{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:2NEHPM6NWJJ37O4SSLROQKFS5Y","short_pith_number":"pith:2NEHPM6N","schema_version":"1.0","canonical_sha256":"d34877b3cdb253bfbb9292e2e828b2ee0af532d56f55436efcc7aa66a28f6c91","source":{"kind":"arxiv","id":"1605.07678","version":4},"attestation_state":"computed","paper":{"title":"An Analysis of Deep Neural Network Models for Practical Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Paszke, Alfredo Canziani, Eugenio Culurciello","submitted_at":"2016-05-24T22:36:02Z","abstract_excerpt":"Since the emergence of Deep Neural Networks (DNNs) as a prominent technique in the field of computer vision, the ImageNet classification challenge has played a major role in advancing the state-of-the-art. While accuracy figures have steadily increased, the resource utilisation of winning models has not been properly taken into account. In this work, we present a comprehensive analysis of important metrics in practical applications: accuracy, memory footprint, parameters, operations count, inference time and power consumption. Key findings are: (1) power consumption is independent of batch siz"},"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":"1605.07678","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-05-24T22:36:02Z","cross_cats_sorted":[],"title_canon_sha256":"d47cd15754fbf55a6aabbdc60696fe390d33bbba90bdc3e72abf3c7a97474b87","abstract_canon_sha256":"abac135fd7b1e7a52a7124346f318011928fc63adae46031703dc130171bc360"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:21.007971Z","signature_b64":"uktXi4oUR+vw0dMlbkofiBH1zrv0n8ZrAP9WTXYd8d3ChnOQJXQbj5hHvpxxld1QVU5HKa/yuQSdIf6C+R7rDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d34877b3cdb253bfbb9292e2e828b2ee0af532d56f55436efcc7aa66a28f6c91","last_reissued_at":"2026-05-18T00:46:21.007632Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:21.007632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Analysis of Deep Neural Network Models for Practical Applications","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Adam Paszke, Alfredo Canziani, Eugenio Culurciello","submitted_at":"2016-05-24T22:36:02Z","abstract_excerpt":"Since the emergence of Deep Neural Networks (DNNs) as a prominent technique in the field of computer vision, the ImageNet classification challenge has played a major role in advancing the state-of-the-art. While accuracy figures have steadily increased, the resource utilisation of winning models has not been properly taken into account. In this work, we present a comprehensive analysis of important metrics in practical applications: accuracy, memory footprint, parameters, operations count, inference time and power consumption. Key findings are: (1) power consumption is independent of batch siz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.07678","kind":"arxiv","version":4},"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":"1605.07678","created_at":"2026-05-18T00:46:21.007688+00:00"},{"alias_kind":"arxiv_version","alias_value":"1605.07678v4","created_at":"2026-05-18T00:46:21.007688+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.07678","created_at":"2026-05-18T00:46:21.007688+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NEHPM6NWJJ3","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NEHPM6NWJJ37O4S","created_at":"2026-05-18T12:29:55.572404+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NEHPM6N","created_at":"2026-05-18T12:29:55.572404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"1906.08834","citing_title":"Deep Learning in the Automotive Industry: Recent Advances and Application Examples","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"1906.12172","citing_title":"New pointwise convolution in Deep Neural Networks through Extremely Fast and Non Parametric Transforms","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"1907.05748","citing_title":"Benchmarking Physical Performance of Neural Inference Circuits","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07321","citing_title":"Comparison of Neural Network Architectures for Spectrum Sensing","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"1907.07772","citing_title":"Modern CNNs for IoT Based Farms","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2503.10666","citing_title":"Green Prompting: Characterizing Prompt-driven Energy Costs of LLM Inference","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11989","citing_title":"A Transfer Learning Evaluation of Deep Neural Networks for Image Classification","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14552","citing_title":"DEEP-GAP: Deep-learning Evaluation of Execution Parallelism in GPU Architectural Performance","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y","json":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y.json","graph_json":"https://pith.science/api/pith-number/2NEHPM6NWJJ37O4SSLROQKFS5Y/graph.json","events_json":"https://pith.science/api/pith-number/2NEHPM6NWJJ37O4SSLROQKFS5Y/events.json","paper":"https://pith.science/paper/2NEHPM6N"},"agent_actions":{"view_html":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y","download_json":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y.json","view_paper":"https://pith.science/paper/2NEHPM6N","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1605.07678&json=true","fetch_graph":"https://pith.science/api/pith-number/2NEHPM6NWJJ37O4SSLROQKFS5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/2NEHPM6NWJJ37O4SSLROQKFS5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y/action/storage_attestation","attest_author":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y/action/author_attestation","sign_citation":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y/action/citation_signature","submit_replication":"https://pith.science/pith/2NEHPM6NWJJ37O4SSLROQKFS5Y/action/replication_record"}},"created_at":"2026-05-18T00:46:21.007688+00:00","updated_at":"2026-05-18T00:46:21.007688+00:00"}