{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UHIYIGNEXLW3LBLQINWVYXRELL","short_pith_number":"pith:UHIYIGNE","canonical_record":{"source":{"id":"2202.04291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-09T05:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"945c8f861bba3501183301c070109c0fb44d46984d67c4d8e52df32598a9b33e","abstract_canon_sha256":"3bdc313c10d59a732c748add56029877949d9c389f647c4efe003300acc9990b"},"schema_version":"1.0"},"canonical_sha256":"a1d18419a4baedb58570436d5c5e245af0732954c71d06a92808873147e57b85","source":{"kind":"arxiv","id":"2202.04291","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.04291","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2202.04291v2","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04291","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"UHIYIGNEXLW3","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"UHIYIGNEXLW3LBLQ","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"UHIYIGNE","created_at":"2026-07-05T08:01:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UHIYIGNEXLW3LBLQINWVYXRELL","target":"record","payload":{"canonical_record":{"source":{"id":"2202.04291","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-09T05:57:08Z","cross_cats_sorted":[],"title_canon_sha256":"945c8f861bba3501183301c070109c0fb44d46984d67c4d8e52df32598a9b33e","abstract_canon_sha256":"3bdc313c10d59a732c748add56029877949d9c389f647c4efe003300acc9990b"},"schema_version":"1.0"},"canonical_sha256":"a1d18419a4baedb58570436d5c5e245af0732954c71d06a92808873147e57b85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:01:28.347838Z","signature_b64":"w2Do6gQYuwenBLZzPjLmoFdCL/c+FPDTFWk1NLqZHnlfKKiGPafXI3kV8FKsogUxiclWVXV0qrEjp3ndF3u7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d18419a4baedb58570436d5c5e245af0732954c71d06a92808873147e57b85","last_reissued_at":"2026-07-05T08:01:28.347309Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:01:28.347309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2202.04291","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:01:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DSlkHNGBU9Lw3uM3DdSkfvrlOxqn9UgV7hgwIYzUHHa3eGXR5bdoR6ILFM9rfYX0mK7c9Akc8t/EsMgp6XIvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:51:35.794519Z"},"content_sha256":"24256033d634ac8e59ac5de18799e8b2bbd4f458b51c56368f49bc3315a98216","schema_version":"1.0","event_id":"sha256:24256033d634ac8e59ac5de18799e8b2bbd4f458b51c56368f49bc3315a98216"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UHIYIGNEXLW3LBLQINWVYXRELL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"L2B: Learning to Bootstrap Robust Models for Combating Label Noise","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Cihang Xie, Fengze Liu, Lei Xing, Lequan Yu, Matthew P. Lungren, Qingyue Wei, Xianhang Li, Xuxi Chen, Yuyin Zhou","submitted_at":"2022-02-09T05:57:08Z","abstract_excerpt":"Deep neural networks have shown great success in representation learning. However, when learning with noisy labels (LNL), they can easily overfit and fail to generalize to new data. This paper introduces a simple and effective method, named Learning to Bootstrap (L2B), which enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels. It achieves this by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning. Unlike existing instance rew"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04291","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/2202.04291/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":"2026-07-05T08:01:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fsF7rApeo1GuBYG2FDCUbHSpof4MepZVgSEYCZ5MJdQmW4WTNC2m8XbNBMq2Y46cEOdFyUjxS7Uu9JplYowADQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:51:35.795090Z"},"content_sha256":"d2c6d44963f63fb1ce6c0c7ee2fc867187b45bf17e08a08c087fe7e750071b89","schema_version":"1.0","event_id":"sha256:d2c6d44963f63fb1ce6c0c7ee2fc867187b45bf17e08a08c087fe7e750071b89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHIYIGNEXLW3LBLQINWVYXRELL/bundle.json","state_url":"https://pith.science/pith/UHIYIGNEXLW3LBLQINWVYXRELL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHIYIGNEXLW3LBLQINWVYXRELL/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":"2026-08-04T21:51:35Z","links":{"resolver":"https://pith.science/pith/UHIYIGNEXLW3LBLQINWVYXRELL","bundle":"https://pith.science/pith/UHIYIGNEXLW3LBLQINWVYXRELL/bundle.json","state":"https://pith.science/pith/UHIYIGNEXLW3LBLQINWVYXRELL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHIYIGNEXLW3LBLQINWVYXRELL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UHIYIGNEXLW3LBLQINWVYXRELL","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":"3bdc313c10d59a732c748add56029877949d9c389f647c4efe003300acc9990b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-09T05:57:08Z","title_canon_sha256":"945c8f861bba3501183301c070109c0fb44d46984d67c4d8e52df32598a9b33e"},"schema_version":"1.0","source":{"id":"2202.04291","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2202.04291","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"arxiv_version","alias_value":"2202.04291v2","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.04291","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"pith_short_12","alias_value":"UHIYIGNEXLW3","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"pith_short_16","alias_value":"UHIYIGNEXLW3LBLQ","created_at":"2026-07-05T08:01:28Z"},{"alias_kind":"pith_short_8","alias_value":"UHIYIGNE","created_at":"2026-07-05T08:01:28Z"}],"graph_snapshots":[{"event_id":"sha256:d2c6d44963f63fb1ce6c0c7ee2fc867187b45bf17e08a08c087fe7e750071b89","target":"graph","created_at":"2026-07-05T08:01:28Z","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/2202.04291/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks have shown great success in representation learning. However, when learning with noisy labels (LNL), they can easily overfit and fail to generalize to new data. This paper introduces a simple and effective method, named Learning to Bootstrap (L2B), which enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels. It achieves this by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning. Unlike existing instance rew","authors_text":"Cihang Xie, Fengze Liu, Lei Xing, Lequan Yu, Matthew P. Lungren, Qingyue Wei, Xianhang Li, Xuxi Chen, Yuyin Zhou","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-09T05:57:08Z","title":"L2B: Learning to Bootstrap Robust Models for Combating Label Noise"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.04291","kind":"arxiv","version":2},"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":"sha256:24256033d634ac8e59ac5de18799e8b2bbd4f458b51c56368f49bc3315a98216","target":"record","created_at":"2026-07-05T08:01:28Z","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":"3bdc313c10d59a732c748add56029877949d9c389f647c4efe003300acc9990b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-02-09T05:57:08Z","title_canon_sha256":"945c8f861bba3501183301c070109c0fb44d46984d67c4d8e52df32598a9b33e"},"schema_version":"1.0","source":{"id":"2202.04291","kind":"arxiv","version":2}},"canonical_sha256":"a1d18419a4baedb58570436d5c5e245af0732954c71d06a92808873147e57b85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1d18419a4baedb58570436d5c5e245af0732954c71d06a92808873147e57b85","first_computed_at":"2026-07-05T08:01:28.347309Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:01:28.347309Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w2Do6gQYuwenBLZzPjLmoFdCL/c+FPDTFWk1NLqZHnlfKKiGPafXI3kV8FKsogUxiclWVXV0qrEjp3ndF3u7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:01:28.347838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2202.04291","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24256033d634ac8e59ac5de18799e8b2bbd4f458b51c56368f49bc3315a98216","sha256:d2c6d44963f63fb1ce6c0c7ee2fc867187b45bf17e08a08c087fe7e750071b89"],"state_sha256":"f811c818bacaa14d9f96835211e14d7d20f67aba1fd5d2801e20ecc476339bf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"si4YemQLnbhwyEhWCkyHMe4R0B2UuMli4yVTdF8trALqFCTk51p1aHeVYmj0qdQMRT/BNdcz9psjA493d/YGDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:51:35.801737Z","bundle_sha256":"a058d1a992009c743d0bda2ee7b8c398831967a93d396107faefb83bae94dcc9"}}