{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:AGVT2FQZD5E57ZCSASH4NTL4BB","short_pith_number":"pith:AGVT2FQZ","canonical_record":{"source":{"id":"1703.02391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-07T14:15:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a811c6565b969e74b1895303eade7a45b43cdf41075e8acd73706dcf212fabc5","abstract_canon_sha256":"405af84e0504bdb28d7c02935734bd1e9a349dd522b398470f1b6572432f9093"},"schema_version":"1.0"},"canonical_sha256":"01ab3d16191f49dfe452048fc6cd7c087d4a3ebf1ba358c7565e2f4f02b7140d","source":{"kind":"arxiv","id":"1703.02391","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.02391","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1703.02391v2","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02391","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"AGVT2FQZD5E5","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AGVT2FQZD5E57ZCS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AGVT2FQZ","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:AGVT2FQZD5E57ZCSASH4NTL4BB","target":"record","payload":{"canonical_record":{"source":{"id":"1703.02391","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-07T14:15:14Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"a811c6565b969e74b1895303eade7a45b43cdf41075e8acd73706dcf212fabc5","abstract_canon_sha256":"405af84e0504bdb28d7c02935734bd1e9a349dd522b398470f1b6572432f9093"},"schema_version":"1.0"},"canonical_sha256":"01ab3d16191f49dfe452048fc6cd7c087d4a3ebf1ba358c7565e2f4f02b7140d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:43.937100Z","signature_b64":"k10K5rl22HvUXiU/VhrI7GpQucgZ3oWYg20R0Xw8/xlyS4XMS4G+AsIhL6PjzCEHeuZKAao2VUtkwsSuFAVgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01ab3d16191f49dfe452048fc6cd7c087d4a3ebf1ba358c7565e2f4f02b7140d","last_reissued_at":"2026-05-18T00:46:43.936525Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:43.936525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.02391","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":"2026-05-18T00:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AuHHnVgxYeQGjk1sceFFGV3Amfz+DrVQVRUwRRjCUYlV8WyBT26vWVxWTV5c0Ms+nwcNp/JhzCZtLaYaqTABCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T12:43:00.081528Z"},"content_sha256":"3fb65b7c15390a2a2b100557b14d59a8346fadcba55b7e657c8a9cf3a3d63cf7","schema_version":"1.0","event_id":"sha256:3fb65b7c15390a2a2b100557b14d59a8346fadcba55b7e657c8a9cf3a3d63cf7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:AGVT2FQZD5E57ZCSASH4NTL4BB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Noisy Labels with Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Jianchao Yang, Jiebo Luo, Liangliang Cao, Li-Jia Li, Yale Song, Yuncheng Li","submitted_at":"2017-03-07T14:15:14Z","abstract_excerpt":"The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed to alleviate the problem. According to our observation, the real-world noisy labels exhibit multi-mode characteristics as the true labels, rather than behaving like independent random outliers. In this work, we propose a unified distillation framework to use side information, inc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02391","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":""},"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":"2026-05-18T00:46:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5OJp76HBdb3tnf6ERnoRRvupeVR0fkQRsHWDiLh+D0k5jQ4ktYbTwPSnT9AsBEKIro4221+AyYYeeGQzTq/CBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T12:43:00.082203Z"},"content_sha256":"ef73012e803c212eacaf12a6e57f573a9a62c1425278406863fa72210f57fe04","schema_version":"1.0","event_id":"sha256:ef73012e803c212eacaf12a6e57f573a9a62c1425278406863fa72210f57fe04"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGVT2FQZD5E57ZCSASH4NTL4BB/bundle.json","state_url":"https://pith.science/pith/AGVT2FQZD5E57ZCSASH4NTL4BB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGVT2FQZD5E57ZCSASH4NTL4BB/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":"2026-05-22T12:43:00Z","links":{"resolver":"https://pith.science/pith/AGVT2FQZD5E57ZCSASH4NTL4BB","bundle":"https://pith.science/pith/AGVT2FQZD5E57ZCSASH4NTL4BB/bundle.json","state":"https://pith.science/pith/AGVT2FQZD5E57ZCSASH4NTL4BB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGVT2FQZD5E57ZCSASH4NTL4BB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:AGVT2FQZD5E57ZCSASH4NTL4BB","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":"405af84e0504bdb28d7c02935734bd1e9a349dd522b398470f1b6572432f9093","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-07T14:15:14Z","title_canon_sha256":"a811c6565b969e74b1895303eade7a45b43cdf41075e8acd73706dcf212fabc5"},"schema_version":"1.0","source":{"id":"1703.02391","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.02391","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"arxiv_version","alias_value":"1703.02391v2","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.02391","created_at":"2026-05-18T00:46:43Z"},{"alias_kind":"pith_short_12","alias_value":"AGVT2FQZD5E5","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"AGVT2FQZD5E57ZCS","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"AGVT2FQZ","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:ef73012e803c212eacaf12a6e57f573a9a62c1425278406863fa72210f57fe04","target":"graph","created_at":"2026-05-18T00:46:43Z","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"},"paper":{"abstract_excerpt":"The ability of learning from noisy labels is very useful in many visual recognition tasks, as a vast amount of data with noisy labels are relatively easy to obtain. Traditionally, the label noises have been treated as statistical outliers, and approaches such as importance re-weighting and bootstrap have been proposed to alleviate the problem. According to our observation, the real-world noisy labels exhibit multi-mode characteristics as the true labels, rather than behaving like independent random outliers. In this work, we propose a unified distillation framework to use side information, inc","authors_text":"Jianchao Yang, Jiebo Luo, Liangliang Cao, Li-Jia Li, Yale Song, Yuncheng Li","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-07T14:15:14Z","title":"Learning from Noisy Labels with Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.02391","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":"sha256:3fb65b7c15390a2a2b100557b14d59a8346fadcba55b7e657c8a9cf3a3d63cf7","target":"record","created_at":"2026-05-18T00:46:43Z","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":"405af84e0504bdb28d7c02935734bd1e9a349dd522b398470f1b6572432f9093","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2017-03-07T14:15:14Z","title_canon_sha256":"a811c6565b969e74b1895303eade7a45b43cdf41075e8acd73706dcf212fabc5"},"schema_version":"1.0","source":{"id":"1703.02391","kind":"arxiv","version":2}},"canonical_sha256":"01ab3d16191f49dfe452048fc6cd7c087d4a3ebf1ba358c7565e2f4f02b7140d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01ab3d16191f49dfe452048fc6cd7c087d4a3ebf1ba358c7565e2f4f02b7140d","first_computed_at":"2026-05-18T00:46:43.936525Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:46:43.936525Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k10K5rl22HvUXiU/VhrI7GpQucgZ3oWYg20R0Xw8/xlyS4XMS4G+AsIhL6PjzCEHeuZKAao2VUtkwsSuFAVgAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:46:43.937100Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.02391","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3fb65b7c15390a2a2b100557b14d59a8346fadcba55b7e657c8a9cf3a3d63cf7","sha256:ef73012e803c212eacaf12a6e57f573a9a62c1425278406863fa72210f57fe04"],"state_sha256":"a8ad859f6512d613a854ca887a287b7d90ae53f548b10cda58b9700ca69b5841"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7DY3+U2DJyWYEcH9LB7sxYc6fAQ/Jgtr8ePgqViQVLlobLmd+HNqFqbLxfoJWuzVkrtvwqNy3At+F4yLPP49Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T12:43:00.086004Z","bundle_sha256":"b50872d8ef258027fd1281d4d39b08c553530db49eea9fac3f825e506c281925"}}