{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JD46EQFDHAPDBL3GTBIGPRQIUC","short_pith_number":"pith:JD46EQFD","schema_version":"1.0","canonical_sha256":"48f9e240a3381e30af66985067c608a095f4fd1344c757da86fccf7c0450e076","source":{"kind":"arxiv","id":"2310.05715","version":2},"attestation_state":"computed","paper":{"title":"A simple linear algebra identity to optimize Large-Scale Neural Network Quantum States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"cond-mat.str-el","authors_text":"Federico Becca, Lorenzo Bardone, Luciano Loris Viteritti, Riccardo Rende, Sebastian Goldt","submitted_at":"2023-10-09T13:38:36Z","abstract_excerpt":"Neural-network architectures have been increasingly used to represent quantum many-body wave functions. These networks require a large number of variational parameters and are challenging to optimize using traditional methods, as gradient descent. Stochastic Reconfiguration (SR) has been effective with a limited number of parameters, but becomes impractical beyond a few thousand parameters. Here, we leverage a simple linear algebra identity to show that SR can be employed even in the deep learning scenario. We demonstrate the effectiveness of our method by optimizing a Deep Transformer archite"},"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":"2310.05715","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.str-el","submitted_at":"2023-10-09T13:38:36Z","cross_cats_sorted":["cond-mat.dis-nn"],"title_canon_sha256":"fe6acbc89379e93002d1df445208c3257a5f4ad42bf08dc71636314dbad1a9ca","abstract_canon_sha256":"3363ad67f3d9a92f78dce51d200f4fd66543d05f8c4e50071ea6dda84c691afe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:11.759771Z","signature_b64":"VLTEIjLMTEfj0hMainCfiDKNxhp0PuFIWmQjxKsoceutTKsZp597x3qjY2OI3epIp/PakSGwYjldV58Oy+jiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48f9e240a3381e30af66985067c608a095f4fd1344c757da86fccf7c0450e076","last_reissued_at":"2026-07-05T08:51:11.759336Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:11.759336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A simple linear algebra identity to optimize Large-Scale Neural Network Quantum States","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn"],"primary_cat":"cond-mat.str-el","authors_text":"Federico Becca, Lorenzo Bardone, Luciano Loris Viteritti, Riccardo Rende, Sebastian Goldt","submitted_at":"2023-10-09T13:38:36Z","abstract_excerpt":"Neural-network architectures have been increasingly used to represent quantum many-body wave functions. These networks require a large number of variational parameters and are challenging to optimize using traditional methods, as gradient descent. Stochastic Reconfiguration (SR) has been effective with a limited number of parameters, but becomes impractical beyond a few thousand parameters. Here, we leverage a simple linear algebra identity to show that SR can be employed even in the deep learning scenario. We demonstrate the effectiveness of our method by optimizing a Deep Transformer archite"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05715","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/2310.05715/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":"2310.05715","created_at":"2026-07-05T08:51:11.759394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.05715v2","created_at":"2026-07-05T08:51:11.759394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05715","created_at":"2026-07-05T08:51:11.759394+00:00"},{"alias_kind":"pith_short_12","alias_value":"JD46EQFDHAPD","created_at":"2026-07-05T08:51:11.759394+00:00"},{"alias_kind":"pith_short_16","alias_value":"JD46EQFDHAPDBL3G","created_at":"2026-07-05T08:51:11.759394+00:00"},{"alias_kind":"pith_short_8","alias_value":"JD46EQFD","created_at":"2026-07-05T08:51:11.759394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.04943","citing_title":"Graph-Theoretic Analysis of Phase Optimization Complexity in Variational Wave Functions for Heisenberg Antiferromagnets","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC","json":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC.json","graph_json":"https://pith.science/api/pith-number/JD46EQFDHAPDBL3GTBIGPRQIUC/graph.json","events_json":"https://pith.science/api/pith-number/JD46EQFDHAPDBL3GTBIGPRQIUC/events.json","paper":"https://pith.science/paper/JD46EQFD"},"agent_actions":{"view_html":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC","download_json":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC.json","view_paper":"https://pith.science/paper/JD46EQFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.05715&json=true","fetch_graph":"https://pith.science/api/pith-number/JD46EQFDHAPDBL3GTBIGPRQIUC/graph.json","fetch_events":"https://pith.science/api/pith-number/JD46EQFDHAPDBL3GTBIGPRQIUC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC/action/storage_attestation","attest_author":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC/action/author_attestation","sign_citation":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC/action/citation_signature","submit_replication":"https://pith.science/pith/JD46EQFDHAPDBL3GTBIGPRQIUC/action/replication_record"}},"created_at":"2026-07-05T08:51:11.759394+00:00","updated_at":"2026-07-05T08:51:11.759394+00:00"}