{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:UZUW2GZZ25ZWXDGNIQRL2ZTMSR","short_pith_number":"pith:UZUW2GZZ","schema_version":"1.0","canonical_sha256":"a6696d1b39d7736b8ccd4422bd666c945bdbf93a5bc488909e0caba66f39fc45","source":{"kind":"arxiv","id":"1811.11553","version":3},"attestation_state":"computed","paper":{"title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Chengfei Wang, Long Mai, Michael A. Alcorn, Qi Li, Wei-shinn Ku, Zhitao Gong","submitted_at":"2018-11-28T13:39:27Z","abstract_excerpt":"Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial ones, which are common in real-world settings. In this paper, we present a framework for discovering DNN failures that harnesses 3D renderers and 3D models. That is, we estimate the parameters of a 3D renderer that cause a target DNN to misbehave in response to the rendered image. Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects "},"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":"1811.11553","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-11-28T13:39:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f9fb17a6d0470d62f673699ecdc412fdb66916fbb415744f469f6d54c5f74c7d","abstract_canon_sha256":"11767199c365ed46e0993a7c3e3f6fc524064a9f8a0378841a02b12645755d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:16.922309Z","signature_b64":"JVJ01UbaL8v56fepw1UrGfvB/yb1e9VdsOljnzf1YIDWa+kRhMErOBY9y3WmW7OHwlXysTqpEI8mav0xtIWqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6696d1b39d7736b8ccd4422bd666c945bdbf93a5bc488909e0caba66f39fc45","last_reissued_at":"2026-05-17T23:48:16.921745Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:16.921745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Strike (with) a Pose: Neural Networks Are Easily Fooled by Strange Poses of Familiar Objects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anh Nguyen, Chengfei Wang, Long Mai, Michael A. Alcorn, Qi Li, Wei-shinn Ku, Zhitao Gong","submitted_at":"2018-11-28T13:39:27Z","abstract_excerpt":"Despite excellent performance on stationary test sets, deep neural networks (DNNs) can fail to generalize to out-of-distribution (OoD) inputs, including natural, non-adversarial ones, which are common in real-world settings. In this paper, we present a framework for discovering DNN failures that harnesses 3D renderers and 3D models. That is, we estimate the parameters of a 3D renderer that cause a target DNN to misbehave in response to the rendered image. Using our framework and a self-assembled dataset of 3D objects, we investigate the vulnerability of DNNs to OoD poses of well-known objects "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.11553","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":"1811.11553","created_at":"2026-05-17T23:48:16.921816+00:00"},{"alias_kind":"arxiv_version","alias_value":"1811.11553v3","created_at":"2026-05-17T23:48:16.921816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.11553","created_at":"2026-05-17T23:48:16.921816+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZUW2GZZ25ZW","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZUW2GZZ25ZWXDGN","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZUW2GZZ","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"1906.11235","citing_title":"Invariance-inducing regularization using worst-case transformations suffices to boost accuracy and spatial robustness","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR","json":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR.json","graph_json":"https://pith.science/api/pith-number/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/graph.json","events_json":"https://pith.science/api/pith-number/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/events.json","paper":"https://pith.science/paper/UZUW2GZZ"},"agent_actions":{"view_html":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR","download_json":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR.json","view_paper":"https://pith.science/paper/UZUW2GZZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1811.11553&json=true","fetch_graph":"https://pith.science/api/pith-number/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/graph.json","fetch_events":"https://pith.science/api/pith-number/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/action/storage_attestation","attest_author":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/action/author_attestation","sign_citation":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/action/citation_signature","submit_replication":"https://pith.science/pith/UZUW2GZZ25ZWXDGNIQRL2ZTMSR/action/replication_record"}},"created_at":"2026-05-17T23:48:16.921816+00:00","updated_at":"2026-05-17T23:48:16.921816+00:00"}