{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X4ZLXSGAD3OL34NZH4Y4LFNQQ3","short_pith_number":"pith:X4ZLXSGA","schema_version":"1.0","canonical_sha256":"bf32bbc8c01edcbdf1b93f31c595b086ea61a5280143c147488976cb49d8fa09","source":{"kind":"arxiv","id":"2506.23546","version":2},"attestation_state":"computed","paper":{"title":"Neural Langevin Machine: a local asymmetric learning rule can be creative","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Haiping Huang, Weizhong Huang, Zhendong Yu","submitted_at":"2025-06-30T06:35:43Z","abstract_excerpt":"Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used to find them for generative learning of a real dataset. We call this type of generative model a neural Langevin machine, which derives an asymmetric and firing-rate-speed adjusted learning rule requiring only local neural signals, thereby bearing biological relevance in terms of local predictive learning. An interesting out-of-equilibrium regime of the generative process is revea"},"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":"2506.23546","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.NC","submitted_at":"2025-06-30T06:35:43Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","cs.NE"],"title_canon_sha256":"70bbc987842d655881aaafbabc19ebb62a451f296dbc5ff30895743e81287216","abstract_canon_sha256":"f9d9c91fba936d2b6835d2ca6bfa52b0a5f69ffc9be0ae4e389d6d34f33e7cd6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:30.108017Z","signature_b64":"c6zE5tjdLyA0RUUFkFuuPts+O5BFj8cRTRcHOZt5Iz90e9gHaBl7lqKX5xxsb9eruMMAyzlrBJ/4TPoKoPGTCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf32bbc8c01edcbdf1b93f31c595b086ea61a5280143c147488976cb49d8fa09","last_reissued_at":"2026-06-04T01:08:30.107203Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:30.107203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Langevin Machine: a local asymmetric learning rule can be creative","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Haiping Huang, Weizhong Huang, Zhendong Yu","submitted_at":"2025-06-30T06:35:43Z","abstract_excerpt":"Fixed points of recurrent neural networks can be leveraged to store and generate information. These fixed points can be captured by the Boltzmann-Gibbs measure, which leads to neural Langevin dynamics that can be used to find them for generative learning of a real dataset. We call this type of generative model a neural Langevin machine, which derives an asymmetric and firing-rate-speed adjusted learning rule requiring only local neural signals, thereby bearing biological relevance in terms of local predictive learning. An interesting out-of-equilibrium regime of the generative process is revea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23546","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/2506.23546/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":"2506.23546","created_at":"2026-06-04T01:08:30.107302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23546v2","created_at":"2026-06-04T01:08:30.107302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23546","created_at":"2026-06-04T01:08:30.107302+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4ZLXSGAD3OL","created_at":"2026-06-04T01:08:30.107302+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4ZLXSGAD3OL34NZ","created_at":"2026-06-04T01:08:30.107302+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4ZLXSGA","created_at":"2026-06-04T01:08:30.107302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2601.04702","citing_title":"Chaos in high-dimensional dynamical systems with tunable non-reciprocity","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3","json":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3.json","graph_json":"https://pith.science/api/pith-number/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/graph.json","events_json":"https://pith.science/api/pith-number/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/events.json","paper":"https://pith.science/paper/X4ZLXSGA"},"agent_actions":{"view_html":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3","download_json":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3.json","view_paper":"https://pith.science/paper/X4ZLXSGA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23546&json=true","fetch_graph":"https://pith.science/api/pith-number/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/graph.json","fetch_events":"https://pith.science/api/pith-number/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/action/storage_attestation","attest_author":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/action/author_attestation","sign_citation":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/action/citation_signature","submit_replication":"https://pith.science/pith/X4ZLXSGAD3OL34NZH4Y4LFNQQ3/action/replication_record"}},"created_at":"2026-06-04T01:08:30.107302+00:00","updated_at":"2026-06-04T01:08:30.107302+00:00"}