{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:26ATPK5HPJGQCASZLWXJB7BVK6","short_pith_number":"pith:26ATPK5H","schema_version":"1.0","canonical_sha256":"d78137aba77a4d0102595dae90fc35579767664a97c64b9dd3be66129486f10b","source":{"kind":"arxiv","id":"1611.10080","version":1},"attestation_state":"computed","paper":{"title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chunhua Shen, Zifeng Wu","submitted_at":"2016-11-30T10:24:32Z","abstract_excerpt":"The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be the best way to increase performance, particularly given other limitations. Investigations into deep residual networks have also suggested that they may not in fact be operating as a single deep network, but rather as an ensemble of many relatively shallow networks. We examine these issues, and in doing so arrive at a new interpretation of the unravelled vi"},"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":"1611.10080","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-30T10:24:32Z","cross_cats_sorted":[],"title_canon_sha256":"6b587639b8f0557226c3949658c559bb36de7f6430a0334a25de887dda7386d3","abstract_canon_sha256":"1784f8ad7640e9e2567a8a129293112ba6c04e2bc8fe30fd04b1dc40a81abc81"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:56:11.243980Z","signature_b64":"yjVasexRKFvZF46NCD7vJBmpYQ/lzX96F8/2vmRc7/GzDQEjKg/fk+iVxew1+U63HQD72hquHLVLDktgzdywDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d78137aba77a4d0102595dae90fc35579767664a97c64b9dd3be66129486f10b","last_reissued_at":"2026-05-18T00:56:11.243519Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:56:11.243519Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Wider or Deeper: Revisiting the ResNet Model for Visual Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anton van den Hengel, Chunhua Shen, Zifeng Wu","submitted_at":"2016-11-30T10:24:32Z","abstract_excerpt":"The trend towards increasingly deep neural networks has been driven by a general observation that increasing depth increases the performance of a network. Recently, however, evidence has been amassing that simply increasing depth may not be the best way to increase performance, particularly given other limitations. Investigations into deep residual networks have also suggested that they may not in fact be operating as a single deep network, but rather as an ensemble of many relatively shallow networks. We examine these issues, and in doing so arrive at a new interpretation of the unravelled vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.10080","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":"1611.10080","created_at":"2026-05-18T00:56:11.243581+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.10080v1","created_at":"2026-05-18T00:56:11.243581+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.10080","created_at":"2026-05-18T00:56:11.243581+00:00"},{"alias_kind":"pith_short_12","alias_value":"26ATPK5HPJGQ","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"26ATPK5HPJGQCASZ","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"26ATPK5H","created_at":"2026-05-18T12:29:52.810259+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1907.07156","citing_title":"Efficient Segmentation: Learning Downsampling Near Semantic Boundaries","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10142","citing_title":"Scaling Vision Models Does Not Consistently Improve Localisation-Based Explanation Quality","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":86,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6","json":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6.json","graph_json":"https://pith.science/api/pith-number/26ATPK5HPJGQCASZLWXJB7BVK6/graph.json","events_json":"https://pith.science/api/pith-number/26ATPK5HPJGQCASZLWXJB7BVK6/events.json","paper":"https://pith.science/paper/26ATPK5H"},"agent_actions":{"view_html":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6","download_json":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6.json","view_paper":"https://pith.science/paper/26ATPK5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.10080&json=true","fetch_graph":"https://pith.science/api/pith-number/26ATPK5HPJGQCASZLWXJB7BVK6/graph.json","fetch_events":"https://pith.science/api/pith-number/26ATPK5HPJGQCASZLWXJB7BVK6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6/action/storage_attestation","attest_author":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6/action/author_attestation","sign_citation":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6/action/citation_signature","submit_replication":"https://pith.science/pith/26ATPK5HPJGQCASZLWXJB7BVK6/action/replication_record"}},"created_at":"2026-05-18T00:56:11.243581+00:00","updated_at":"2026-05-18T00:56:11.243581+00:00"}