{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:RG2PFROIQ7FLSZYELUR4WY2QVL","short_pith_number":"pith:RG2PFROI","schema_version":"1.0","canonical_sha256":"89b4f2c5c887cab967045d23cb6350aafecba4109446d200b1422a5c4bc819d2","source":{"kind":"arxiv","id":"1507.08973","version":2},"attestation_state":"computed","paper":{"title":"Training recurrent neural networks with sparse, delayed rewards for flexible decision tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Thomas Miconi","submitted_at":"2015-07-31T18:43:28Z","abstract_excerpt":"Recurrent neural networks in the chaotic regime exhibit complex dynamics reminiscent of high-level cortical activity during behavioral tasks. However, existing training methods for such networks are either biologically implausible, or require a real-time continuous error signal to guide the learning process. This is in contrast with most behavioral tasks, which only provide time-sparse, delayed rewards. Here we show that a biologically plausible reward-modulated Hebbian learning algorithm, previously used in feedforward models of birdsong learning, can train recurrent networks based solely on "},"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":"1507.08973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2015-07-31T18:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"375201bc9417006f6b7ac9923e503ba8a4eb38cf887c089c45fc858f228f7522","abstract_canon_sha256":"bb9f392a175b9bbec7e37a72cbca7f6d390530508aded15b3b18e02a72f40ef8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:24:53.516094Z","signature_b64":"kZpQLO8M1W/rUMkvvcOmdu+iBkzUJfwUfltmO0kguRHzVYasu46axcgUlDDOiE/gFeQ8hjW93416JYZmjwxyCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b4f2c5c887cab967045d23cb6350aafecba4109446d200b1422a5c4bc819d2","last_reissued_at":"2026-05-18T01:24:53.515437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:24:53.515437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training recurrent neural networks with sparse, delayed rewards for flexible decision tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-bio.NC","authors_text":"Thomas Miconi","submitted_at":"2015-07-31T18:43:28Z","abstract_excerpt":"Recurrent neural networks in the chaotic regime exhibit complex dynamics reminiscent of high-level cortical activity during behavioral tasks. However, existing training methods for such networks are either biologically implausible, or require a real-time continuous error signal to guide the learning process. This is in contrast with most behavioral tasks, which only provide time-sparse, delayed rewards. Here we show that a biologically plausible reward-modulated Hebbian learning algorithm, previously used in feedforward models of birdsong learning, can train recurrent networks based solely on "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1507.08973","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":""},"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":"1507.08973","created_at":"2026-05-18T01:24:53.515574+00:00"},{"alias_kind":"arxiv_version","alias_value":"1507.08973v2","created_at":"2026-05-18T01:24:53.515574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1507.08973","created_at":"2026-05-18T01:24:53.515574+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG2PFROIQ7FL","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG2PFROIQ7FLSZYE","created_at":"2026-05-18T12:29:39.896362+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG2PFROI","created_at":"2026-05-18T12:29:39.896362+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/RG2PFROIQ7FLSZYELUR4WY2QVL","json":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL.json","graph_json":"https://pith.science/api/pith-number/RG2PFROIQ7FLSZYELUR4WY2QVL/graph.json","events_json":"https://pith.science/api/pith-number/RG2PFROIQ7FLSZYELUR4WY2QVL/events.json","paper":"https://pith.science/paper/RG2PFROI"},"agent_actions":{"view_html":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL","download_json":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL.json","view_paper":"https://pith.science/paper/RG2PFROI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1507.08973&json=true","fetch_graph":"https://pith.science/api/pith-number/RG2PFROIQ7FLSZYELUR4WY2QVL/graph.json","fetch_events":"https://pith.science/api/pith-number/RG2PFROIQ7FLSZYELUR4WY2QVL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL/action/storage_attestation","attest_author":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL/action/author_attestation","sign_citation":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL/action/citation_signature","submit_replication":"https://pith.science/pith/RG2PFROIQ7FLSZYELUR4WY2QVL/action/replication_record"}},"created_at":"2026-05-18T01:24:53.515574+00:00","updated_at":"2026-05-18T01:24:53.515574+00:00"}