{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:CWE6KETVKRMKJZ5GCA6WAHSEUK","short_pith_number":"pith:CWE6KETV","schema_version":"1.0","canonical_sha256":"1589e512755458a4e7a6103d601e44a29da38c3c87533cc6e7fe212ab19efdeb","source":{"kind":"arxiv","id":"1901.10208","version":1},"attestation_state":"computed","paper":{"title":"A Push-Pull Layer Improves Robustness of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Manuel Lopez-Antequera, Nicolai Petkov, Nicola Strisciuglio","submitted_at":"2019-01-29T10:42:04Z","abstract_excerpt":"We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images. We call this a push-pull layer and compute its response as the combination of two half-wave rectified convolutions, with kernels of opposite polarity. It is based on a biologically-motivated non-linear model of certain neurons in the visual system that exhibit a response suppression phenomenon, known as push-pull inhibition. We validate our method by substituting the first convolutional layer of the LeNet-5 and WideResNet architectures with ou"},"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":"1901.10208","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-01-29T10:42:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b23eaba44316f203c0db959eec1fe5447827284ef3a0855a7efaff84e545190a","abstract_canon_sha256":"78b3b145b3fc0329c8b8a359771ee1298f2408b3201b730f3bbd6d5ecd3ddc90"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:55:15.845341Z","signature_b64":"t3GpMsPAzIsje3wZqI6R1uEL6M54gTwemY93HObkSfg4llx0k/uHaPM9krpao8jftBMrgPOAlsLNkU4w8wNmBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1589e512755458a4e7a6103d601e44a29da38c3c87533cc6e7fe212ab19efdeb","last_reissued_at":"2026-05-17T23:55:15.844799Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:55:15.844799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Push-Pull Layer Improves Robustness of Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Manuel Lopez-Antequera, Nicolai Petkov, Nicola Strisciuglio","submitted_at":"2019-01-29T10:42:04Z","abstract_excerpt":"We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images. We call this a push-pull layer and compute its response as the combination of two half-wave rectified convolutions, with kernels of opposite polarity. It is based on a biologically-motivated non-linear model of certain neurons in the visual system that exhibit a response suppression phenomenon, known as push-pull inhibition. We validate our method by substituting the first convolutional layer of the LeNet-5 and WideResNet architectures with ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1901.10208","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":"1901.10208","created_at":"2026-05-17T23:55:15.844881+00:00"},{"alias_kind":"arxiv_version","alias_value":"1901.10208v1","created_at":"2026-05-17T23:55:15.844881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1901.10208","created_at":"2026-05-17T23:55:15.844881+00:00"},{"alias_kind":"pith_short_12","alias_value":"CWE6KETVKRMK","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_16","alias_value":"CWE6KETVKRMKJZ5G","created_at":"2026-05-18T12:33:15.570797+00:00"},{"alias_kind":"pith_short_8","alias_value":"CWE6KETV","created_at":"2026-05-18T12:33:15.570797+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.12151","citing_title":"Place recognition in gardens by learning visual representations: data set and benchmark analysis","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK","json":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK.json","graph_json":"https://pith.science/api/pith-number/CWE6KETVKRMKJZ5GCA6WAHSEUK/graph.json","events_json":"https://pith.science/api/pith-number/CWE6KETVKRMKJZ5GCA6WAHSEUK/events.json","paper":"https://pith.science/paper/CWE6KETV"},"agent_actions":{"view_html":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK","download_json":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK.json","view_paper":"https://pith.science/paper/CWE6KETV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1901.10208&json=true","fetch_graph":"https://pith.science/api/pith-number/CWE6KETVKRMKJZ5GCA6WAHSEUK/graph.json","fetch_events":"https://pith.science/api/pith-number/CWE6KETVKRMKJZ5GCA6WAHSEUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK/action/storage_attestation","attest_author":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK/action/author_attestation","sign_citation":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK/action/citation_signature","submit_replication":"https://pith.science/pith/CWE6KETVKRMKJZ5GCA6WAHSEUK/action/replication_record"}},"created_at":"2026-05-17T23:55:15.844881+00:00","updated_at":"2026-05-17T23:55:15.844881+00:00"}