{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:4SA7SRYEWAZAXRBL4VTHKRPIXI","short_pith_number":"pith:4SA7SRYE","schema_version":"1.0","canonical_sha256":"e481f94704b0320bc42be5667545e8ba0f688f3039c83e7436bcaebd0257ba60","source":{"kind":"arxiv","id":"1807.03247","version":2},"attestation_state":"computed","paper":{"title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alex Sergeev, Eric Frank, Felipe Petroski Such, Jason Yosinski, Joel Lehman, Piero Molino, Rosanne Liu","submitted_at":"2018-07-09T15:48:08Z","abstract_excerpt":"Few ideas have enjoyed as large an impact on deep learning as convolution. For any problem involving pixels or spatial representations, common intuition holds that convolutional neural networks may be appropriate. In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x,y) Cartesian space and one-hot pixel space. Although convolutional networks would seem appropriate for this task, we show that they fail spectacularly. We demonstrate and carefully analyze the fail"},"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":"1807.03247","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2018-07-09T15:48:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"7e1ce6fd321c65696a85272ba73a6c1deb87729cc996ce76d43886716ebbbed2","abstract_canon_sha256":"2a6db73102699c63cb35d26b9f78e69ced6212a001cd5bd07bfcb5fcd02520ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:22.542654Z","signature_b64":"VjH9o6IvFnW4uTLBLCSxt2Wy/kyVXqBX7Buo0cFTS2J5Iy44wqStTAsRXK/dIiJu2laomFs3LETjbBlK+161DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e481f94704b0320bc42be5667545e8ba0f688f3039c83e7436bcaebd0257ba60","last_reissued_at":"2026-05-17T23:59:22.542250Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:22.542250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alex Sergeev, Eric Frank, Felipe Petroski Such, Jason Yosinski, Joel Lehman, Piero Molino, Rosanne Liu","submitted_at":"2018-07-09T15:48:08Z","abstract_excerpt":"Few ideas have enjoyed as large an impact on deep learning as convolution. For any problem involving pixels or spatial representations, common intuition holds that convolutional neural networks may be appropriate. In this paper we show a striking counterexample to this intuition via the seemingly trivial coordinate transform problem, which simply requires learning a mapping between coordinates in (x,y) Cartesian space and one-hot pixel space. Although convolutional networks would seem appropriate for this task, we show that they fail spectacularly. We demonstrate and carefully analyze the fail"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.03247","kind":"arxiv","version":2},"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":"1807.03247","created_at":"2026-05-17T23:59:22.542304+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.03247v2","created_at":"2026-05-17T23:59:22.542304+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.03247","created_at":"2026-05-17T23:59:22.542304+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SA7SRYEWAZA","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SA7SRYEWAZAXRBL","created_at":"2026-05-18T12:32:05.422762+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SA7SRYE","created_at":"2026-05-18T12:32:05.422762+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1906.08945","citing_title":"Rules of the Road: Predicting Driving Behavior with a Convolutional Model of Semantic Interactions","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"1906.11557","citing_title":"Flexible SVBRDF Capture with a Multi-Image Deep Network","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.10237","citing_title":"The Benefits of Temporal Correlations: SGD Learns k-Juntas from Random Walks Efficiently","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23799","citing_title":"VitaminP: cross-modal learning enables whole-cell segmentation from routine histology","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI","json":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI.json","graph_json":"https://pith.science/api/pith-number/4SA7SRYEWAZAXRBL4VTHKRPIXI/graph.json","events_json":"https://pith.science/api/pith-number/4SA7SRYEWAZAXRBL4VTHKRPIXI/events.json","paper":"https://pith.science/paper/4SA7SRYE"},"agent_actions":{"view_html":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI","download_json":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI.json","view_paper":"https://pith.science/paper/4SA7SRYE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.03247&json=true","fetch_graph":"https://pith.science/api/pith-number/4SA7SRYEWAZAXRBL4VTHKRPIXI/graph.json","fetch_events":"https://pith.science/api/pith-number/4SA7SRYEWAZAXRBL4VTHKRPIXI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI/action/storage_attestation","attest_author":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI/action/author_attestation","sign_citation":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI/action/citation_signature","submit_replication":"https://pith.science/pith/4SA7SRYEWAZAXRBL4VTHKRPIXI/action/replication_record"}},"created_at":"2026-05-17T23:59:22.542304+00:00","updated_at":"2026-05-17T23:59:22.542304+00:00"}