{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6U3BCKGMZDAGXJ67ER4UGQOBJA","short_pith_number":"pith:6U3BCKGM","canonical_record":{"source":{"id":"2106.03110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T12:52:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"748f0375a9835904af638b3459728a1e6bc9809b3feb2159d767e0592585fd01","abstract_canon_sha256":"0b65c349eb5ce469d5f9b3f12a751d5b7c8830add8c2f0c7058bc5ef52846f84"},"schema_version":"1.0"},"canonical_sha256":"f5361128ccc8c06ba7df24794341c148241b75c40cb9a8057dc7cbf1f6ca8afe","source":{"kind":"arxiv","id":"2106.03110","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03110","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03110v1","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03110","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"6U3BCKGMZDAG","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"6U3BCKGMZDAGXJ67","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"6U3BCKGM","created_at":"2026-07-05T02:46:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6U3BCKGMZDAGXJ67ER4UGQOBJA","target":"record","payload":{"canonical_record":{"source":{"id":"2106.03110","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T12:52:48Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"748f0375a9835904af638b3459728a1e6bc9809b3feb2159d767e0592585fd01","abstract_canon_sha256":"0b65c349eb5ce469d5f9b3f12a751d5b7c8830add8c2f0c7058bc5ef52846f84"},"schema_version":"1.0"},"canonical_sha256":"f5361128ccc8c06ba7df24794341c148241b75c40cb9a8057dc7cbf1f6ca8afe","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:33.893218Z","signature_b64":"DITZcS0ORFl3IKF9z0ufmTVjPgrO1MM5JThr/QP7rvU2XBbLxqJbC23OH14avINaYKsyX6HEiz2e2zNm6SexDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5361128ccc8c06ba7df24794341c148241b75c40cb9a8057dc7cbf1f6ca8afe","last_reissued_at":"2026-07-05T02:46:33.892818Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:33.892818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.03110","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":"2026-07-05T02:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Py2jNOegWnizbfNW7tM+AgLHfRWr6uwHP2k05VTrHglbsuQ5sfAxqR/drNtXHl7WJoE5jL8PRSZ44qn8dFAtBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:55:35.961496Z"},"content_sha256":"560894c59ea820c1c51e55eab05d5d9d7a3c9cb43290ce1950af4c2e2079252b","schema_version":"1.0","event_id":"sha256:560894c59ea820c1c51e55eab05d5d9d7a3c9cb43290ce1950af4c2e2079252b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6U3BCKGMZDAGXJ67ER4UGQOBJA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Asymmetric Loss Functions for Learning with Noisy Labels","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Junjun Jiang, Xiangyang Ji, Xianming Liu, Xin Gao, Xiong Zhou","submitted_at":"2021-06-06T12:52:48Z","abstract_excerpt":"Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is overly restrictive. In this work, we propose a new class of loss functions, namely \\textit{asymmetric loss functions}, which are robust to learning with noisy labels for various types of noise. We investigate general theoretical properties of asymmetric loss functions, including classification calibration, excess risk bound, and noise tolerance. Meanwhile, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03110","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/2106.03110/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":"2026-07-05T02:46:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7wZWk5fN/DQRlTFxt8a7ri8/Cm4BtqJ/ZkVXBxDJ2Vx1sTyf0yrIv8Iw5ojv/s85fUMAKN8y9r6D8GaVMEoqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T10:55:35.962049Z"},"content_sha256":"439390aeef3e68e12dccd7054e4b7e02f412f076a19d08e04b7e21de5aa0aa12","schema_version":"1.0","event_id":"sha256:439390aeef3e68e12dccd7054e4b7e02f412f076a19d08e04b7e21de5aa0aa12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA/bundle.json","state_url":"https://pith.science/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA/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":"2026-08-06T10:55:35Z","links":{"resolver":"https://pith.science/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA","bundle":"https://pith.science/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA/bundle.json","state":"https://pith.science/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6U3BCKGMZDAGXJ67ER4UGQOBJA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6U3BCKGMZDAGXJ67ER4UGQOBJA","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":"0b65c349eb5ce469d5f9b3f12a751d5b7c8830add8c2f0c7058bc5ef52846f84","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T12:52:48Z","title_canon_sha256":"748f0375a9835904af638b3459728a1e6bc9809b3feb2159d767e0592585fd01"},"schema_version":"1.0","source":{"id":"2106.03110","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.03110","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"arxiv_version","alias_value":"2106.03110v1","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03110","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"pith_short_12","alias_value":"6U3BCKGMZDAG","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"pith_short_16","alias_value":"6U3BCKGMZDAGXJ67","created_at":"2026-07-05T02:46:33Z"},{"alias_kind":"pith_short_8","alias_value":"6U3BCKGM","created_at":"2026-07-05T02:46:33Z"}],"graph_snapshots":[{"event_id":"sha256:439390aeef3e68e12dccd7054e4b7e02f412f076a19d08e04b7e21de5aa0aa12","target":"graph","created_at":"2026-07-05T02:46:33Z","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/2106.03110/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Robust loss functions are essential for training deep neural networks with better generalization power in the presence of noisy labels. Symmetric loss functions are confirmed to be robust to label noise. However, the symmetric condition is overly restrictive. In this work, we propose a new class of loss functions, namely \\textit{asymmetric loss functions}, which are robust to learning with noisy labels for various types of noise. We investigate general theoretical properties of asymmetric loss functions, including classification calibration, excess risk bound, and noise tolerance. Meanwhile, w","authors_text":"Junjun Jiang, Xiangyang Ji, Xianming Liu, Xin Gao, Xiong Zhou","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T12:52:48Z","title":"Asymmetric Loss Functions for Learning with Noisy Labels"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03110","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":"sha256:560894c59ea820c1c51e55eab05d5d9d7a3c9cb43290ce1950af4c2e2079252b","target":"record","created_at":"2026-07-05T02:46:33Z","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":"0b65c349eb5ce469d5f9b3f12a751d5b7c8830add8c2f0c7058bc5ef52846f84","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-06T12:52:48Z","title_canon_sha256":"748f0375a9835904af638b3459728a1e6bc9809b3feb2159d767e0592585fd01"},"schema_version":"1.0","source":{"id":"2106.03110","kind":"arxiv","version":1}},"canonical_sha256":"f5361128ccc8c06ba7df24794341c148241b75c40cb9a8057dc7cbf1f6ca8afe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5361128ccc8c06ba7df24794341c148241b75c40cb9a8057dc7cbf1f6ca8afe","first_computed_at":"2026-07-05T02:46:33.892818Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:33.892818Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DITZcS0ORFl3IKF9z0ufmTVjPgrO1MM5JThr/QP7rvU2XBbLxqJbC23OH14avINaYKsyX6HEiz2e2zNm6SexDA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:33.893218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.03110","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:560894c59ea820c1c51e55eab05d5d9d7a3c9cb43290ce1950af4c2e2079252b","sha256:439390aeef3e68e12dccd7054e4b7e02f412f076a19d08e04b7e21de5aa0aa12"],"state_sha256":"ab49f3f8677f8e792bfb2eaa643d4551370258e8023877a766c96c1ce77708cd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ntrHsiJPS5LUNfl1rTdbfur16PIIYbgdiJspJkv+8SPHXGldEoVfUXp9WgOEEQvxcYAjnvJ5F1GRZwFz6+HdAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T10:55:35.967021Z","bundle_sha256":"31ce038de562de1eb982ba463891bf85af07edbf6ae9bd2b6bcdf79f9afcb6db"}}