{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:3CHUHHJ7H6ADMFVTC34KU5RPL2","short_pith_number":"pith:3CHUHHJ7","schema_version":"1.0","canonical_sha256":"d88f439d3f3f803616b316f8aa762f5ead731db23a5010d1cad15e76b61e5ba6","source":{"kind":"arxiv","id":"1312.6229","version":4},"attestation_state":"computed","paper":{"title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Eigen, Michael Mathieu, Pierre Sermanet, Rob Fergus, Xiang Zhang, Yann LeCun","submitted_at":"2013-12-21T09:52:33Z","abstract_excerpt":"We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet La"},"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":"1312.6229","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-12-21T09:52:33Z","cross_cats_sorted":[],"title_canon_sha256":"75231db0be3ec88c1201a34859cd8df88794d7fdfd5556a6101d30e326694840","abstract_canon_sha256":"dea27451683c220fd7a3813b09b5677e32f08522c66f4bf9319ffbe4c33c3555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:58:21.399395Z","signature_b64":"Kxfcgj4Qyb5CU6ydL4ihfUac7ZPZnc5jYGe82TPkean2CMh3QxgCpJfLHkLyMPBWAhQsWRknSwED0GWKgJ4ACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d88f439d3f3f803616b316f8aa762f5ead731db23a5010d1cad15e76b61e5ba6","last_reissued_at":"2026-05-18T02:58:21.398638Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:58:21.398638Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Eigen, Michael Mathieu, Pierre Sermanet, Rob Fergus, Xiang Zhang, Yann LeCun","submitted_at":"2013-12-21T09:52:33Z","abstract_excerpt":"We present an integrated framework for using Convolutional Networks for classification, localization and detection. We show how a multiscale and sliding window approach can be efficiently implemented within a ConvNet. We also introduce a novel deep learning approach to localization by learning to predict object boundaries. Bounding boxes are then accumulated rather than suppressed in order to increase detection confidence. We show that different tasks can be learned simultaneously using a single shared network. This integrated framework is the winner of the localization task of the ImageNet La"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.6229","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":"1312.6229","created_at":"2026-05-18T02:58:21.398764+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.6229v4","created_at":"2026-05-18T02:58:21.398764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.6229","created_at":"2026-05-18T02:58:21.398764+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CHUHHJ7H6AD","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CHUHHJ7H6ADMFVT","created_at":"2026-05-18T12:27:32.513160+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CHUHHJ7","created_at":"2026-05-18T12:27:32.513160+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"1907.05287","citing_title":"A Regularized Convolutional Neural Network for Semantic Image Segmentation","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"1907.04444","citing_title":"A review on deep learning techniques for 3D sensed data classification","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2601.07859","citing_title":"Differentiable Surrogate for Detector Simulation and Design with Diffusion Models","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2204.00598","citing_title":"Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"1706.05587","citing_title":"Rethinking Atrous Convolution for Semantic Image Segmentation","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24599","citing_title":"DETOUR: A Practical Backdoor Attack against Object Detection","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2","json":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2.json","graph_json":"https://pith.science/api/pith-number/3CHUHHJ7H6ADMFVTC34KU5RPL2/graph.json","events_json":"https://pith.science/api/pith-number/3CHUHHJ7H6ADMFVTC34KU5RPL2/events.json","paper":"https://pith.science/paper/3CHUHHJ7"},"agent_actions":{"view_html":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2","download_json":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2.json","view_paper":"https://pith.science/paper/3CHUHHJ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.6229&json=true","fetch_graph":"https://pith.science/api/pith-number/3CHUHHJ7H6ADMFVTC34KU5RPL2/graph.json","fetch_events":"https://pith.science/api/pith-number/3CHUHHJ7H6ADMFVTC34KU5RPL2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2/action/storage_attestation","attest_author":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2/action/author_attestation","sign_citation":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2/action/citation_signature","submit_replication":"https://pith.science/pith/3CHUHHJ7H6ADMFVTC34KU5RPL2/action/replication_record"}},"created_at":"2026-05-18T02:58:21.398764+00:00","updated_at":"2026-05-18T02:58:21.398764+00:00"}