{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:C7OX6SZZ2VSEGGR2NLSDWYVEWF","short_pith_number":"pith:C7OX6SZZ","schema_version":"1.0","canonical_sha256":"17dd7f4b39d564431a3a6ae43b62a4b15b99186d3ce80aa2ec22bfbc7d3dec66","source":{"kind":"arxiv","id":"1908.08993","version":1},"attestation_state":"computed","paper":{"title":"Local Unsupervised Learning for Image Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","q-bio.NC","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dmitry Krotov, John Hopfield, Leopold Grinberg","submitted_at":"2019-08-14T17:42:11Z","abstract_excerpt":"Local Hebbian learning is believed to be inferior in performance to end-to-end training using a backpropagation algorithm. We question this popular belief by designing a local algorithm that can learn convolutional filters at scale on large image datasets. These filters combined with patch normalization and very steep non-linearities result in a good classification accuracy for shallow networks trained locally, as opposed to end-to-end. The filters learned by our algorithm contain both orientation selective units and unoriented color units, resembling the responses of pyramidal neurons located"},"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":"1908.08993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-14T17:42:11Z","cross_cats_sorted":["cs.LG","cs.NE","q-bio.NC","stat.ML"],"title_canon_sha256":"b9b4b08705cf313333cb6c204617b4bf72eff92bf94f0af94c1b32b28b54958a","abstract_canon_sha256":"0d2f75f6f36aed6fa5ed76dbb5fe39a8c0ffdd0ab51fe138299e49c465481efb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:35.682686Z","signature_b64":"nrDzBKHt5foZSSBjnCqKOC3zf9lqaK78/f4RGzBLOk0KiswJ2LweXjfQoUEnU5wvI2dE3LpupPq4fNSn+xMDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17dd7f4b39d564431a3a6ae43b62a4b15b99186d3ce80aa2ec22bfbc7d3dec66","last_reissued_at":"2026-07-04T23:59:35.682253Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:35.682253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Unsupervised Learning for Image Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","q-bio.NC","stat.ML"],"primary_cat":"cs.CV","authors_text":"Dmitry Krotov, John Hopfield, Leopold Grinberg","submitted_at":"2019-08-14T17:42:11Z","abstract_excerpt":"Local Hebbian learning is believed to be inferior in performance to end-to-end training using a backpropagation algorithm. We question this popular belief by designing a local algorithm that can learn convolutional filters at scale on large image datasets. These filters combined with patch normalization and very steep non-linearities result in a good classification accuracy for shallow networks trained locally, as opposed to end-to-end. The filters learned by our algorithm contain both orientation selective units and unoriented color units, resembling the responses of pyramidal neurons located"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08993","kind":"arxiv","version":1},"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/1908.08993/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":"1908.08993","created_at":"2026-07-04T23:59:35.682309+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.08993v1","created_at":"2026-07-04T23:59:35.682309+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08993","created_at":"2026-07-04T23:59:35.682309+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7OX6SZZ2VSE","created_at":"2026-07-04T23:59:35.682309+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7OX6SZZ2VSEGGR2","created_at":"2026-07-04T23:59:35.682309+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7OX6SZZ","created_at":"2026-07-04T23:59:35.682309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.05042","citing_title":"Energy-Based Dynamical Models for Neurocomputation, Learning, and Optimization","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF","json":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF.json","graph_json":"https://pith.science/api/pith-number/C7OX6SZZ2VSEGGR2NLSDWYVEWF/graph.json","events_json":"https://pith.science/api/pith-number/C7OX6SZZ2VSEGGR2NLSDWYVEWF/events.json","paper":"https://pith.science/paper/C7OX6SZZ"},"agent_actions":{"view_html":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF","download_json":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF.json","view_paper":"https://pith.science/paper/C7OX6SZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.08993&json=true","fetch_graph":"https://pith.science/api/pith-number/C7OX6SZZ2VSEGGR2NLSDWYVEWF/graph.json","fetch_events":"https://pith.science/api/pith-number/C7OX6SZZ2VSEGGR2NLSDWYVEWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF/action/storage_attestation","attest_author":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF/action/author_attestation","sign_citation":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF/action/citation_signature","submit_replication":"https://pith.science/pith/C7OX6SZZ2VSEGGR2NLSDWYVEWF/action/replication_record"}},"created_at":"2026-07-04T23:59:35.682309+00:00","updated_at":"2026-07-04T23:59:35.682309+00:00"}