{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:5VMCNHWCSYTUWPWSC4FHUDG4H7","short_pith_number":"pith:5VMCNHWC","schema_version":"1.0","canonical_sha256":"ed58269ec296274b3ed2170a7a0cdc3ffca3bc9ee47c83a460be76ea52c535ee","source":{"kind":"arxiv","id":"1311.2524","version":5},"attestation_state":"computed","paper":{"title":"Rich feature hierarchies for accurate object detection and semantic segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Jitendra Malik, Ross Girshick, Trevor Darrell","submitted_at":"2013-11-11T18:43:49Z","abstract_excerpt":"Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals i"},"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":"1311.2524","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2013-11-11T18:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"2f45d5fadccb80e4a93dd2950a58ce4afdd8c265854e63e9a99cd3669d87c2cd","abstract_canon_sha256":"43d7a2278917a8a4fec94de6745231c2ba60b24225a289cf4aa2a0527f1aa9dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:39:38.275835Z","signature_b64":"C2c0igaIam40l7G5c81rhieGvhNOSL0PAVpdCFc4rSOvnXiLFGW6MVIJw07tw748nrbdTfDs+CSJx/NgDKLlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed58269ec296274b3ed2170a7a0cdc3ffca3bc9ee47c83a460be76ea52c535ee","last_reissued_at":"2026-05-18T02:39:38.275426Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:39:38.275426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rich feature hierarchies for accurate object detection and semantic segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jeff Donahue, Jitendra Malik, Ross Girshick, Trevor Darrell","submitted_at":"2013-11-11T18:43:49Z","abstract_excerpt":"Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1311.2524","kind":"arxiv","version":5},"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":"1311.2524","created_at":"2026-05-18T02:39:38.275489+00:00"},{"alias_kind":"arxiv_version","alias_value":"1311.2524v5","created_at":"2026-05-18T02:39:38.275489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1311.2524","created_at":"2026-05-18T02:39:38.275489+00:00"},{"alias_kind":"pith_short_12","alias_value":"5VMCNHWCSYTU","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_16","alias_value":"5VMCNHWCSYTUWPWS","created_at":"2026-05-18T12:27:34.582898+00:00"},{"alias_kind":"pith_short_8","alias_value":"5VMCNHWC","created_at":"2026-05-18T12:27:34.582898+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.00408","citing_title":"GarmNet: Improving Global with Local Perception for Robotic Laundry Folding","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"1907.06838","citing_title":"Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"1312.6199","citing_title":"Intriguing properties of neural networks","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20030","citing_title":"Learning to count small and clustered objects with application to bacterial colonies","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2511.16624","citing_title":"SAM 3D: 3Dfy Anything in Images","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7","json":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7.json","graph_json":"https://pith.science/api/pith-number/5VMCNHWCSYTUWPWSC4FHUDG4H7/graph.json","events_json":"https://pith.science/api/pith-number/5VMCNHWCSYTUWPWSC4FHUDG4H7/events.json","paper":"https://pith.science/paper/5VMCNHWC"},"agent_actions":{"view_html":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7","download_json":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7.json","view_paper":"https://pith.science/paper/5VMCNHWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1311.2524&json=true","fetch_graph":"https://pith.science/api/pith-number/5VMCNHWCSYTUWPWSC4FHUDG4H7/graph.json","fetch_events":"https://pith.science/api/pith-number/5VMCNHWCSYTUWPWSC4FHUDG4H7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7/action/storage_attestation","attest_author":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7/action/author_attestation","sign_citation":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7/action/citation_signature","submit_replication":"https://pith.science/pith/5VMCNHWCSYTUWPWSC4FHUDG4H7/action/replication_record"}},"created_at":"2026-05-18T02:39:38.275489+00:00","updated_at":"2026-05-18T02:39:38.275489+00:00"}