{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HWXC35ZFG43W24JAVX4IM6DRZS","short_pith_number":"pith:HWXC35ZF","schema_version":"1.0","canonical_sha256":"3dae2df72537376d7120adf8867871cc99a8029f42e1939460e035d810b6af2d","source":{"kind":"arxiv","id":"2311.10869","version":2},"attestation_state":"computed","paper":{"title":"Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Eli Shlizerman, Eric Shea-Brown, James Hazelden, Yuhan Helena Liu","submitted_at":"2023-11-17T20:59:57Z","abstract_excerpt":"Training networks consisting of biophysically accurate neuron models could allow for new insights into how brain circuits can organize and solve tasks. We begin by analyzing the extent to which the central algorithm for neural network learning -- stochastic gradient descent through backpropagation (BP) -- can be used to train such networks. We find that properties of biophysically based neural network models needed for accurate modelling such as stiffness, high nonlinearity and long evaluation timeframes relative to spike times makes BP unstable and divergent in a variety of cases. To address "},"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":"2311.10869","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2023-11-17T20:59:57Z","cross_cats_sorted":["cs.NE"],"title_canon_sha256":"87a04caea51eb155df42235c999985a1a490ec491f0d5cd2ad28b2eb934adcd0","abstract_canon_sha256":"c8d03464ada79db2d02de6aba0a9fc5bb0ac0c21ba1fee872c5888c8c97e42ec"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:59.242207Z","signature_b64":"dyiv9mvvLu/5rsmdD0IBPqGznEEocIMgb/SuY0RSdTgEwKzEaHxVW+ZnRiRbPQGZMSFhQppcXgKY8iz4sugIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dae2df72537376d7120adf8867871cc99a8029f42e1939460e035d810b6af2d","last_reissued_at":"2026-07-05T07:14:59.241722Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:59.241722Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evolutionary algorithms as an alternative to backpropagation for supervised training of Biophysical Neural Networks and Neural ODEs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Eli Shlizerman, Eric Shea-Brown, James Hazelden, Yuhan Helena Liu","submitted_at":"2023-11-17T20:59:57Z","abstract_excerpt":"Training networks consisting of biophysically accurate neuron models could allow for new insights into how brain circuits can organize and solve tasks. We begin by analyzing the extent to which the central algorithm for neural network learning -- stochastic gradient descent through backpropagation (BP) -- can be used to train such networks. We find that properties of biophysically based neural network models needed for accurate modelling such as stiffness, high nonlinearity and long evaluation timeframes relative to spike times makes BP unstable and divergent in a variety of cases. To address "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10869","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/2311.10869/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":"2311.10869","created_at":"2026-07-05T07:14:59.241783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.10869v2","created_at":"2026-07-05T07:14:59.241783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10869","created_at":"2026-07-05T07:14:59.241783+00:00"},{"alias_kind":"pith_short_12","alias_value":"HWXC35ZFG43W","created_at":"2026-07-05T07:14:59.241783+00:00"},{"alias_kind":"pith_short_16","alias_value":"HWXC35ZFG43W24JA","created_at":"2026-07-05T07:14:59.241783+00:00"},{"alias_kind":"pith_short_8","alias_value":"HWXC35ZF","created_at":"2026-07-05T07:14:59.241783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12763","citing_title":"State-Space NTK Collapse Near Bifurcations","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08746","citing_title":"The Global Empirical NTK: Self-Referential Bias and Dimensionality of Gradient Descent Learning","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS","json":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS.json","graph_json":"https://pith.science/api/pith-number/HWXC35ZFG43W24JAVX4IM6DRZS/graph.json","events_json":"https://pith.science/api/pith-number/HWXC35ZFG43W24JAVX4IM6DRZS/events.json","paper":"https://pith.science/paper/HWXC35ZF"},"agent_actions":{"view_html":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS","download_json":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS.json","view_paper":"https://pith.science/paper/HWXC35ZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.10869&json=true","fetch_graph":"https://pith.science/api/pith-number/HWXC35ZFG43W24JAVX4IM6DRZS/graph.json","fetch_events":"https://pith.science/api/pith-number/HWXC35ZFG43W24JAVX4IM6DRZS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS/action/storage_attestation","attest_author":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS/action/author_attestation","sign_citation":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS/action/citation_signature","submit_replication":"https://pith.science/pith/HWXC35ZFG43W24JAVX4IM6DRZS/action/replication_record"}},"created_at":"2026-07-05T07:14:59.241783+00:00","updated_at":"2026-07-05T07:14:59.241783+00:00"}