{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:H2IXAE26ISV7VA5RYXRUUFRXXF","short_pith_number":"pith:H2IXAE26","schema_version":"1.0","canonical_sha256":"3e9170135e44abfa83b1c5e34a1637b9404b6d47b5bcb45a7f82e19c4f1ebf30","source":{"kind":"arxiv","id":"1412.6806","version":3},"attestation_state":"computed","paper":{"title":"Striving for Simplicity: The All Convolutional Net","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox","submitted_at":"2014-12-21T16:16:37Z","abstract_excerpt":"Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity of different components in the pipeline. We find that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Following this finding -- and building on other rec"},"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":"1412.6806","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2014-12-21T16:16:37Z","cross_cats_sorted":["cs.CV","cs.NE"],"title_canon_sha256":"43d1811b4499004f0572eb18a865df5adfe9ef5623b052e6ada083e21a364424","abstract_canon_sha256":"f1549b8e7550646db691d10c2c18f74df384baf54f60b8d3cb5bfc579b0ebdcf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:19:00.628502Z","signature_b64":"j+rrQX69hK2GtwhTF2MMAnBhoVj+yR9fBBQh4DaXPbVpnfK9X/TjDccLeyHcnwZzgV5jD3IcMQzFKCa3pIuNDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e9170135e44abfa83b1c5e34a1637b9404b6d47b5bcb45a7f82e19c4f1ebf30","last_reissued_at":"2026-05-18T02:19:00.627858Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:19:00.627858Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Striving for Simplicity: The All Convolutional Net","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.NE"],"primary_cat":"cs.LG","authors_text":"Alexey Dosovitskiy, Jost Tobias Springenberg, Martin Riedmiller, Thomas Brox","submitted_at":"2014-12-21T16:16:37Z","abstract_excerpt":"Most modern convolutional neural networks (CNNs) used for object recognition are built using the same principles: Alternating convolution and max-pooling layers followed by a small number of fully connected layers. We re-evaluate the state of the art for object recognition from small images with convolutional networks, questioning the necessity of different components in the pipeline. We find that max-pooling can simply be replaced by a convolutional layer with increased stride without loss in accuracy on several image recognition benchmarks. Following this finding -- and building on other rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6806","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":"1412.6806","created_at":"2026-05-18T02:19:00.627949+00:00"},{"alias_kind":"arxiv_version","alias_value":"1412.6806v3","created_at":"2026-05-18T02:19:00.627949+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6806","created_at":"2026-05-18T02:19:00.627949+00:00"},{"alias_kind":"pith_short_12","alias_value":"H2IXAE26ISV7","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_16","alias_value":"H2IXAE26ISV7VA5R","created_at":"2026-05-18T12:28:30.664211+00:00"},{"alias_kind":"pith_short_8","alias_value":"H2IXAE26","created_at":"2026-05-18T12:28:30.664211+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":13,"sample":[{"citing_arxiv_id":"1906.10282","citing_title":"Saliency-driven Word Alignment Interpretation for Neural Machine Translation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04572","citing_title":"Out-of-Distribution Detection Using Neural Rendering Generative Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04911","citing_title":"Explaining an increase in predicted risk for clinical alerts","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09000","citing_title":"Image Classification with Hierarchical Multigraph Networks","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2210.15304","citing_title":"Explaining the Explainers in Graph Neural Networks: a Comparative Study","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"1811.10959","citing_title":"Dataset Distillation","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2407.07639","citing_title":"Explaining Graph Neural Networks for Node Similarity on Graphs","ref_index":70,"is_internal_anchor":true},{"citing_arxiv_id":"2411.02622","citing_title":"AdaProb: Efficient Machine Unlearning via Adaptive Probability","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2502.18026","citing_title":"ExPath: Targeted Pathway Inference for Biological Knowledge Bases via Graph Learning and Explanation","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"2503.08633","citing_title":"How Does Overparameterization Affect Machine Unlearning of Deep Neural Networks?","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19607","citing_title":"Spectral Integrated Gradients for Coarse-to-Fine Feature Attribution","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2310.12508","citing_title":"SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2601.23011","citing_title":"Leveraging Convolutional Sparse Autoencoders for Robust Movement Classification from Low-Density sEMG","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"1511.06434","citing_title":"Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2104.13478","citing_title":"Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"1610.05492","citing_title":"Federated Learning: Strategies for Improving Communication Efficiency","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05283","citing_title":"Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09799","citing_title":"Explainable Human Activity Recognition: A Unified Review of Concepts and Mechanisms","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF","json":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF.json","graph_json":"https://pith.science/api/pith-number/H2IXAE26ISV7VA5RYXRUUFRXXF/graph.json","events_json":"https://pith.science/api/pith-number/H2IXAE26ISV7VA5RYXRUUFRXXF/events.json","paper":"https://pith.science/paper/H2IXAE26"},"agent_actions":{"view_html":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF","download_json":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF.json","view_paper":"https://pith.science/paper/H2IXAE26","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1412.6806&json=true","fetch_graph":"https://pith.science/api/pith-number/H2IXAE26ISV7VA5RYXRUUFRXXF/graph.json","fetch_events":"https://pith.science/api/pith-number/H2IXAE26ISV7VA5RYXRUUFRXXF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF/action/storage_attestation","attest_author":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF/action/author_attestation","sign_citation":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF/action/citation_signature","submit_replication":"https://pith.science/pith/H2IXAE26ISV7VA5RYXRUUFRXXF/action/replication_record"}},"created_at":"2026-05-18T02:19:00.627949+00:00","updated_at":"2026-05-18T02:19:00.627949+00:00"}