{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:YGRCJWNT5RJVPEKAGO54UFPNR4","short_pith_number":"pith:YGRCJWNT","schema_version":"1.0","canonical_sha256":"c1a224d9b3ec5357914033bbca15ed8f2b436065685286409dbddf5369e01975","source":{"kind":"arxiv","id":"2011.11307","version":2},"attestation_state":"computed","paper":{"title":"Restricted Boltzmann Machine, recent advances and mean-field theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Aur\\'elien Decelle, Cyril FURTLEHNER","submitted_at":"2020-11-23T10:08:53Z","abstract_excerpt":"This review deals with Restricted Boltzmann Machine (RBM) under the light of statistical physics. The RBM is a classical family of Machine learning (ML) models which played a central role in the development of deep learning. Viewing it as a Spin Glass model and exhibiting various links with other models of statistical physics, we gather recent results dealing with mean-field theory in this context. First the functioning of the RBM can be analyzed via the phase diagrams obtained for various statistical ensembles of RBM leading in particular to identify a {\\it compositional phase} where a small "},"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":"2011.11307","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2020-11-23T10:08:53Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG"],"title_canon_sha256":"4edb19e188d516efea1b7882242b25c615616a91f47b6c93ff01da937164d180","abstract_canon_sha256":"e5ca4013292066f98fdbb71e7d1e1a08ef27ffc11a16c61cf5b6c4e30d15bad0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:30:41.113227Z","signature_b64":"vSqpZgI7gLqLtFSYEmmTH0vL5+l202/aF9llUilTNm37sInnWr5vAhn3/M6ndYkQMwrxXd3BzEbKeacaLsTgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1a224d9b3ec5357914033bbca15ed8f2b436065685286409dbddf5369e01975","last_reissued_at":"2026-07-05T06:30:41.112800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:30:41.112800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Restricted Boltzmann Machine, recent advances and mean-field theory","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG"],"primary_cat":"cond-mat.dis-nn","authors_text":"Aur\\'elien Decelle, Cyril FURTLEHNER","submitted_at":"2020-11-23T10:08:53Z","abstract_excerpt":"This review deals with Restricted Boltzmann Machine (RBM) under the light of statistical physics. The RBM is a classical family of Machine learning (ML) models which played a central role in the development of deep learning. Viewing it as a Spin Glass model and exhibiting various links with other models of statistical physics, we gather recent results dealing with mean-field theory in this context. First the functioning of the RBM can be analyzed via the phase diagrams obtained for various statistical ensembles of RBM leading in particular to identify a {\\it compositional phase} where a small "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.11307","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/2011.11307/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":"2011.11307","created_at":"2026-07-05T06:30:41.112855+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.11307v2","created_at":"2026-07-05T06:30:41.112855+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.11307","created_at":"2026-07-05T06:30:41.112855+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGRCJWNT5RJV","created_at":"2026-07-05T06:30:41.112855+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGRCJWNT5RJVPEKA","created_at":"2026-07-05T06:30:41.112855+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGRCJWNT","created_at":"2026-07-05T06:30:41.112855+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.20496","citing_title":"Random Matrix Theory for Stochastic Gradient Descent","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4","json":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4.json","graph_json":"https://pith.science/api/pith-number/YGRCJWNT5RJVPEKAGO54UFPNR4/graph.json","events_json":"https://pith.science/api/pith-number/YGRCJWNT5RJVPEKAGO54UFPNR4/events.json","paper":"https://pith.science/paper/YGRCJWNT"},"agent_actions":{"view_html":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4","download_json":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4.json","view_paper":"https://pith.science/paper/YGRCJWNT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.11307&json=true","fetch_graph":"https://pith.science/api/pith-number/YGRCJWNT5RJVPEKAGO54UFPNR4/graph.json","fetch_events":"https://pith.science/api/pith-number/YGRCJWNT5RJVPEKAGO54UFPNR4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4/action/storage_attestation","attest_author":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4/action/author_attestation","sign_citation":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4/action/citation_signature","submit_replication":"https://pith.science/pith/YGRCJWNT5RJVPEKAGO54UFPNR4/action/replication_record"}},"created_at":"2026-07-05T06:30:41.112855+00:00","updated_at":"2026-07-05T06:30:41.112855+00:00"}