPiRPKbmFsp0q56iUwtLDDyCrd03Aox8zBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a437edea6424ee5f8b1b9b35e1cb31f46ad7693a1c6a3b7a53ed9a7358aea0ae","last_reissued_at":"2026-07-05T03:58:33.197272Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:33.197272Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lattice gauge equivariant convolutional neural networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ph","hep-th","stat.ML"],"primary_cat":"hep-lat","authors_text":"Andreas Ipp, Daniel Schuh, David I. M\\\"uller, Matteo Favoni","submitted_at":"2020-12-23T19:00:01Z","abstract_excerpt":"We propose Lattice gauge equivariant Convolutional Neural Networks (L-CNNs) for generic machine learning applications on lattice gauge theoretical problems. At the heart of this network structure is a novel convolutional layer that preserves gauge equivariance while forming arbitrarily shaped Wilson loops in successive bilinear layers. Together with topological information, for example from Polyakov loops, such a network can in principle approximate any gauge covariant function on the lattice. We demonstrate that L-CNNs can learn and generalize gauge invariant quantities that traditional convo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.12901","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/2012.12901/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":"2012.12901","created_at":"2026-07-05T03:58:33.197339+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.12901v2","created_at":"2026-07-05T03:58:33.197339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.12901","created_at":"2026-07-05T03:58:33.197339+00:00"},{"alias_kind":"pith_short_12","alias_value":"UQ3632TEETXF","created_at":"2026-07-05T03:58:33.197339+00:00"},{"alias_kind":"pith_short_16","alias_value":"UQ3632TEETXF7CY3","created_at":"2026-07-05T03:58:33.197339+00:00"},{"alias_kind":"pith_short_8","alias_value":"UQ3632TE","created_at":"2026-07-05T03:58:33.197339+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31492","citing_title":"Higher-order hopping-parameter expansion by human-AI collaboration","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29109","citing_title":"First steps towards gauge-independent vortex identification through machine learning","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2510.25704","citing_title":"Scaling flow-based approaches for topology sampling in $\\mathrm{SU}(3)$ gauge theory","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2602.02436","citing_title":"Wilson loops with neural networks","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06134","citing_title":"Diffusion model for SU(N) gauge theories","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07226","citing_title":"Neural network interpolators for Wilson loops","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12416","citing_title":"Machine learning for four-dimensional SU(3) lattice gauge theories","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R","json":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R.json","graph_json":"https://pith.science/api/pith-number/UQ3632TEETXF7CY3TM26DSZR6R/graph.json","events_json":"https://pith.science/api/pith-number/UQ3632TEETXF7CY3TM26DSZR6R/events.json","paper":"https://pith.science/paper/UQ3632TE"},"agent_actions":{"view_html":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R","download_json":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R.json","view_paper":"https://pith.science/paper/UQ3632TE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.12901&json=true","fetch_graph":"https://pith.science/api/pith-number/UQ3632TEETXF7CY3TM26DSZR6R/graph.json","fetch_events":"https://pith.science/api/pith-number/UQ3632TEETXF7CY3TM26DSZR6R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R/action/storage_attestation","attest_author":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R/action/author_attestation","sign_citation":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R/action/citation_signature","submit_replication":"https://pith.science/pith/UQ3632TEETXF7CY3TM26DSZR6R/action/replication_record"}},"created_at":"2026-07-05T03:58:33.197339+00:00","updated_at":"2026-07-05T03:58:33.197339+00:00"}