{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:R5UQSCDKFKG6XNS2EVRLL2CACG","short_pith_number":"pith:R5UQSCDK","schema_version":"1.0","canonical_sha256":"8f6909086a2a8debb65a2562b5e84011aad312921e51a07994c4bbadc938843e","source":{"kind":"arxiv","id":"2010.14765","version":1},"attestation_state":"computed","paper":{"title":"Deep Networks from the Principle of Rate Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chong You, Haozhi Qi, John Wright, Kwan Ho Ryan Chan, Yaodong Yu, Yi Ma","submitted_at":"2020-10-27T06:01:43Z","abstract_excerpt":"This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of learned features naturally leads to a multi-layer deep network, one iteration per layer. The layered architectures, linear and nonlinear operators, and even parameters of the network are all explicitly constructed layer-by-layer in a forward propagation fashion by emulating the gradient scheme. All components of this \"white box\" network have precise optimizati"},"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":"2010.14765","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-27T06:01:43Z","cross_cats_sorted":["cs.IT","math.IT","math.OC","stat.ML"],"title_canon_sha256":"dc1bcd682a8e85e007e3be9add7f3a89a2ff31ec844242dbd09db64149809dfd","abstract_canon_sha256":"2ae1de11ce7fd5477f39a3aded0253bb60b12c2b8df70eb8b95f1b6ec85d66ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:33.813672Z","signature_b64":"V1xjOOWoRmfWmQOKLitPK8SYz2icHEOULPUUs1JbaLDIUnNhg7QHlgtAkfX0TKfOlVnJ1xJ5Z3T8R6A1IdiIDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f6909086a2a8debb65a2562b5e84011aad312921e51a07994c4bbadc938843e","last_reissued_at":"2026-07-05T01:47:33.813180Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:33.813180Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Networks from the Principle of Rate Reduction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","math.OC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chong You, Haozhi Qi, John Wright, Kwan Ho Ryan Chan, Yaodong Yu, Yi Ma","submitted_at":"2020-10-27T06:01:43Z","abstract_excerpt":"This work attempts to interpret modern deep (convolutional) networks from the principles of rate reduction and (shift) invariant classification. We show that the basic iterative gradient ascent scheme for optimizing the rate reduction of learned features naturally leads to a multi-layer deep network, one iteration per layer. The layered architectures, linear and nonlinear operators, and even parameters of the network are all explicitly constructed layer-by-layer in a forward propagation fashion by emulating the gradient scheme. All components of this \"white box\" network have precise optimizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.14765","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/2010.14765/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":"2010.14765","created_at":"2026-07-05T01:47:33.813233+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.14765v1","created_at":"2026-07-05T01:47:33.813233+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.14765","created_at":"2026-07-05T01:47:33.813233+00:00"},{"alias_kind":"pith_short_12","alias_value":"R5UQSCDKFKG6","created_at":"2026-07-05T01:47:33.813233+00:00"},{"alias_kind":"pith_short_16","alias_value":"R5UQSCDKFKG6XNS2","created_at":"2026-07-05T01:47:33.813233+00:00"},{"alias_kind":"pith_short_8","alias_value":"R5UQSCDK","created_at":"2026-07-05T01:47:33.813233+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/R5UQSCDKFKG6XNS2EVRLL2CACG","json":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG.json","graph_json":"https://pith.science/api/pith-number/R5UQSCDKFKG6XNS2EVRLL2CACG/graph.json","events_json":"https://pith.science/api/pith-number/R5UQSCDKFKG6XNS2EVRLL2CACG/events.json","paper":"https://pith.science/paper/R5UQSCDK"},"agent_actions":{"view_html":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG","download_json":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG.json","view_paper":"https://pith.science/paper/R5UQSCDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.14765&json=true","fetch_graph":"https://pith.science/api/pith-number/R5UQSCDKFKG6XNS2EVRLL2CACG/graph.json","fetch_events":"https://pith.science/api/pith-number/R5UQSCDKFKG6XNS2EVRLL2CACG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG/action/storage_attestation","attest_author":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG/action/author_attestation","sign_citation":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG/action/citation_signature","submit_replication":"https://pith.science/pith/R5UQSCDKFKG6XNS2EVRLL2CACG/action/replication_record"}},"created_at":"2026-07-05T01:47:33.813233+00:00","updated_at":"2026-07-05T01:47:33.813233+00:00"}