{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BJMASSOV3RDAVVQ2SKJJT47SBQ","short_pith_number":"pith:BJMASSOV","schema_version":"1.0","canonical_sha256":"0a580949d5dc460ad61a929299f3f20c3a3723df9e1d1edaf85a484dec5c9409","source":{"kind":"arxiv","id":"2602.14885","version":2},"attestation_state":"computed","paper":{"title":"Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"primary_cat":"cond-mat.dis-nn","authors_text":"Alain Goriely, Ram\\'on Nartallo-Kaluarachchi, Renaud Lambiotte","submitted_at":"2026-02-16T16:15:59Z","abstract_excerpt":"Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that restricts network dynamics to gradient-like flows. In contrast, biological networks support rich time-dependent behaviour facilitated by their asymmetry. Here we introduce a general framework, which we term drift-diffusion matching, for training continuous-time RNNs to represent arbitrary, nonlinear stochastic differential equations (SDEs), with given drift and dif"},"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":"2602.14885","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2026-02-16T16:15:59Z","cross_cats_sorted":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"title_canon_sha256":"31f6fe8758ed1b69d6ab6c549e166a66726cdf440dcf9cece287ca431458f6fe","abstract_canon_sha256":"0803e22bf7d9c23fad06e96b4bf2979af5e98d5faa6fc859eacf689aa8c281c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:45.537780Z","signature_b64":"S7GbNeosi/TkNb7qfvDHqOCa6hjN1WVRT9wSYcHiifpW0TaLQfBs7EqmCl6GU5nqNfOrULGtf2sYY0TQRoj7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a580949d5dc460ad61a929299f3f20c3a3723df9e1d1edaf85a484dec5c9409","last_reissued_at":"2026-06-04T01:08:45.536904Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:45.536904Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Drift-Diffusion Matching: Embedding dynamics in latent manifolds of asymmetric neural networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.stat-mech","cs.LG","q-bio.NC"],"primary_cat":"cond-mat.dis-nn","authors_text":"Alain Goriely, Ram\\'on Nartallo-Kaluarachchi, Renaud Lambiotte","submitted_at":"2026-02-16T16:15:59Z","abstract_excerpt":"Recurrent neural networks (RNNs) provide a theoretical framework for understanding computation in biological neural circuits, yet classical results, such as Hopfield's model of associative memory, rely on symmetric connectivity that restricts network dynamics to gradient-like flows. In contrast, biological networks support rich time-dependent behaviour facilitated by their asymmetry. Here we introduce a general framework, which we term drift-diffusion matching, for training continuous-time RNNs to represent arbitrary, nonlinear stochastic differential equations (SDEs), with given drift and dif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.14885","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/2602.14885/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":"2602.14885","created_at":"2026-06-04T01:08:45.537031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.14885v2","created_at":"2026-06-04T01:08:45.537031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.14885","created_at":"2026-06-04T01:08:45.537031+00:00"},{"alias_kind":"pith_short_12","alias_value":"BJMASSOV3RDA","created_at":"2026-06-04T01:08:45.537031+00:00"},{"alias_kind":"pith_short_16","alias_value":"BJMASSOV3RDAVVQ2","created_at":"2026-06-04T01:08:45.537031+00:00"},{"alias_kind":"pith_short_8","alias_value":"BJMASSOV","created_at":"2026-06-04T01:08:45.537031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ","json":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ.json","graph_json":"https://pith.science/api/pith-number/BJMASSOV3RDAVVQ2SKJJT47SBQ/graph.json","events_json":"https://pith.science/api/pith-number/BJMASSOV3RDAVVQ2SKJJT47SBQ/events.json","paper":"https://pith.science/paper/BJMASSOV"},"agent_actions":{"view_html":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ","download_json":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ.json","view_paper":"https://pith.science/paper/BJMASSOV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.14885&json=true","fetch_graph":"https://pith.science/api/pith-number/BJMASSOV3RDAVVQ2SKJJT47SBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/BJMASSOV3RDAVVQ2SKJJT47SBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ/action/storage_attestation","attest_author":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ/action/author_attestation","sign_citation":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ/action/citation_signature","submit_replication":"https://pith.science/pith/BJMASSOV3RDAVVQ2SKJJT47SBQ/action/replication_record"}},"created_at":"2026-06-04T01:08:45.537031+00:00","updated_at":"2026-06-04T01:08:45.537031+00:00"}