{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:BCVCJOLCTZ3ISZJQY6OF7KGCAI","short_pith_number":"pith:BCVCJOLC","canonical_record":{"source":{"id":"1905.10964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T04:00:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5640c2b8c64786049b24212ba2eb2abe07426fd93e30a3ff8b3cdad411198107","abstract_canon_sha256":"7ebfedf9792a3e0a9c6cfa35460a631dc459ef29ee5354b6cd25156df627bb8e"},"schema_version":"1.0"},"canonical_sha256":"08aa24b9629e76896530c79c5fa8c202389fdab9613d0a687334ee529f79e246","source":{"kind":"arxiv","id":"1905.10964","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10964","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10964v2","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10964","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"BCVCJOLCTZ3I","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"pith_short_16","alias_value":"BCVCJOLCTZ3ISZJQ","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"pith_short_8","alias_value":"BCVCJOLC","created_at":"2026-07-04T23:51:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:BCVCJOLCTZ3ISZJQY6OF7KGCAI","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10964","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T04:00:51Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"5640c2b8c64786049b24212ba2eb2abe07426fd93e30a3ff8b3cdad411198107","abstract_canon_sha256":"7ebfedf9792a3e0a9c6cfa35460a631dc459ef29ee5354b6cd25156df627bb8e"},"schema_version":"1.0"},"canonical_sha256":"08aa24b9629e76896530c79c5fa8c202389fdab9613d0a687334ee529f79e246","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:51:04.544614Z","signature_b64":"yOiG5RPImDXfpbiisrIQ3G137HD9966cWT7HYRn1rstc4sfLnoel1A2JdDQNKAZcyKpkT5la3z1H5tkwxZInBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08aa24b9629e76896530c79c5fa8c202389fdab9613d0a687334ee529f79e246","last_reissued_at":"2026-07-04T23:51:04.544129Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:51:04.544129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10964","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":"2026-07-04T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xYwnWV6s6Zzm3sVp0/q/JEYtmDRNcYeFFy6ZsNQZhUSQDlR4nUUyULo2kRUvzI4ilRsZ13rK+32Pn59nfdhWCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T00:55:35.149713Z"},"content_sha256":"de61c7bb57d82074a2276e8333b80eb24534cebfbb4fb20dbe836cd7894a591d","schema_version":"1.0","event_id":"sha256:de61c7bb57d82074a2276e8333b80eb24534cebfbb4fb20dbe836cd7894a591d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:BCVCJOLCTZ3ISZJQY6OF7KGCAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combating Label Noise in Deep Learning Using Abstention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gopinath Chennupati, Jamal Mohd-Yusof, Jeff Bilmes, Sunil Thulasidasan, Tanmoy Bhattacharya","submitted_at":"2019-05-27T04:00:51Z","abstract_excerpt":"We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the non-abstained samples. We show how such a deep abstaining classifier (DAC) can be used for robust learning in the presence of different types of label noise. In the case of structured or systematic label noise -- where noisy training labels or confusing examples are correlated with underlying featu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10964","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/1905.10964/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":"2026-07-04T23:51:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/FpLfAN61D/TV2BQeEH2FTKCtje362Hf+4aFzSTCci1AD3sPhhNu7sykasZSMPwjueNuIT++xz5dmunAcdliCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T00:55:35.150099Z"},"content_sha256":"b2eeea1b97be7918342406581c3bc2774d284ddb514e15f2222e045388f4b4dc","schema_version":"1.0","event_id":"sha256:b2eeea1b97be7918342406581c3bc2774d284ddb514e15f2222e045388f4b4dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI/bundle.json","state_url":"https://pith.science/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI/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":"2026-07-12T00:55:35Z","links":{"resolver":"https://pith.science/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI","bundle":"https://pith.science/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI/bundle.json","state":"https://pith.science/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BCVCJOLCTZ3ISZJQY6OF7KGCAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:BCVCJOLCTZ3ISZJQY6OF7KGCAI","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":"7ebfedf9792a3e0a9c6cfa35460a631dc459ef29ee5354b6cd25156df627bb8e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T04:00:51Z","title_canon_sha256":"5640c2b8c64786049b24212ba2eb2abe07426fd93e30a3ff8b3cdad411198107"},"schema_version":"1.0","source":{"id":"1905.10964","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10964","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10964v2","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10964","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"pith_short_12","alias_value":"BCVCJOLCTZ3I","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"pith_short_16","alias_value":"BCVCJOLCTZ3ISZJQ","created_at":"2026-07-04T23:51:04Z"},{"alias_kind":"pith_short_8","alias_value":"BCVCJOLC","created_at":"2026-07-04T23:51:04Z"}],"graph_snapshots":[{"event_id":"sha256:b2eeea1b97be7918342406581c3bc2774d284ddb514e15f2222e045388f4b4dc","target":"graph","created_at":"2026-07-04T23:51:04Z","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/1905.10964/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a novel method to combat label noise when training deep neural networks for classification. We propose a loss function that permits abstention during training thereby allowing the DNN to abstain on confusing samples while continuing to learn and improve classification performance on the non-abstained samples. We show how such a deep abstaining classifier (DAC) can be used for robust learning in the presence of different types of label noise. In the case of structured or systematic label noise -- where noisy training labels or confusing examples are correlated with underlying featu","authors_text":"Gopinath Chennupati, Jamal Mohd-Yusof, Jeff Bilmes, Sunil Thulasidasan, Tanmoy Bhattacharya","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T04:00:51Z","title":"Combating Label Noise in Deep Learning Using Abstention"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10964","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:de61c7bb57d82074a2276e8333b80eb24534cebfbb4fb20dbe836cd7894a591d","target":"record","created_at":"2026-07-04T23:51:04Z","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":"7ebfedf9792a3e0a9c6cfa35460a631dc459ef29ee5354b6cd25156df627bb8e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T04:00:51Z","title_canon_sha256":"5640c2b8c64786049b24212ba2eb2abe07426fd93e30a3ff8b3cdad411198107"},"schema_version":"1.0","source":{"id":"1905.10964","kind":"arxiv","version":2}},"canonical_sha256":"08aa24b9629e76896530c79c5fa8c202389fdab9613d0a687334ee529f79e246","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08aa24b9629e76896530c79c5fa8c202389fdab9613d0a687334ee529f79e246","first_computed_at":"2026-07-04T23:51:04.544129Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:51:04.544129Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yOiG5RPImDXfpbiisrIQ3G137HD9966cWT7HYRn1rstc4sfLnoel1A2JdDQNKAZcyKpkT5la3z1H5tkwxZInBA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:51:04.544614Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10964","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de61c7bb57d82074a2276e8333b80eb24534cebfbb4fb20dbe836cd7894a591d","sha256:b2eeea1b97be7918342406581c3bc2774d284ddb514e15f2222e045388f4b4dc"],"state_sha256":"f7536f99d238c1a814f7506644fecedf06d6e2319f9f60d7b41b586c5e6c5888"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S0DEeF0n92PGoI1TD7j6K8xMdXBYBkkBnwZmZdXkn+JF9YE7FJKdTE6ISdKhnsvPpLG021MbKN+TClSsFWfPBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T00:55:35.153101Z","bundle_sha256":"40aa4153d82537ecb7e4ea23daa3d837bba77d84bbae8e46a7b1189b1ebe6df8"}}