{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:B2XKAQ5XQL5VOU2BOHQS2C272J","short_pith_number":"pith:B2XKAQ5X","schema_version":"1.0","canonical_sha256":"0eaea043b782fb57534171e12d0b5fd25a5cae012e8a72c247430a9b9e5c8ccc","source":{"kind":"arxiv","id":"1807.00053","version":2},"attestation_state":"computed","paper":{"title":"Task-Driven Convolutional Recurrent Models of the Visual System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Aran Nayebi, Daniel Bear, Daniel L. K. Yamins, David Sussillo, James J. DiCarlo, Jonas Kubilius, Kohitij Kar, Surya Ganguli","submitted_at":"2018-06-20T20:27:23Z","abstract_excerpt":"Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence ("},"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":"1807.00053","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-bio.NC","submitted_at":"2018-06-20T20:27:23Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.NE"],"title_canon_sha256":"4f5545677b53bf6006a3719c2155c70bba0ed14fb49f48f060faee95e0ab3611","abstract_canon_sha256":"d49242b24d5921451269d45fc808bc8b55720bab978abca1f875bc1d513a4650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:09.627266Z","signature_b64":"WmjLu+2s5w+cl8QU+Z3r6YeUjin7iT96Pz1w+Fm81EQSytZwGxFv2Rf6fGgq0xLY+aHdMfOfmrcuPZmdySx7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0eaea043b782fb57534171e12d0b5fd25a5cae012e8a72c247430a9b9e5c8ccc","last_reissued_at":"2026-05-18T00:02:09.626705Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:09.626705Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Task-Driven Convolutional Recurrent Models of the Visual System","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.NE"],"primary_cat":"q-bio.NC","authors_text":"Aran Nayebi, Daniel Bear, Daniel L. K. Yamins, David Sussillo, James J. DiCarlo, Jonas Kubilius, Kohitij Kar, Surya Ganguli","submitted_at":"2018-06-20T20:27:23Z","abstract_excerpt":"Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object classification tasks such as ImageNet. Further, they are quantitatively accurate models of temporally-averaged responses of neurons in the primate brain's visual system. However, biological visual systems have two ubiquitous architectural features not shared with typical CNNs: local recurrence within cortical areas, and long-range feedback from downstream areas to upstream areas. Here we explored the role of recurrence in improving classification performance. We found that standard forms of recurrence ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00053","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":"1807.00053","created_at":"2026-05-18T00:02:09.626794+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00053v2","created_at":"2026-05-18T00:02:09.626794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00053","created_at":"2026-05-18T00:02:09.626794+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2XKAQ5XQL5V","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2XKAQ5XQL5VOU2B","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2XKAQ5X","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11718","citing_title":"Self-organized MT Direction Maps Emerge from Spatiotemporal Contrastive Optimization","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J","json":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J.json","graph_json":"https://pith.science/api/pith-number/B2XKAQ5XQL5VOU2BOHQS2C272J/graph.json","events_json":"https://pith.science/api/pith-number/B2XKAQ5XQL5VOU2BOHQS2C272J/events.json","paper":"https://pith.science/paper/B2XKAQ5X"},"agent_actions":{"view_html":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J","download_json":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J.json","view_paper":"https://pith.science/paper/B2XKAQ5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00053&json=true","fetch_graph":"https://pith.science/api/pith-number/B2XKAQ5XQL5VOU2BOHQS2C272J/graph.json","fetch_events":"https://pith.science/api/pith-number/B2XKAQ5XQL5VOU2BOHQS2C272J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J/action/storage_attestation","attest_author":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J/action/author_attestation","sign_citation":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J/action/citation_signature","submit_replication":"https://pith.science/pith/B2XKAQ5XQL5VOU2BOHQS2C272J/action/replication_record"}},"created_at":"2026-05-18T00:02:09.626794+00:00","updated_at":"2026-05-18T00:02:09.626794+00:00"}