{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OXUQCJ6T73XP5QFV4LTTCDJNRB","short_pith_number":"pith:OXUQCJ6T","schema_version":"1.0","canonical_sha256":"75e90127d3feeefec0b5e2e7310d2d885d72d9001b62629b48aabc72e606de9e","source":{"kind":"arxiv","id":"2211.09983","version":3},"attestation_state":"computed","paper":{"title":"Universal Approximation Property of Fully Convolutional Neural Networks with Zero Padding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Geonho Hwang, Myungjoo Kang","submitted_at":"2022-11-18T02:04:16Z","abstract_excerpt":"The Convolutional Neural Network (CNN) is one of the most prominent neural network architectures in deep learning. Despite its widespread adoption, our understanding of its universal approximation properties has been limited due to its intricate nature. CNNs inherently function as tensor-to-tensor mappings, preserving the spatial structure of input data. However, limited research has explored the universal approximation properties of fully convolutional neural networks as arbitrary continuous tensor-to-tensor functions. In this study, we demonstrate that CNNs, when utilizing zero padding, can "},"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":"2211.09983","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2022-11-18T02:04:16Z","cross_cats_sorted":[],"title_canon_sha256":"189858471ca64c7624eb540f061e51cc8e83cb897a59e348b1f617858caf50ca","abstract_canon_sha256":"e5492c4f6110c571911628e50ac3065d5ee1c8ccad5963c0586bbe2dab79aeee"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:42.087174Z","signature_b64":"UqGMW3hKHaHxtIs10IYoZky0q3W9xLUsJN8IxXn78RhikEg9EUDeZnxk84RXD9SQw26pAW0OD7nHx33jSBedBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75e90127d3feeefec0b5e2e7310d2d885d72d9001b62629b48aabc72e606de9e","last_reissued_at":"2026-07-05T07:19:42.086729Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:42.086729Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Universal Approximation Property of Fully Convolutional Neural Networks with Zero Padding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Geonho Hwang, Myungjoo Kang","submitted_at":"2022-11-18T02:04:16Z","abstract_excerpt":"The Convolutional Neural Network (CNN) is one of the most prominent neural network architectures in deep learning. Despite its widespread adoption, our understanding of its universal approximation properties has been limited due to its intricate nature. CNNs inherently function as tensor-to-tensor mappings, preserving the spatial structure of input data. However, limited research has explored the universal approximation properties of fully convolutional neural networks as arbitrary continuous tensor-to-tensor functions. In this study, we demonstrate that CNNs, when utilizing zero padding, can "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09983","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2211.09983/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2211.09983","created_at":"2026-07-05T07:19:42.086798+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.09983v3","created_at":"2026-07-05T07:19:42.086798+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09983","created_at":"2026-07-05T07:19:42.086798+00:00"},{"alias_kind":"pith_short_12","alias_value":"OXUQCJ6T73XP","created_at":"2026-07-05T07:19:42.086798+00:00"},{"alias_kind":"pith_short_16","alias_value":"OXUQCJ6T73XP5QFV","created_at":"2026-07-05T07:19:42.086798+00:00"},{"alias_kind":"pith_short_8","alias_value":"OXUQCJ6T","created_at":"2026-07-05T07:19:42.086798+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.09456","citing_title":"IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB","json":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB.json","graph_json":"https://pith.science/api/pith-number/OXUQCJ6T73XP5QFV4LTTCDJNRB/graph.json","events_json":"https://pith.science/api/pith-number/OXUQCJ6T73XP5QFV4LTTCDJNRB/events.json","paper":"https://pith.science/paper/OXUQCJ6T"},"agent_actions":{"view_html":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB","download_json":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB.json","view_paper":"https://pith.science/paper/OXUQCJ6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.09983&json=true","fetch_graph":"https://pith.science/api/pith-number/OXUQCJ6T73XP5QFV4LTTCDJNRB/graph.json","fetch_events":"https://pith.science/api/pith-number/OXUQCJ6T73XP5QFV4LTTCDJNRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB/action/storage_attestation","attest_author":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB/action/author_attestation","sign_citation":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB/action/citation_signature","submit_replication":"https://pith.science/pith/OXUQCJ6T73XP5QFV4LTTCDJNRB/action/replication_record"}},"created_at":"2026-07-05T07:19:42.086798+00:00","updated_at":"2026-07-05T07:19:42.086798+00:00"}