{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:A7ZECEEBFX7NB346ELFQ7UOMB5","short_pith_number":"pith:A7ZECEEB","schema_version":"1.0","canonical_sha256":"07f24110812dfed0ef9e22cb0fd1cc0f5691c4c62d446f713c09b277f1a5438b","source":{"kind":"arxiv","id":"1409.0575","version":3},"attestation_state":"computed","paper":{"title":"ImageNet Large Scale Visual Recognition Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Khosla, Alexander C. Berg, Andrej Karpathy, Hao Su, Jia Deng, Jonathan Krause, Li Fei-Fei, Michael Bernstein, Olga Russakovsky, Sanjeev Satheesh, Sean Ma, Zhiheng Huang","submitted_at":"2014-09-01T22:29:38Z","abstract_excerpt":"The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions.\n  This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of"},"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":"1409.0575","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2014-09-01T22:29:38Z","cross_cats_sorted":[],"title_canon_sha256":"21013e6c36be20d65e9b5ca40030fa5072493862d2279fae88a6789240060633","abstract_canon_sha256":"6cb3a70839db9b122c024f3835abf67d0ed25a77ecb71f369c913ae1465ddb5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:28:20.616993Z","signature_b64":"3FhfK2Z2aQlbU1qU0ss0lV/cKvWEXGo+rUGG6OkYT3NNUPyvVbrCUSE3TTKbQ7aYs2rNBT33XjSPM8QHB02ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07f24110812dfed0ef9e22cb0fd1cc0f5691c4c62d446f713c09b277f1a5438b","last_reissued_at":"2026-05-18T02:28:20.616285Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:28:20.616285Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ImageNet Large Scale Visual Recognition Challenge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Khosla, Alexander C. Berg, Andrej Karpathy, Hao Su, Jia Deng, Jonathan Krause, Li Fei-Fei, Michael Bernstein, Olga Russakovsky, Sanjeev Satheesh, Sean Ma, Zhiheng Huang","submitted_at":"2014-09-01T22:29:38Z","abstract_excerpt":"The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds of object categories and millions of images. The challenge has been run annually from 2010 to present, attracting participation from more than fifty institutions.\n  This paper describes the creation of this benchmark dataset and the advances in object recognition that have been possible as a result. We discuss the challenges of collecting large-scale ground truth annotation, highlight key breakthroughs in categorical object recognition, provide a detailed analysis of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.0575","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":""},"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":"1409.0575","created_at":"2026-05-18T02:28:20.616417+00:00"},{"alias_kind":"arxiv_version","alias_value":"1409.0575v3","created_at":"2026-05-18T02:28:20.616417+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.0575","created_at":"2026-05-18T02:28:20.616417+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7ZECEEBFX7N","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7ZECEEBFX7NB346","created_at":"2026-05-18T12:28:19.803747+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7ZECEEB","created_at":"2026-05-18T12:28:19.803747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":8,"sample":[{"citing_arxiv_id":"1907.08822","citing_title":"PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2208.14649","citing_title":"DetailCLIP: Injecting Image Details into CLIP's Feature Space","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2504.13850","citing_title":"FedOptima: Optimizing Resource Utilization in Federated Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2603.13652","citing_title":"Causal Attribution via Activation Patching","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2506.08514","citing_title":"DiffGradCAM: A Class Activation Map Using the Full Model Decision to Solve Unaddressed Adversarial Attacks","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2509.14448","citing_title":"VCBench: Benchmarking LLMs in Venture Capital","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2411.04983","citing_title":"DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planning","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05243","citing_title":"CORP: Closed-Form One-shot Representation-Preserving Structured Pruning for Transformers","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"1712.00409","citing_title":"Deep Learning Scaling is Predictable, Empirically","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"1511.06939","citing_title":"Session-based Recommendations with Recurrent Neural Networks","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21330","citing_title":"Teacher-Guided Routing for Sparse Vision Mixture-of-Experts","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10970","citing_title":"Using Deep Learning Models Pretrained by Self-Supervised Learning for Protein Localization","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08837","citing_title":"Discrete Meanflow Training Curriculum","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"1512.03385","citing_title":"Deep Residual Learning for Image Recognition","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14570","citing_title":"Deepfake Detection Generalization with Diffusion Noise","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5","json":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5.json","graph_json":"https://pith.science/api/pith-number/A7ZECEEBFX7NB346ELFQ7UOMB5/graph.json","events_json":"https://pith.science/api/pith-number/A7ZECEEBFX7NB346ELFQ7UOMB5/events.json","paper":"https://pith.science/paper/A7ZECEEB"},"agent_actions":{"view_html":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5","download_json":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5.json","view_paper":"https://pith.science/paper/A7ZECEEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1409.0575&json=true","fetch_graph":"https://pith.science/api/pith-number/A7ZECEEBFX7NB346ELFQ7UOMB5/graph.json","fetch_events":"https://pith.science/api/pith-number/A7ZECEEBFX7NB346ELFQ7UOMB5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5/action/storage_attestation","attest_author":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5/action/author_attestation","sign_citation":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5/action/citation_signature","submit_replication":"https://pith.science/pith/A7ZECEEBFX7NB346ELFQ7UOMB5/action/replication_record"}},"created_at":"2026-05-18T02:28:20.616417+00:00","updated_at":"2026-05-18T02:28:20.616417+00:00"}