{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:CLB25YGGOAOD3IXRKQCABJY2TS","short_pith_number":"pith:CLB25YGG","schema_version":"1.0","canonical_sha256":"12c3aee0c6701c3da2f1540400a71a9c995fdc17bd2c2e9aa64e92ba746826bd","source":{"kind":"arxiv","id":"1311.2901","version":3},"attestation_state":"computed","paper":{"title":"Visualizing and Understanding Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthew D Zeiler, Rob Fergus","submitted_at":"2013-11-12T20:02:22Z","abstract_excerpt":"Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky \\etal on t"},"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":"1311.2901","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-11-12T20:02:22Z","cross_cats_sorted":[],"title_canon_sha256":"8d3b24f48aa95ea61e44bc4f40e4f9f1720445ac0eaa7be8669cdb181b598c52","abstract_canon_sha256":"6e681cc77a9a7f4664a232a1f4ec649be15a87744935ceac2742542288ec2f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:05:57.287759Z","signature_b64":"WvFEre5HEWq1oQOXjPrfO9EyEebNeSOVG7l4hf0lH1o1LAJLvSXYchTjRTfuj6a6wQUyYqiCf/i8dJzjX0YPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12c3aee0c6701c3da2f1540400a71a9c995fdc17bd2c2e9aa64e92ba746826bd","last_reissued_at":"2026-05-18T03:05:57.287073Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:05:57.287073Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visualizing and Understanding Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Matthew D Zeiler, Rob Fergus","submitted_at":"2013-11-12T20:02:22Z","abstract_excerpt":"Large Convolutional Network models have recently demonstrated impressive classification performance on the ImageNet benchmark. However there is no clear understanding of why they perform so well, or how they might be improved. In this paper we address both issues. We introduce a novel visualization technique that gives insight into the function of intermediate feature layers and the operation of the classifier. We also perform an ablation study to discover the performance contribution from different model layers. This enables us to find model architectures that outperform Krizhevsky \\etal on t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.2901","kind":"arxiv","version":3},"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":"1311.2901","created_at":"2026-05-18T03:05:57.287170+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.2901v3","created_at":"2026-05-18T03:05:57.287170+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.2901","created_at":"2026-05-18T03:05:57.287170+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLB25YGGOAOD","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLB25YGGOAOD3IXR","created_at":"2026-05-18T12:27:40.988391+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLB25YGG","created_at":"2026-05-18T12:27:40.988391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1906.10852","citing_title":"Water Preservation in Soan River Basin using Deep Learning Techniques","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"1906.12213","citing_title":"On the notion of number in humans and machines","ref_index":73,"is_internal_anchor":true},{"citing_arxiv_id":"1907.02519","citing_title":"Neuron ranking -- an informed way to condense convolutional neural networks architecture","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04572","citing_title":"Out-of-Distribution Detection Using Neural Rendering Generative Models","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06286","citing_title":"Autoencoding sensory substitution","ref_index":166,"is_internal_anchor":true},{"citing_arxiv_id":"2312.03508","citing_title":"Convolutional neural network based decoders for surface codes","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2412.00666","citing_title":"Explaining Object Detectors via Collective Contribution of Pixels","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2509.21677","citing_title":"Prophecy: Inferring Formal Properties from Neuron Activations","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08564","citing_title":"Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"1312.6199","citing_title":"Intriguing properties of neural networks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06357","citing_title":"Memory Efficient Full-gradient Attacks (MEFA) Framework for Adversarial Defense Evaluations","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"1312.6034","citing_title":"Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08192","citing_title":"Inside-Out: Measuring Generalization in Vision Transformers Through Inner Workings","ref_index":80,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS","json":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS.json","graph_json":"https://pith.science/api/pith-number/CLB25YGGOAOD3IXRKQCABJY2TS/graph.json","events_json":"https://pith.science/api/pith-number/CLB25YGGOAOD3IXRKQCABJY2TS/events.json","paper":"https://pith.science/paper/CLB25YGG"},"agent_actions":{"view_html":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS","download_json":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS.json","view_paper":"https://pith.science/paper/CLB25YGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.2901&json=true","fetch_graph":"https://pith.science/api/pith-number/CLB25YGGOAOD3IXRKQCABJY2TS/graph.json","fetch_events":"https://pith.science/api/pith-number/CLB25YGGOAOD3IXRKQCABJY2TS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS/action/storage_attestation","attest_author":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS/action/author_attestation","sign_citation":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS/action/citation_signature","submit_replication":"https://pith.science/pith/CLB25YGGOAOD3IXRKQCABJY2TS/action/replication_record"}},"created_at":"2026-05-18T03:05:57.287170+00:00","updated_at":"2026-05-18T03:05:57.287170+00:00"}