{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:N3W6TVVRXMQP4GCZA7BIR23S5X","short_pith_number":"pith:N3W6TVVR","schema_version":"1.0","canonical_sha256":"6eede9d6b1bb20fe185907c288eb72edd3e912b9200ee7c2d9524d35b9e5201e","source":{"kind":"arxiv","id":"1703.08245","version":1},"attestation_state":"computed","paper":{"title":"On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Gabriel Kreiman, Martin Schrimpf, Nicholas Cheney","submitted_at":"2017-03-23T22:25:05Z","abstract_excerpt":"Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of convolutional neural networks to perturbations to the internal weights and architecture of the network itself. We show that convolutional networks are surprisingly robust to a number of internal perturbations in the higher convolutional layers but the bottom convolutional layers are much more fragile. For instance, Alexnet shows less than a 30% decrease in classific"},"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":"1703.08245","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-03-23T22:25:05Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"6e6f1510e9044c1024ea0a6a8d671becbfec463a7c7cb2689b79e4702f2cd20d","abstract_canon_sha256":"2962cd9d7d4fe0f5081d0ec03096cde3b9426dc8120114c7930845e8101d6e01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:48:00.375452Z","signature_b64":"ahok9Zi6qZHEZixIP359OvclluYTT2ePrlxMwYCy9C/s3qFXlHvx8ah6Vj3s0NaRyFObqzQiVMyNWmSRteZTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6eede9d6b1bb20fe185907c288eb72edd3e912b9200ee7c2d9524d35b9e5201e","last_reissued_at":"2026-05-18T00:48:00.375027Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:48:00.375027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Gabriel Kreiman, Martin Schrimpf, Nicholas Cheney","submitted_at":"2017-03-23T22:25:05Z","abstract_excerpt":"Deep convolutional neural networks are generally regarded as robust function approximators. So far, this intuition is based on perturbations to external stimuli such as the images to be classified. Here we explore the robustness of convolutional neural networks to perturbations to the internal weights and architecture of the network itself. We show that convolutional networks are surprisingly robust to a number of internal perturbations in the higher convolutional layers but the bottom convolutional layers are much more fragile. For instance, Alexnet shows less than a 30% decrease in classific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.08245","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":"1703.08245","created_at":"2026-05-18T00:48:00.375094+00:00"},{"alias_kind":"arxiv_version","alias_value":"1703.08245v1","created_at":"2026-05-18T00:48:00.375094+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.08245","created_at":"2026-05-18T00:48:00.375094+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3W6TVVRXMQP","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3W6TVVRXMQP4GCZ","created_at":"2026-05-18T12:31:31.346846+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3W6TVVR","created_at":"2026-05-18T12:31:31.346846+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15435","citing_title":"On the Stability of Growth in Structural Plasticity","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X","json":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X.json","graph_json":"https://pith.science/api/pith-number/N3W6TVVRXMQP4GCZA7BIR23S5X/graph.json","events_json":"https://pith.science/api/pith-number/N3W6TVVRXMQP4GCZA7BIR23S5X/events.json","paper":"https://pith.science/paper/N3W6TVVR"},"agent_actions":{"view_html":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X","download_json":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X.json","view_paper":"https://pith.science/paper/N3W6TVVR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1703.08245&json=true","fetch_graph":"https://pith.science/api/pith-number/N3W6TVVRXMQP4GCZA7BIR23S5X/graph.json","fetch_events":"https://pith.science/api/pith-number/N3W6TVVRXMQP4GCZA7BIR23S5X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X/action/storage_attestation","attest_author":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X/action/author_attestation","sign_citation":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X/action/citation_signature","submit_replication":"https://pith.science/pith/N3W6TVVRXMQP4GCZA7BIR23S5X/action/replication_record"}},"created_at":"2026-05-18T00:48:00.375094+00:00","updated_at":"2026-05-18T00:48:00.375094+00:00"}