{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:2Q6YBCHJMWBRGZT47GIUX3IVQJ","short_pith_number":"pith:2Q6YBCHJ","schema_version":"1.0","canonical_sha256":"d43d8088e9658313667cf9914bed1582544f5e44499e3273d342027a3598e8ca","source":{"kind":"arxiv","id":"1708.02862","version":1},"attestation_state":"computed","paper":{"title":"WebVision Database: Visual Learning and Understanding from Web Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eirikur Agustsson, Limin Wang, Luc Van Gool, Wei Li, Wen Li","submitted_at":"2017-08-09T14:59:30Z","abstract_excerpt":"In this paper, we present a study on learning visual recognition models from large scale noisy web data. We build a new database called WebVision, which contains more than $2.4$ million web images crawled from the Internet by using queries generated from the 1,000 semantic concepts of the benchmark ILSVRC 2012 dataset. Meta information along with those web images (e.g., title, description, tags, etc.) are also crawled. A validation set and test set containing human annotated images are also provided to facilitate algorithmic development. Based on our new database, we obtain a few interesting o"},"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":"1708.02862","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-08-09T14:59:30Z","cross_cats_sorted":[],"title_canon_sha256":"172892028ed623f1b42e2ac07310d04102d0821c484c5f4d0edfc74c99848b9c","abstract_canon_sha256":"8c8987f203975ce569b7cc5cacedad68f8eda87f93ea3b14709cc81a47ea0419"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:38:19.304205Z","signature_b64":"04w22sZiH3u/WhUP5gRT0UJnaDUprtp62FUVB9gh/0H5GH3KfvXAWQrH8LwfZC8/jRyJrKBcvSgpmVjh8VVNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d43d8088e9658313667cf9914bed1582544f5e44499e3273d342027a3598e8ca","last_reissued_at":"2026-05-18T00:38:19.303387Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:38:19.303387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebVision Database: Visual Learning and Understanding from Web Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Eirikur Agustsson, Limin Wang, Luc Van Gool, Wei Li, Wen Li","submitted_at":"2017-08-09T14:59:30Z","abstract_excerpt":"In this paper, we present a study on learning visual recognition models from large scale noisy web data. We build a new database called WebVision, which contains more than $2.4$ million web images crawled from the Internet by using queries generated from the 1,000 semantic concepts of the benchmark ILSVRC 2012 dataset. Meta information along with those web images (e.g., title, description, tags, etc.) are also crawled. A validation set and test set containing human annotated images are also provided to facilitate algorithmic development. Based on our new database, we obtain a few interesting o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1708.02862","kind":"arxiv","version":1},"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":"1708.02862","created_at":"2026-05-18T00:38:19.303537+00:00"},{"alias_kind":"arxiv_version","alias_value":"1708.02862v1","created_at":"2026-05-18T00:38:19.303537+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1708.02862","created_at":"2026-05-18T00:38:19.303537+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q6YBCHJMWBR","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q6YBCHJMWBRGZT4","created_at":"2026-05-18T12:30:55.937587+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q6YBCHJ","created_at":"2026-05-18T12:30:55.937587+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.23254","citing_title":"CARE: Class-Adaptive Expert Consensus for Reliable Learning with Long-Tailed Noisy Labels","ref_index":132,"is_internal_anchor":true},{"citing_arxiv_id":"1907.11384","citing_title":"Product Image Recognition with Guidance Learning and Noisy Supervision","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2405.12969","citing_title":"EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labels","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2408.11338","citing_title":"Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.23125","citing_title":"Learning from Imperfect Text Guidance: Robust Long-Tail Visual Recognition with High-Noise Label","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07306","citing_title":"Beyond Loss Values: Robust Dynamic Pruning via Loss Trajectory Alignment","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16562","citing_title":"See Through the Noise: Improving Domain Generalization in Gaze Estimation","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ","json":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ.json","graph_json":"https://pith.science/api/pith-number/2Q6YBCHJMWBRGZT47GIUX3IVQJ/graph.json","events_json":"https://pith.science/api/pith-number/2Q6YBCHJMWBRGZT47GIUX3IVQJ/events.json","paper":"https://pith.science/paper/2Q6YBCHJ"},"agent_actions":{"view_html":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ","download_json":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ.json","view_paper":"https://pith.science/paper/2Q6YBCHJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1708.02862&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q6YBCHJMWBRGZT47GIUX3IVQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q6YBCHJMWBRGZT47GIUX3IVQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ/action/storage_attestation","attest_author":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ/action/author_attestation","sign_citation":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ/action/citation_signature","submit_replication":"https://pith.science/pith/2Q6YBCHJMWBRGZT47GIUX3IVQJ/action/replication_record"}},"created_at":"2026-05-18T00:38:19.303537+00:00","updated_at":"2026-05-18T00:38:19.303537+00:00"}