{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VXNPUZLCFDDJRVGXUNVD42IRW2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"988338a47a2ce17a4847458d4668f653ad9bd813045b5a1c28fa41a8aa81f6a8","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-23T03:58:10Z","title_canon_sha256":"2ae35d658a9efcc0d17ee15c19129cd2e2c251ce36fe1241e6c8afb292e6a5f7"},"schema_version":"1.0","source":{"id":"2101.09412","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.09412","created_at":"2026-07-05T02:09:18Z"},{"alias_kind":"arxiv_version","alias_value":"2101.09412v1","created_at":"2026-07-05T02:09:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.09412","created_at":"2026-07-05T02:09:18Z"},{"alias_kind":"pith_short_12","alias_value":"VXNPUZLCFDDJ","created_at":"2026-07-05T02:09:18Z"},{"alias_kind":"pith_short_16","alias_value":"VXNPUZLCFDDJRVGX","created_at":"2026-07-05T02:09:18Z"},{"alias_kind":"pith_short_8","alias_value":"VXNPUZLC","created_at":"2026-07-05T02:09:18Z"}],"graph_snapshots":[{"event_id":"sha256:5605ca1a4bacfb530ed51886b47ff0e6f4e49a12bb47b39596230c79a7025784","target":"graph","created_at":"2026-07-05T02:09:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2101.09412/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Labeling objects at a subordinate level typically requires expert knowledge, which is not always available when using random annotators. As such, learning directly from web images for fine-grained recognition has attracted broad attention. However, the presence of label noise and hard examples in web images are two obstacles for training robust fine-grained recognition models. Therefore, in this paper, we propose a novel approach for removing irrelevant samples from real-world web images during training, while employing useful hard examples to update the network. Thus, our approach can allevia","authors_text":"Chuanyi Zhang, Fumin Shen, Huafeng Liu, Jian Zhang, Xiushen Wei, Yazhou Yao, Zhenmin Tang","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-23T03:58:10Z","title":"Exploiting Web Images for Fine-Grained Visual Recognition by Eliminating Noisy Samples and Utilizing Hard Ones"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.09412","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ccd116ebe5264490fad07e14c48d2fd25a0479f3cc0933cf091f9c82e66786a7","target":"record","created_at":"2026-07-05T02:09:18Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"988338a47a2ce17a4847458d4668f653ad9bd813045b5a1c28fa41a8aa81f6a8","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-01-23T03:58:10Z","title_canon_sha256":"2ae35d658a9efcc0d17ee15c19129cd2e2c251ce36fe1241e6c8afb292e6a5f7"},"schema_version":"1.0","source":{"id":"2101.09412","kind":"arxiv","version":1}},"canonical_sha256":"addafa656228c698d4d7a36a3e6911b68ef3bd7ca2a28917b042197e7d4f54dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"addafa656228c698d4d7a36a3e6911b68ef3bd7ca2a28917b042197e7d4f54dc","first_computed_at":"2026-07-05T02:09:18.379467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:09:18.379467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GgZx+5q6+3HOUWlPSYCZa7UQpH5hh7ThX3u4l6hj2oKf02Jo6CQF0MCMhPIrK0Dj4iYBuLjMerIdo+3TZ+6ADA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:09:18.379815Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.09412","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccd116ebe5264490fad07e14c48d2fd25a0479f3cc0933cf091f9c82e66786a7","sha256:5605ca1a4bacfb530ed51886b47ff0e6f4e49a12bb47b39596230c79a7025784"],"state_sha256":"ef4d0d107a3fe82383efe4e4664c8ca88f813bcdea8769b2c18bccee51d1d422"}