{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XLH4HNTFWIPMFDIOTEGZAQQIVE","short_pith_number":"pith:XLH4HNTF","canonical_record":{"source":{"id":"2012.04224","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T05:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"08597cfd30f6543939055a0335c7c0c3180b9dfe21b757c97001ca8bc97b4245","abstract_canon_sha256":"d69d5d65911499b871cbf6355177c686791138b8eaf955a0a9c9246dd06d30b6"},"schema_version":"1.0"},"canonical_sha256":"bacfc3b665b21ec28d0e990d904208a9227963c01006b8869f15ec059532c1c9","source":{"kind":"arxiv","id":"2012.04224","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04224","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04224v1","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04224","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"XLH4HNTFWIPM","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"XLH4HNTFWIPMFDIO","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"XLH4HNTF","created_at":"2026-07-05T01:58:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XLH4HNTFWIPMFDIOTEGZAQQIVE","target":"record","payload":{"canonical_record":{"source":{"id":"2012.04224","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T05:21:29Z","cross_cats_sorted":[],"title_canon_sha256":"08597cfd30f6543939055a0335c7c0c3180b9dfe21b757c97001ca8bc97b4245","abstract_canon_sha256":"d69d5d65911499b871cbf6355177c686791138b8eaf955a0a9c9246dd06d30b6"},"schema_version":"1.0"},"canonical_sha256":"bacfc3b665b21ec28d0e990d904208a9227963c01006b8869f15ec059532c1c9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:02.108241Z","signature_b64":"ABuG6kyvSZZ271rik4zlLWXugoBaaX4bYJCXDqomj+cllvpp8bxXBvJIClJhgiDOPx2MdfWimEdttPUHXHe8DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bacfc3b665b21ec28d0e990d904208a9227963c01006b8869f15ec059532c1c9","last_reissued_at":"2026-07-05T01:58:02.107913Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:02.107913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.04224","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6V5bwWlLdeLpkVE7EHMe3LiXdd6TQLT6ennEBHi6B6lpIWmpVEEzQPMXGp0zlCQz2gI6xX/L9u8MAmxjnmaAAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:26:44.720540Z"},"content_sha256":"ee20dc6f4985a31542e87354411af83afa5971f051d6e82798b8b0851eaf6f13","schema_version":"1.0","event_id":"sha256:ee20dc6f4985a31542e87354411af83afa5971f051d6e82798b8b0851eaf6f13"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XLH4HNTFWIPMFDIOTEGZAQQIVE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KNN-enhanced Deep Learning Against Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amin Rezaei, Hai Zhou, Jia Wang, Shuyu Kong, You Li","submitted_at":"2020-12-08T05:21:29Z","abstract_excerpt":"Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optimizing performance of DNN in the presence of noisy labels has become of paramount importance since collecting a large dataset will usually bring in noisy labels. Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup. Our approach leverages DNNs for feature extraction and KNN for ground-truth label inference. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04224","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2012.04224/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:58:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JqvDHKu2I1tur6k85U4vc9V3garJ2QVnvYjeizaP7/2xqYaS0sXznyL7JMdYmAmz88d4mfGFiORPD4K5/iuECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T15:26:44.720922Z"},"content_sha256":"87905e3d54d227b1c280eccd8399d72e634e9e323b781d76b423b13ad4a0a6dd","schema_version":"1.0","event_id":"sha256:87905e3d54d227b1c280eccd8399d72e634e9e323b781d76b423b13ad4a0a6dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE/bundle.json","state_url":"https://pith.science/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-07T15:26:44Z","links":{"resolver":"https://pith.science/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE","bundle":"https://pith.science/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE/bundle.json","state":"https://pith.science/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLH4HNTFWIPMFDIOTEGZAQQIVE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XLH4HNTFWIPMFDIOTEGZAQQIVE","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":"d69d5d65911499b871cbf6355177c686791138b8eaf955a0a9c9246dd06d30b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T05:21:29Z","title_canon_sha256":"08597cfd30f6543939055a0335c7c0c3180b9dfe21b757c97001ca8bc97b4245"},"schema_version":"1.0","source":{"id":"2012.04224","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.04224","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"arxiv_version","alias_value":"2012.04224v1","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.04224","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"pith_short_12","alias_value":"XLH4HNTFWIPM","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"pith_short_16","alias_value":"XLH4HNTFWIPMFDIO","created_at":"2026-07-05T01:58:02Z"},{"alias_kind":"pith_short_8","alias_value":"XLH4HNTF","created_at":"2026-07-05T01:58:02Z"}],"graph_snapshots":[{"event_id":"sha256:87905e3d54d227b1c280eccd8399d72e634e9e323b781d76b423b13ad4a0a6dd","target":"graph","created_at":"2026-07-05T01:58:02Z","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/2012.04224/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised learning on Deep Neural Networks (DNNs) is data hungry. Optimizing performance of DNN in the presence of noisy labels has become of paramount importance since collecting a large dataset will usually bring in noisy labels. Inspired by the robustness of K-Nearest Neighbors (KNN) against data noise, in this work, we propose to apply deep KNN for label cleanup. Our approach leverages DNNs for feature extraction and KNN for ground-truth label inference. We iteratively train the neural network and update labels to simultaneously proceed towards higher label recovery rate and better classi","authors_text":"Amin Rezaei, Hai Zhou, Jia Wang, Shuyu Kong, You Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T05:21:29Z","title":"KNN-enhanced Deep Learning Against Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.04224","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:ee20dc6f4985a31542e87354411af83afa5971f051d6e82798b8b0851eaf6f13","target":"record","created_at":"2026-07-05T01:58:02Z","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":"d69d5d65911499b871cbf6355177c686791138b8eaf955a0a9c9246dd06d30b6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2020-12-08T05:21:29Z","title_canon_sha256":"08597cfd30f6543939055a0335c7c0c3180b9dfe21b757c97001ca8bc97b4245"},"schema_version":"1.0","source":{"id":"2012.04224","kind":"arxiv","version":1}},"canonical_sha256":"bacfc3b665b21ec28d0e990d904208a9227963c01006b8869f15ec059532c1c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bacfc3b665b21ec28d0e990d904208a9227963c01006b8869f15ec059532c1c9","first_computed_at":"2026-07-05T01:58:02.107913Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:02.107913Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ABuG6kyvSZZ271rik4zlLWXugoBaaX4bYJCXDqomj+cllvpp8bxXBvJIClJhgiDOPx2MdfWimEdttPUHXHe8DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:02.108241Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.04224","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee20dc6f4985a31542e87354411af83afa5971f051d6e82798b8b0851eaf6f13","sha256:87905e3d54d227b1c280eccd8399d72e634e9e323b781d76b423b13ad4a0a6dd"],"state_sha256":"63a4351ae7cbf5ece0f2c5d1b75a1506f6dd74cc05d3717d9754dda7c743af36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZ0yLbJegamqB6aPI+XYkw9KBD+9Da1GQCvRHGyoBYVCi8MfbXD+o0jyof0/DH25IIoOVb8D0xaMAnrnK4joBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T15:26:44.723001Z","bundle_sha256":"cd9c3668f3eef035ca16826f627ee74ce7e1ed470dfb2771fcb7d2fc075e1a42"}}