{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:XDPHQQ5E66TDRTKBVVDGH7TPYL","short_pith_number":"pith:XDPHQQ5E","schema_version":"1.0","canonical_sha256":"b8de7843a4f7a638cd41ad4663fe6fc2daab304ca4396ab8e385b6b30d8368cd","source":{"kind":"arxiv","id":"1512.04785","version":2},"attestation_state":"computed","paper":{"title":"On Deep Representation Learning from Noisy Web Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Adrian Popescu, Alexandru Ginsca, Herv\\'e Le Borgne, Phong D. Vo","submitted_at":"2015-12-15T13:57:39Z","abstract_excerpt":"The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has not been validated on convolutional networks (convnet) -- one of best performing deep models -- because of their supervised regime. While unsupervised alternatives are not so good as convnet in generalizing the learned model to new domains, we use convnet to leverage semi-supervised representation learning. Our approach is to use massive amounts of unlabeled "},"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":"1512.04785","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2015-12-15T13:57:39Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"de05e7b105d5a5d5b60bf5fbc321c66411f5782b9fced67a9c7ed9914d0d5b6a","abstract_canon_sha256":"fa2db981b9fa0735e513f92e2ec8b445359b5c3fa1fc97c010145d1f222d23b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:59.593255Z","signature_b64":"RgPUeXcwQTKACgRPiYAaOFe9pRjfS8Lv0+0Hgd3l1mIg8jVP+j4ee4Ejl2sWJfyRCIzZzSPaaKlg54q/QWElBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8de7843a4f7a638cd41ad4663fe6fc2daab304ca4396ab8e385b6b30d8368cd","last_reissued_at":"2026-05-18T01:10:59.592775Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:59.592775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Deep Representation Learning from Noisy Web Images","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Adrian Popescu, Alexandru Ginsca, Herv\\'e Le Borgne, Phong D. Vo","submitted_at":"2015-12-15T13:57:39Z","abstract_excerpt":"The keep-growing content of Web images may be the next important data source to scale up deep neural networks, which recently obtained a great success in the ImageNet classification challenge and related tasks. This prospect, however, has not been validated on convolutional networks (convnet) -- one of best performing deep models -- because of their supervised regime. While unsupervised alternatives are not so good as convnet in generalizing the learned model to new domains, we use convnet to leverage semi-supervised representation learning. Our approach is to use massive amounts of unlabeled "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1512.04785","kind":"arxiv","version":2},"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":"1512.04785","created_at":"2026-05-18T01:10:59.592850+00:00"},{"alias_kind":"arxiv_version","alias_value":"1512.04785v2","created_at":"2026-05-18T01:10:59.592850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1512.04785","created_at":"2026-05-18T01:10:59.592850+00:00"},{"alias_kind":"pith_short_12","alias_value":"XDPHQQ5E66TD","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_16","alias_value":"XDPHQQ5E66TDRTKB","created_at":"2026-05-18T12:29:50.041715+00:00"},{"alias_kind":"pith_short_8","alias_value":"XDPHQQ5E","created_at":"2026-05-18T12:29:50.041715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL","json":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL.json","graph_json":"https://pith.science/api/pith-number/XDPHQQ5E66TDRTKBVVDGH7TPYL/graph.json","events_json":"https://pith.science/api/pith-number/XDPHQQ5E66TDRTKBVVDGH7TPYL/events.json","paper":"https://pith.science/paper/XDPHQQ5E"},"agent_actions":{"view_html":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL","download_json":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL.json","view_paper":"https://pith.science/paper/XDPHQQ5E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1512.04785&json=true","fetch_graph":"https://pith.science/api/pith-number/XDPHQQ5E66TDRTKBVVDGH7TPYL/graph.json","fetch_events":"https://pith.science/api/pith-number/XDPHQQ5E66TDRTKBVVDGH7TPYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL/action/storage_attestation","attest_author":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL/action/author_attestation","sign_citation":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL/action/citation_signature","submit_replication":"https://pith.science/pith/XDPHQQ5E66TDRTKBVVDGH7TPYL/action/replication_record"}},"created_at":"2026-05-18T01:10:59.592850+00:00","updated_at":"2026-05-18T01:10:59.592850+00:00"}