{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:IQ7V5NXXMYLLW64AIYJCO2HJ5M","short_pith_number":"pith:IQ7V5NXX","schema_version":"1.0","canonical_sha256":"443f5eb6f76616bb7b8046122768e9eb3fb4b1497a79e57252935cd736bc7095","source":{"kind":"arxiv","id":"2006.11052","version":2},"attestation_state":"computed","paper":{"title":"Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Soon Hoe Lim","submitted_at":"2020-06-19T10:09:09Z","abstract_excerpt":"Recurrent neural networks (RNNs) are brain-inspired models widely used in machine learning for analyzing sequential data. The present work is a contribution towards a deeper understanding of how RNNs process input signals using the response theory from nonequilibrium statistical mechanics. For a class of continuous-time stochastic RNNs (SRNNs) driven by an input signal, we derive a Volterra type series representation for their output. This representation is interpretable and disentangles the input signal from the SRNN architecture. The kernels of the series are certain recursively defined corr"},"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":"2006.11052","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2020-06-19T10:09:09Z","cross_cats_sorted":["cond-mat.dis-nn","cs.LG","math.PR"],"title_canon_sha256":"48c5aa7f338ba0dc0bab9197779637b3813ef4c670d23eb02f588a2f98bea7bb","abstract_canon_sha256":"609459cb5936b21addcef348fc1d12ec93d3f7cc1e4bdfb5a350f4e4451861b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:14:42.218590Z","signature_b64":"KIqwEvvcP+Si+Pq4lcHMglgPVa7OkzErdiSWQRS32Nc97aLerwWpqHtd1NzvShhLdMcHUh82OGm4UV6xr2bcBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"443f5eb6f76616bb7b8046122768e9eb3fb4b1497a79e57252935cd736bc7095","last_reissued_at":"2026-07-05T02:14:42.218229Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:14:42.218229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Recurrent Neural Networks Using Nonequilibrium Response Theory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.LG","math.PR"],"primary_cat":"stat.ML","authors_text":"Soon Hoe Lim","submitted_at":"2020-06-19T10:09:09Z","abstract_excerpt":"Recurrent neural networks (RNNs) are brain-inspired models widely used in machine learning for analyzing sequential data. The present work is a contribution towards a deeper understanding of how RNNs process input signals using the response theory from nonequilibrium statistical mechanics. For a class of continuous-time stochastic RNNs (SRNNs) driven by an input signal, we derive a Volterra type series representation for their output. This representation is interpretable and disentangles the input signal from the SRNN architecture. The kernels of the series are certain recursively defined corr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.11052","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/2006.11052/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":"2006.11052","created_at":"2026-07-05T02:14:42.218289+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.11052v2","created_at":"2026-07-05T02:14:42.218289+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.11052","created_at":"2026-07-05T02:14:42.218289+00:00"},{"alias_kind":"pith_short_12","alias_value":"IQ7V5NXXMYLL","created_at":"2026-07-05T02:14:42.218289+00:00"},{"alias_kind":"pith_short_16","alias_value":"IQ7V5NXXMYLLW64A","created_at":"2026-07-05T02:14:42.218289+00:00"},{"alias_kind":"pith_short_8","alias_value":"IQ7V5NXX","created_at":"2026-07-05T02:14:42.218289+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1908.03771","citing_title":"Predicting Critical Transitions in Multiscale Dynamical Systems Using Reservoir Computing","ref_index":2002,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M","json":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M.json","graph_json":"https://pith.science/api/pith-number/IQ7V5NXXMYLLW64AIYJCO2HJ5M/graph.json","events_json":"https://pith.science/api/pith-number/IQ7V5NXXMYLLW64AIYJCO2HJ5M/events.json","paper":"https://pith.science/paper/IQ7V5NXX"},"agent_actions":{"view_html":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M","download_json":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M.json","view_paper":"https://pith.science/paper/IQ7V5NXX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.11052&json=true","fetch_graph":"https://pith.science/api/pith-number/IQ7V5NXXMYLLW64AIYJCO2HJ5M/graph.json","fetch_events":"https://pith.science/api/pith-number/IQ7V5NXXMYLLW64AIYJCO2HJ5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M/action/storage_attestation","attest_author":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M/action/author_attestation","sign_citation":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M/action/citation_signature","submit_replication":"https://pith.science/pith/IQ7V5NXXMYLLW64AIYJCO2HJ5M/action/replication_record"}},"created_at":"2026-07-05T02:14:42.218289+00:00","updated_at":"2026-07-05T02:14:42.218289+00:00"}