{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:XVEDW7GHIAHVD5YCX3KIVZY2TN","short_pith_number":"pith:XVEDW7GH","schema_version":"1.0","canonical_sha256":"bd483b7cc7400f51f702bed48ae71a9b69ac994d05e3cf315ecf135fff9c3f66","source":{"kind":"arxiv","id":"1312.6082","version":4},"attestation_state":"computed","paper":{"title":"Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ian J. Goodfellow, Julian Ibarz, Sacha Arnoud, Vinay Shet, Yaroslav Bulatov","submitted_at":"2013-12-20T19:25:44Z","abstract_excerpt":"Recognizing arbitrary multi-character text in unconstrained natural photographs is a hard problem. In this paper, we address an equally hard sub-problem in this domain viz. recognizing arbitrary multi-digit numbers from Street View imagery. Traditional approaches to solve this problem typically separate out the localization, segmentation, and recognition steps. In this paper we propose a unified approach that integrates these three steps via the use of a deep convolutional neural network that operates directly on the image pixels. We employ the DistBelief implementation of deep neural networks"},"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":"1312.6082","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-12-20T19:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"edc65315bffd7ab6b758bb25a9865bce2fc1017eb28876423957b944de88a079","abstract_canon_sha256":"914dfc4b842c18953a77636e83e8d0b62fef9a76e5400ada049b00fab589195d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:54:20.992224Z","signature_b64":"LE7naW7YWnAe7tU1iHJrp3bHHqzpAsKs+JWOfXnBzwpOa4AwxW0WdhqnknoLdR2bnEl+sR3wCL/9EzLTrHetDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd483b7cc7400f51f702bed48ae71a9b69ac994d05e3cf315ecf135fff9c3f66","last_reissued_at":"2026-05-18T02:54:20.991808Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:54:20.991808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-digit Number Recognition from Street View Imagery using Deep Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Ian J. Goodfellow, Julian Ibarz, Sacha Arnoud, Vinay Shet, Yaroslav Bulatov","submitted_at":"2013-12-20T19:25:44Z","abstract_excerpt":"Recognizing arbitrary multi-character text in unconstrained natural photographs is a hard problem. In this paper, we address an equally hard sub-problem in this domain viz. recognizing arbitrary multi-digit numbers from Street View imagery. Traditional approaches to solve this problem typically separate out the localization, segmentation, and recognition steps. In this paper we propose a unified approach that integrates these three steps via the use of a deep convolutional neural network that operates directly on the image pixels. We employ the DistBelief implementation of deep neural networks"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.6082","kind":"arxiv","version":4},"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":"1312.6082","created_at":"2026-05-18T02:54:20.991876+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.6082v4","created_at":"2026-05-18T02:54:20.991876+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.6082","created_at":"2026-05-18T02:54:20.991876+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVEDW7GHIAHV","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVEDW7GHIAHVD5YC","created_at":"2026-05-18T12:28:06.772260+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVEDW7GH","created_at":"2026-05-18T12:28:06.772260+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2404.10370","citing_title":"Know Yourself Better: Diverse Object-Related Features Improve Open Set Recognition","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12340","citing_title":"Online Learning-to-Defer with Varying Experts","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2509.09926","citing_title":"LoFT: Parameter-Efficient Fine-Tuning for Long-tailed Semi-Supervised Learning in Open-World Scenarios","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2507.05595","citing_title":"PaddleOCR 3.0 Technical Report","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12340","citing_title":"Online Learning-to-Defer with Varying Experts","ref_index":104,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN","json":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN.json","graph_json":"https://pith.science/api/pith-number/XVEDW7GHIAHVD5YCX3KIVZY2TN/graph.json","events_json":"https://pith.science/api/pith-number/XVEDW7GHIAHVD5YCX3KIVZY2TN/events.json","paper":"https://pith.science/paper/XVEDW7GH"},"agent_actions":{"view_html":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN","download_json":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN.json","view_paper":"https://pith.science/paper/XVEDW7GH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.6082&json=true","fetch_graph":"https://pith.science/api/pith-number/XVEDW7GHIAHVD5YCX3KIVZY2TN/graph.json","fetch_events":"https://pith.science/api/pith-number/XVEDW7GHIAHVD5YCX3KIVZY2TN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN/action/storage_attestation","attest_author":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN/action/author_attestation","sign_citation":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN/action/citation_signature","submit_replication":"https://pith.science/pith/XVEDW7GHIAHVD5YCX3KIVZY2TN/action/replication_record"}},"created_at":"2026-05-18T02:54:20.991876+00:00","updated_at":"2026-05-18T02:54:20.991876+00:00"}