{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WALG77HBNU7C4QSCUEKG3YSTG7","short_pith_number":"pith:WALG77HB","schema_version":"1.0","canonical_sha256":"b0166ffce16d3e2e4242a1146de25337f820b7d2c6626778771f94e1f73f5340","source":{"kind":"arxiv","id":"2009.07330","version":1},"attestation_state":"computed","paper":{"title":"Training neural networks under physical constraints using a stochastic augmented Lagrangian approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","physics.plasm-ph","stat.ML"],"primary_cat":"physics.comp-ph","authors_text":"Alp Dener, Choong-Seock Chang, Marco Andres Miller, Randy Michael Churchill, Todd Munson","submitted_at":"2020-09-15T19:20:29Z","abstract_excerpt":"We investigate the physics-constrained training of an encoder-decoder neural network for approximating the Fokker-Planck-Landau collision operator in the 5-dimensional kinetic fusion simulation in XGC. To train this network, we propose a stochastic augmented Lagrangian approach that utilizes pyTorch's native stochastic gradient descent method to solve the inner unconstrained minimization subproblem, paired with a heuristic update for the penalty factor and Lagrange multipliers in the outer augmented Lagrangian loop. Our training results for a single ion species case, with self-collisions and c"},"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":"2009.07330","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.comp-ph","submitted_at":"2020-09-15T19:20:29Z","cross_cats_sorted":["cs.LG","math.OC","physics.plasm-ph","stat.ML"],"title_canon_sha256":"49598360351a2af9d5c3813b6cdc3bbe4d1b1538be7b39e185fac758a12da9b6","abstract_canon_sha256":"0a937f30d47cbd671f59ec447d3d0667557759fca98a6e8195584c7863a10492"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:35:51.169330Z","signature_b64":"osQJC//3fr2oi6rEcl1XXz5I/tSVcwNAqfPJUdmpyqN5LS29Q0RcGX7JPbA5GTXzPybyQaX0itLfZyck5u5LBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0166ffce16d3e2e4242a1146de25337f820b7d2c6626778771f94e1f73f5340","last_reissued_at":"2026-07-05T01:35:51.168866Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:35:51.168866Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training neural networks under physical constraints using a stochastic augmented Lagrangian approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC","physics.plasm-ph","stat.ML"],"primary_cat":"physics.comp-ph","authors_text":"Alp Dener, Choong-Seock Chang, Marco Andres Miller, Randy Michael Churchill, Todd Munson","submitted_at":"2020-09-15T19:20:29Z","abstract_excerpt":"We investigate the physics-constrained training of an encoder-decoder neural network for approximating the Fokker-Planck-Landau collision operator in the 5-dimensional kinetic fusion simulation in XGC. To train this network, we propose a stochastic augmented Lagrangian approach that utilizes pyTorch's native stochastic gradient descent method to solve the inner unconstrained minimization subproblem, paired with a heuristic update for the penalty factor and Lagrange multipliers in the outer augmented Lagrangian loop. Our training results for a single ion species case, with self-collisions and c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.07330","kind":"arxiv","version":1},"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/2009.07330/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":"2009.07330","created_at":"2026-07-05T01:35:51.168924+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.07330v1","created_at":"2026-07-05T01:35:51.168924+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.07330","created_at":"2026-07-05T01:35:51.168924+00:00"},{"alias_kind":"pith_short_12","alias_value":"WALG77HBNU7C","created_at":"2026-07-05T01:35:51.168924+00:00"},{"alias_kind":"pith_short_16","alias_value":"WALG77HBNU7C4QSC","created_at":"2026-07-05T01:35:51.168924+00:00"},{"alias_kind":"pith_short_8","alias_value":"WALG77HB","created_at":"2026-07-05T01:35:51.168924+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07984","citing_title":"Lagrange multipliers in Maximum likelihood estimations and Least squares problems with Constraints","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09317","citing_title":"SnareNet: Flexible Repair Layers for Neural Networks with Hard Constraints","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7","json":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7.json","graph_json":"https://pith.science/api/pith-number/WALG77HBNU7C4QSCUEKG3YSTG7/graph.json","events_json":"https://pith.science/api/pith-number/WALG77HBNU7C4QSCUEKG3YSTG7/events.json","paper":"https://pith.science/paper/WALG77HB"},"agent_actions":{"view_html":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7","download_json":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7.json","view_paper":"https://pith.science/paper/WALG77HB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.07330&json=true","fetch_graph":"https://pith.science/api/pith-number/WALG77HBNU7C4QSCUEKG3YSTG7/graph.json","fetch_events":"https://pith.science/api/pith-number/WALG77HBNU7C4QSCUEKG3YSTG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7/action/storage_attestation","attest_author":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7/action/author_attestation","sign_citation":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7/action/citation_signature","submit_replication":"https://pith.science/pith/WALG77HBNU7C4QSCUEKG3YSTG7/action/replication_record"}},"created_at":"2026-07-05T01:35:51.168924+00:00","updated_at":"2026-07-05T01:35:51.168924+00:00"}