{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VD4DJDQ25X455USBX5AQQM5ZNH","short_pith_number":"pith:VD4DJDQ2","schema_version":"1.0","canonical_sha256":"a8f8348e1aedf9ded241bf410833b969de0bbf5c102cfd3d26eef8b9d1a99917","source":{"kind":"arxiv","id":"2110.08866","version":2},"attestation_state":"computed","paper":{"title":"Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxin Wei, Kai Ma, Tao Xu, Yefeng Zheng, Yuexiang Li, Ziqi Zhang","submitted_at":"2021-10-17T17:01:57Z","abstract_excerpt":"Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. Recent studies employed learning-to-learn paradigms (e.g., Co-teaching and JoCoR) to filter the samples with noisy labels from the training set. However, most of them use a simple cross-entropy loss as the criterion for noisy label identification. The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value tha"},"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":"2110.08866","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-17T17:01:57Z","cross_cats_sorted":[],"title_canon_sha256":"dbe2333c4e10ce0439a72c471f87924ff17d039c64280e58e2b769ff7b38ec3e","abstract_canon_sha256":"cec07ae696c9159748272d774389c63cfb49f552d658fe79427ba809519987c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:48.801239Z","signature_b64":"GBk3XpjK1JP3wdJdcvStD/v6HmYeGqHrd+lJuxuAxSiqs59jRDClif4KDlyaa0Jro7MTbSQHGwZKxKZgLiUbCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8f8348e1aedf9ded241bf410833b969de0bbf5c102cfd3d26eef8b9d1a99917","last_reissued_at":"2026-07-05T06:04:48.800750Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:48.800750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Alleviating Noisy-label Effects in Image Classification via Probability Transition Matrix","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxin Wei, Kai Ma, Tao Xu, Yefeng Zheng, Yuexiang Li, Ziqi Zhang","submitted_at":"2021-10-17T17:01:57Z","abstract_excerpt":"Deep-learning-based image classification frameworks often suffer from the noisy label problem caused by the inter-observer variation. Recent studies employed learning-to-learn paradigms (e.g., Co-teaching and JoCoR) to filter the samples with noisy labels from the training set. However, most of them use a simple cross-entropy loss as the criterion for noisy label identification. The hard samples, which are beneficial for classifier learning, are often mistakenly treated as noises in such a setting since both the hard samples and ones with noisy labels lead to a relatively larger loss value tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.08866","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2110.08866/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2110.08866","created_at":"2026-07-05T06:04:48.800813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.08866v2","created_at":"2026-07-05T06:04:48.800813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.08866","created_at":"2026-07-05T06:04:48.800813+00:00"},{"alias_kind":"pith_short_12","alias_value":"VD4DJDQ25X45","created_at":"2026-07-05T06:04:48.800813+00:00"},{"alias_kind":"pith_short_16","alias_value":"VD4DJDQ25X455USB","created_at":"2026-07-05T06:04:48.800813+00:00"},{"alias_kind":"pith_short_8","alias_value":"VD4DJDQ2","created_at":"2026-07-05T06:04:48.800813+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/VD4DJDQ25X455USBX5AQQM5ZNH","json":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH.json","graph_json":"https://pith.science/api/pith-number/VD4DJDQ25X455USBX5AQQM5ZNH/graph.json","events_json":"https://pith.science/api/pith-number/VD4DJDQ25X455USBX5AQQM5ZNH/events.json","paper":"https://pith.science/paper/VD4DJDQ2"},"agent_actions":{"view_html":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH","download_json":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH.json","view_paper":"https://pith.science/paper/VD4DJDQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.08866&json=true","fetch_graph":"https://pith.science/api/pith-number/VD4DJDQ25X455USBX5AQQM5ZNH/graph.json","fetch_events":"https://pith.science/api/pith-number/VD4DJDQ25X455USBX5AQQM5ZNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH/action/storage_attestation","attest_author":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH/action/author_attestation","sign_citation":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH/action/citation_signature","submit_replication":"https://pith.science/pith/VD4DJDQ25X455USBX5AQQM5ZNH/action/replication_record"}},"created_at":"2026-07-05T06:04:48.800813+00:00","updated_at":"2026-07-05T06:04:48.800813+00:00"}