{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UYPAE5VEGM6BR4TCM2AYWDBU2L","short_pith_number":"pith:UYPAE5VE","schema_version":"1.0","canonical_sha256":"a61e0276a4333c18f26266818b0c34d2c76cb24d9d99ebf4de84d96e6dace5f3","source":{"kind":"arxiv","id":"2309.09240","version":2},"attestation_state":"computed","paper":{"title":"High-dimensional manifold of solutions in neural networks: insights from statistical physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","math.ST","stat.TH"],"primary_cat":"cond-mat.dis-nn","authors_text":"Enrico M. Malatesta","submitted_at":"2023-09-17T11:10:25Z","abstract_excerpt":"In these pedagogic notes I review the statistical mechanics approach to neural networks, focusing on the paradigmatic example of the perceptron architecture with binary an continuous weights, in the classification setting. I will review the Gardner's approach based on replica method and the derivation of the SAT/UNSAT transition in the storage setting. Then, I discuss some recent works that unveiled how the zero training error configurations are geometrically arranged, and how this arrangement changes as the size of the training set increases. I also illustrate how different regions of solutio"},"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":"2309.09240","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2023-09-17T11:10:25Z","cross_cats_sorted":["cs.LG","math.PR","math.ST","stat.TH"],"title_canon_sha256":"f43107c28f50e97f8b6a0e4e2a94a92cafbc1fbb1abb57cdcc3c821d76a6ae8b","abstract_canon_sha256":"3c75627e06e28833e9bcfe6d94b41f3477ba98cca4d7b873cb4475c69f96a481"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:31.814346Z","signature_b64":"HHobnioJfKYsA6X3eMguIZH1OX63B9IBmqFMp/U+EZSB0qq9iqvswN6GCccRn9DFYzTY2tBdojI0OCmjPz7sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a61e0276a4333c18f26266818b0c34d2c76cb24d9d99ebf4de84d96e6dace5f3","last_reissued_at":"2026-07-05T10:16:31.813784Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:31.813784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-dimensional manifold of solutions in neural networks: insights from statistical physics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.PR","math.ST","stat.TH"],"primary_cat":"cond-mat.dis-nn","authors_text":"Enrico M. Malatesta","submitted_at":"2023-09-17T11:10:25Z","abstract_excerpt":"In these pedagogic notes I review the statistical mechanics approach to neural networks, focusing on the paradigmatic example of the perceptron architecture with binary an continuous weights, in the classification setting. I will review the Gardner's approach based on replica method and the derivation of the SAT/UNSAT transition in the storage setting. Then, I discuss some recent works that unveiled how the zero training error configurations are geometrically arranged, and how this arrangement changes as the size of the training set increases. I also illustrate how different regions of solutio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.09240","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/2309.09240/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":"2309.09240","created_at":"2026-07-05T10:16:31.813841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.09240v2","created_at":"2026-07-05T10:16:31.813841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.09240","created_at":"2026-07-05T10:16:31.813841+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYPAE5VEGM6B","created_at":"2026-07-05T10:16:31.813841+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYPAE5VEGM6BR4TC","created_at":"2026-07-05T10:16:31.813841+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYPAE5VE","created_at":"2026-07-05T10:16:31.813841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.04390","citing_title":"Shortcomings and capacities of real-constrained neural networks in complex spaces","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01028","citing_title":"Pseudo quantum advantages in perceptron storage capacity","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L","json":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L.json","graph_json":"https://pith.science/api/pith-number/UYPAE5VEGM6BR4TCM2AYWDBU2L/graph.json","events_json":"https://pith.science/api/pith-number/UYPAE5VEGM6BR4TCM2AYWDBU2L/events.json","paper":"https://pith.science/paper/UYPAE5VE"},"agent_actions":{"view_html":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L","download_json":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L.json","view_paper":"https://pith.science/paper/UYPAE5VE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.09240&json=true","fetch_graph":"https://pith.science/api/pith-number/UYPAE5VEGM6BR4TCM2AYWDBU2L/graph.json","fetch_events":"https://pith.science/api/pith-number/UYPAE5VEGM6BR4TCM2AYWDBU2L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L/action/storage_attestation","attest_author":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L/action/author_attestation","sign_citation":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L/action/citation_signature","submit_replication":"https://pith.science/pith/UYPAE5VEGM6BR4TCM2AYWDBU2L/action/replication_record"}},"created_at":"2026-07-05T10:16:31.813841+00:00","updated_at":"2026-07-05T10:16:31.813841+00:00"}