{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IMIYESBBJA7V46OZ7SVGZTWK5G","short_pith_number":"pith:IMIYESBB","canonical_record":{"source":{"id":"1803.09050","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-24T03:41:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"92d52b91d75f4ee2595fa6561287bd8dc1db0ad89b1c9c52b728069996e894d7","abstract_canon_sha256":"253d179b6fd5487793f0294562a763ec9b57e3c29208fefb07a5d5a983375426"},"schema_version":"1.0"},"canonical_sha256":"4311824821483f5e79d9fcaa6ccecae983d5a054049cf57c3d492674a448e91b","source":{"kind":"arxiv","id":"1803.09050","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09050","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09050v3","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09050","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"IMIYESBBJA7V","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IMIYESBBJA7V46OZ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IMIYESBB","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IMIYESBBJA7V46OZ7SVGZTWK5G","target":"record","payload":{"canonical_record":{"source":{"id":"1803.09050","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-24T03:41:59Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"92d52b91d75f4ee2595fa6561287bd8dc1db0ad89b1c9c52b728069996e894d7","abstract_canon_sha256":"253d179b6fd5487793f0294562a763ec9b57e3c29208fefb07a5d5a983375426"},"schema_version":"1.0"},"canonical_sha256":"4311824821483f5e79d9fcaa6ccecae983d5a054049cf57c3d492674a448e91b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:03.455656Z","signature_b64":"M4id/Kaab0W1OpZv7BKoQHEbsozZP1rQeCX3suKTyOF7JYI1Yi39u5nCOec3JVmLgQtTE9q7NvdX+oQZ3eWxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4311824821483f5e79d9fcaa6ccecae983d5a054049cf57c3d492674a448e91b","last_reissued_at":"2026-05-17T23:47:03.454939Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:03.454939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.09050","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jzQuYY2k25ffHEIEW9RuKwiit6CP/1/YMpYgE5W5tS7uLGnVnURTY7AENgjWQj6if6/Llsg+/gPmKb2ZOZGOBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:18:09.834689Z"},"content_sha256":"d465a2045fe0dfbed4a30aab9940a6083429bb3fae039f8117c8f0a74bcf7967","schema_version":"1.0","event_id":"sha256:d465a2045fe0dfbed4a30aab9940a6083429bb3fae039f8117c8f0a74bcf7967"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IMIYESBBJA7V46OZ7SVGZTWK5G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Reweight Examples for Robust Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bin Yang, Mengye Ren, Raquel Urtasun, Wenyuan Zeng","submitted_at":"2018-03-24T03:41:59Z","abstract_excerpt":"Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit to training set biases and label noises. In addition to various regularizers, example reweighting algorithms are popular solutions to these problems, but they require careful tuning of additional hyperparameters, such as example mining schedules and regularization hyperparameters. In contrast to past reweighting methods, which typically consist of functions of the cost value of each example, in this work we propose a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09050","kind":"arxiv","version":3},"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":"2026-05-17T23:47:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+dSy/XyXCRjQZpaJbJCKqJUpBZDpKH1gSMhbYdi0UuwuBwBklzrDpOURt89gcWcBsUucwL36KSkBkjlLB7fCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T11:18:09.835448Z"},"content_sha256":"7e9caadcc3c998f1ce4f8d6730118b2c5ce995882fbd18627d0262a020c9fcab","schema_version":"1.0","event_id":"sha256:7e9caadcc3c998f1ce4f8d6730118b2c5ce995882fbd18627d0262a020c9fcab"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMIYESBBJA7V46OZ7SVGZTWK5G/bundle.json","state_url":"https://pith.science/pith/IMIYESBBJA7V46OZ7SVGZTWK5G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMIYESBBJA7V46OZ7SVGZTWK5G/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":"2026-05-30T11:18:09Z","links":{"resolver":"https://pith.science/pith/IMIYESBBJA7V46OZ7SVGZTWK5G","bundle":"https://pith.science/pith/IMIYESBBJA7V46OZ7SVGZTWK5G/bundle.json","state":"https://pith.science/pith/IMIYESBBJA7V46OZ7SVGZTWK5G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMIYESBBJA7V46OZ7SVGZTWK5G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IMIYESBBJA7V46OZ7SVGZTWK5G","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":"253d179b6fd5487793f0294562a763ec9b57e3c29208fefb07a5d5a983375426","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-24T03:41:59Z","title_canon_sha256":"92d52b91d75f4ee2595fa6561287bd8dc1db0ad89b1c9c52b728069996e894d7"},"schema_version":"1.0","source":{"id":"1803.09050","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.09050","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"arxiv_version","alias_value":"1803.09050v3","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09050","created_at":"2026-05-17T23:47:03Z"},{"alias_kind":"pith_short_12","alias_value":"IMIYESBBJA7V","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IMIYESBBJA7V46OZ","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IMIYESBB","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:7e9caadcc3c998f1ce4f8d6730118b2c5ce995882fbd18627d0262a020c9fcab","target":"graph","created_at":"2026-05-17T23:47:03Z","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":"Deep neural networks have been shown to be very powerful modeling tools for many supervised learning tasks involving complex input patterns. However, they can also easily overfit to training set biases and label noises. In addition to various regularizers, example reweighting algorithms are popular solutions to these problems, but they require careful tuning of additional hyperparameters, such as example mining schedules and regularization hyperparameters. In contrast to past reweighting methods, which typically consist of functions of the cost value of each example, in this work we propose a ","authors_text":"Bin Yang, Mengye Ren, Raquel Urtasun, Wenyuan Zeng","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-24T03:41:59Z","title":"Learning to Reweight Examples for Robust Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09050","kind":"arxiv","version":3},"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:d465a2045fe0dfbed4a30aab9940a6083429bb3fae039f8117c8f0a74bcf7967","target":"record","created_at":"2026-05-17T23:47:03Z","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":"253d179b6fd5487793f0294562a763ec9b57e3c29208fefb07a5d5a983375426","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-24T03:41:59Z","title_canon_sha256":"92d52b91d75f4ee2595fa6561287bd8dc1db0ad89b1c9c52b728069996e894d7"},"schema_version":"1.0","source":{"id":"1803.09050","kind":"arxiv","version":3}},"canonical_sha256":"4311824821483f5e79d9fcaa6ccecae983d5a054049cf57c3d492674a448e91b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4311824821483f5e79d9fcaa6ccecae983d5a054049cf57c3d492674a448e91b","first_computed_at":"2026-05-17T23:47:03.454939Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:47:03.454939Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M4id/Kaab0W1OpZv7BKoQHEbsozZP1rQeCX3suKTyOF7JYI1Yi39u5nCOec3JVmLgQtTE9q7NvdX+oQZ3eWxCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:47:03.455656Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.09050","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d465a2045fe0dfbed4a30aab9940a6083429bb3fae039f8117c8f0a74bcf7967","sha256:7e9caadcc3c998f1ce4f8d6730118b2c5ce995882fbd18627d0262a020c9fcab"],"state_sha256":"72895be225ec91db7af117edc11d64bcd67a985c14616cd67eca4424840e6134"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O6zviH88eGYlwyU1UgQHXkIj2S24AxkTcpHChcTT85WPa1wwbHu5opfLDj05MyIL2jgo7Nj7sD5QwkHZmjhADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T11:18:09.840239Z","bundle_sha256":"5040749a5450ecb826aa4b1544d301ecfdc0d1e66e3cd321d1b8cddb1b188b51"}}