{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:6AULPEH2HUPXXZLAGNKVS7DFXC","short_pith_number":"pith:6AULPEH2","schema_version":"1.0","canonical_sha256":"f028b790fa3d1f7be5603355597c65b8baebc750c6a82ab2ae91872048cab489","source":{"kind":"arxiv","id":"1608.04064","version":1},"attestation_state":"computed","paper":{"title":"About Pyramid Structure in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alfredo Petrosino, Ihsan Ullah","submitted_at":"2016-08-14T06:03:09Z","abstract_excerpt":"Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no meaningful reduction in performance. In this paper we investigate to what extend CNN may take advantage of pyramid structure typical of biological neurons. A generalized statement over convolutional layers from input till fully connected layer is introduced that helps further in understanding and designing a successful deep network. It reduces ambiguity, nu"},"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":"1608.04064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-08-14T06:03:09Z","cross_cats_sorted":[],"title_canon_sha256":"9c8ae8b7b08c0a2dc907d26b4935e78444954eccd1baceb190f8edc3fe7b28fb","abstract_canon_sha256":"40c8db2a4caaa9e274de840902bfc893f7ac44d2945538dc8b53005b92164f8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:09:04.361094Z","signature_b64":"98usXnoqhDBqzsKEUCtRq6CzwK56bBCC8ObYRIjVMZPEHwCQrjFUJREYfMpO0hzOguqbHQLaeb4JSexa5OJ9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f028b790fa3d1f7be5603355597c65b8baebc750c6a82ab2ae91872048cab489","last_reissued_at":"2026-05-18T01:09:04.360532Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:09:04.360532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"About Pyramid Structure in Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alfredo Petrosino, Ihsan Ullah","submitted_at":"2016-08-14T06:03:09Z","abstract_excerpt":"Deep convolutional neural networks (CNN) brought revolution without any doubt to various challenging tasks, mainly in computer vision. However, their model designing still requires attention to reduce number of learnable parameters, with no meaningful reduction in performance. In this paper we investigate to what extend CNN may take advantage of pyramid structure typical of biological neurons. A generalized statement over convolutional layers from input till fully connected layer is introduced that helps further in understanding and designing a successful deep network. It reduces ambiguity, nu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04064","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":""},"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":"1608.04064","created_at":"2026-05-18T01:09:04.360615+00:00"},{"alias_kind":"arxiv_version","alias_value":"1608.04064v1","created_at":"2026-05-18T01:09:04.360615+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04064","created_at":"2026-05-18T01:09:04.360615+00:00"},{"alias_kind":"pith_short_12","alias_value":"6AULPEH2HUPX","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_16","alias_value":"6AULPEH2HUPXXZLA","created_at":"2026-05-18T12:30:01.593930+00:00"},{"alias_kind":"pith_short_8","alias_value":"6AULPEH2","created_at":"2026-05-18T12:30:01.593930+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/6AULPEH2HUPXXZLAGNKVS7DFXC","json":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC.json","graph_json":"https://pith.science/api/pith-number/6AULPEH2HUPXXZLAGNKVS7DFXC/graph.json","events_json":"https://pith.science/api/pith-number/6AULPEH2HUPXXZLAGNKVS7DFXC/events.json","paper":"https://pith.science/paper/6AULPEH2"},"agent_actions":{"view_html":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC","download_json":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC.json","view_paper":"https://pith.science/paper/6AULPEH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1608.04064&json=true","fetch_graph":"https://pith.science/api/pith-number/6AULPEH2HUPXXZLAGNKVS7DFXC/graph.json","fetch_events":"https://pith.science/api/pith-number/6AULPEH2HUPXXZLAGNKVS7DFXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC/action/storage_attestation","attest_author":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC/action/author_attestation","sign_citation":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC/action/citation_signature","submit_replication":"https://pith.science/pith/6AULPEH2HUPXXZLAGNKVS7DFXC/action/replication_record"}},"created_at":"2026-05-18T01:09:04.360615+00:00","updated_at":"2026-05-18T01:09:04.360615+00:00"}