{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:V6NLNL7MO32HMUNUTVBOZ6XOPH","short_pith_number":"pith:V6NLNL7M","canonical_record":{"source":{"id":"2002.09831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T05:13:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9beb70d0ed22a7639832f8b99ebb6024973a05748d04358121c7aaf4584720d7","abstract_canon_sha256":"832ae513f4a48bf577e6d442cefa72dfda3996e0c2695480971db9d1823f2d17"},"schema_version":"1.0"},"canonical_sha256":"af9ab6afec76f47651b49d42ecfaee79c6fbf2011bb1ea64bac93ba17ca60a4d","source":{"kind":"arxiv","id":"2002.09831","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09831","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09831v1","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09831","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"V6NLNL7MO32H","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"V6NLNL7MO32HMUNU","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"V6NLNL7M","created_at":"2026-07-05T00:43:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:V6NLNL7MO32HMUNUTVBOZ6XOPH","target":"record","payload":{"canonical_record":{"source":{"id":"2002.09831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T05:13:12Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9beb70d0ed22a7639832f8b99ebb6024973a05748d04358121c7aaf4584720d7","abstract_canon_sha256":"832ae513f4a48bf577e6d442cefa72dfda3996e0c2695480971db9d1823f2d17"},"schema_version":"1.0"},"canonical_sha256":"af9ab6afec76f47651b49d42ecfaee79c6fbf2011bb1ea64bac93ba17ca60a4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:12.082166Z","signature_b64":"3ucFULevydIEK7PJs6WTYIZi4VoykHsUdxXv4GwAuTZ2udMILpYGEBvet+3cZgTFS2J+ph9PLKL92CmtjzI/AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af9ab6afec76f47651b49d42ecfaee79c6fbf2011bb1ea64bac93ba17ca60a4d","last_reissued_at":"2026-07-05T00:43:12.081730Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:12.081730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.09831","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":"2026-07-05T00:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xE5xu40HqqSG/ttLe/I6ymJXxWS895dwq59tqGUDVzouAnaer7uRobfXaTAD5/23Fn6pyDEHRRd+HtJtbXCQDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:17:53.059164Z"},"content_sha256":"1d7c3b92057b0b4c1032f7e87de5d553942badd72fab643241f29166d5dccd4d","schema_version":"1.0","event_id":"sha256:1d7c3b92057b0b4c1032f7e87de5d553942badd72fab643241f29166d5dccd4d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:V6NLNL7MO32HMUNUTVBOZ6XOPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Role of Dataset Quality and Heterogeneity in Model Confidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiasi Chen, Samet Oymak, Yuan Zhao","submitted_at":"2020-02-23T05:13:12Z","abstract_excerpt":"Safety-critical applications require machine learning models that output accurate and calibrated probabilities. While uncalibrated deep networks are known to make over-confident predictions, it is unclear how model confidence is impacted by the variations in the data, such as label noise or class size. In this paper, we investigate the role of the dataset quality by studying the impact of dataset size and the label noise on the model confidence. We theoretically explain and experimentally demonstrate that, surprisingly, label noise in the training data leads to under-confident networks, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09831","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/2002.09831/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":"2026-07-05T00:43:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KFv9FwF9JuOv6eyGOPr7YVo8JWkqO2jy1j6+/ZeBFvMP4PZhJyuRVspcYlvR3XHVrOy/SHvDwAyZLMHOJGd+AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T21:17:53.059659Z"},"content_sha256":"c6420f4f1c077940dba9046b568d7214c68d71a06f8a9fab19eee9c2f5e8d2fc","schema_version":"1.0","event_id":"sha256:c6420f4f1c077940dba9046b568d7214c68d71a06f8a9fab19eee9c2f5e8d2fc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH/bundle.json","state_url":"https://pith.science/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH/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":"2026-08-05T21:17:53Z","links":{"resolver":"https://pith.science/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH","bundle":"https://pith.science/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH/bundle.json","state":"https://pith.science/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V6NLNL7MO32HMUNUTVBOZ6XOPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:V6NLNL7MO32HMUNUTVBOZ6XOPH","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":"832ae513f4a48bf577e6d442cefa72dfda3996e0c2695480971db9d1823f2d17","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T05:13:12Z","title_canon_sha256":"9beb70d0ed22a7639832f8b99ebb6024973a05748d04358121c7aaf4584720d7"},"schema_version":"1.0","source":{"id":"2002.09831","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.09831","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"arxiv_version","alias_value":"2002.09831v1","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.09831","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_12","alias_value":"V6NLNL7MO32H","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_16","alias_value":"V6NLNL7MO32HMUNU","created_at":"2026-07-05T00:43:12Z"},{"alias_kind":"pith_short_8","alias_value":"V6NLNL7M","created_at":"2026-07-05T00:43:12Z"}],"graph_snapshots":[{"event_id":"sha256:c6420f4f1c077940dba9046b568d7214c68d71a06f8a9fab19eee9c2f5e8d2fc","target":"graph","created_at":"2026-07-05T00:43:12Z","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/2002.09831/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Safety-critical applications require machine learning models that output accurate and calibrated probabilities. While uncalibrated deep networks are known to make over-confident predictions, it is unclear how model confidence is impacted by the variations in the data, such as label noise or class size. In this paper, we investigate the role of the dataset quality by studying the impact of dataset size and the label noise on the model confidence. We theoretically explain and experimentally demonstrate that, surprisingly, label noise in the training data leads to under-confident networks, while ","authors_text":"Jiasi Chen, Samet Oymak, Yuan Zhao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T05:13:12Z","title":"On the Role of Dataset Quality and Heterogeneity in Model Confidence"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.09831","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":"sha256:1d7c3b92057b0b4c1032f7e87de5d553942badd72fab643241f29166d5dccd4d","target":"record","created_at":"2026-07-05T00:43:12Z","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":"832ae513f4a48bf577e6d442cefa72dfda3996e0c2695480971db9d1823f2d17","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-23T05:13:12Z","title_canon_sha256":"9beb70d0ed22a7639832f8b99ebb6024973a05748d04358121c7aaf4584720d7"},"schema_version":"1.0","source":{"id":"2002.09831","kind":"arxiv","version":1}},"canonical_sha256":"af9ab6afec76f47651b49d42ecfaee79c6fbf2011bb1ea64bac93ba17ca60a4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"af9ab6afec76f47651b49d42ecfaee79c6fbf2011bb1ea64bac93ba17ca60a4d","first_computed_at":"2026-07-05T00:43:12.081730Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:43:12.081730Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3ucFULevydIEK7PJs6WTYIZi4VoykHsUdxXv4GwAuTZ2udMILpYGEBvet+3cZgTFS2J+ph9PLKL92CmtjzI/AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:43:12.082166Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.09831","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d7c3b92057b0b4c1032f7e87de5d553942badd72fab643241f29166d5dccd4d","sha256:c6420f4f1c077940dba9046b568d7214c68d71a06f8a9fab19eee9c2f5e8d2fc"],"state_sha256":"ee23019eb73a586d603fd59f60ca3c3796e102644acd5f2ed211c0361c9ae255"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcp33kDVMqIFUl3sanAksuSHTW9UT+ODeGQs7T2jbw4GaqSpMcNLGRZ5L1dDqXmkQy3poQxvsSK7NzIJ7uG0DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T21:17:53.066367Z","bundle_sha256":"45c495450d077557e4e4d40d938aa83a07e2cd90b7504cdd8efc5961d1193f09"}}