{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZKGC7EBNFF6YKMB3RMJ7XSKXRS","short_pith_number":"pith:ZKGC7EBN","canonical_record":{"source":{"id":"1905.11001","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T07:00:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b41e4703c9a0f695dc20505c3d424468861c8a131de993c2831142cb27513d33","abstract_canon_sha256":"ba2a06629904299c4fe6b2a59ad768f104a52bbc141f664ac347eeaae17dca49"},"schema_version":"1.0"},"canonical_sha256":"ca8c2f902d297d85303b8b13fbc9578c9170fffc0dcf88082214f6b5c0ee9480","source":{"kind":"arxiv","id":"1905.11001","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11001","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11001v5","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11001","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZKGC7EBNFF6Y","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZKGC7EBNFF6YKMB3","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZKGC7EBN","created_at":"2026-07-05T00:30:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZKGC7EBNFF6YKMB3RMJ7XSKXRS","target":"record","payload":{"canonical_record":{"source":{"id":"1905.11001","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T07:00:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b41e4703c9a0f695dc20505c3d424468861c8a131de993c2831142cb27513d33","abstract_canon_sha256":"ba2a06629904299c4fe6b2a59ad768f104a52bbc141f664ac347eeaae17dca49"},"schema_version":"1.0"},"canonical_sha256":"ca8c2f902d297d85303b8b13fbc9578c9170fffc0dcf88082214f6b5c0ee9480","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:30:14.344994Z","signature_b64":"nPepNnHoRyqowGDW5SUOW4VBX8E1+xfbxCgllvFsdiog6LZv6VOb/v5Y/AJUUgNd06tDys5dsdZPIcRqO2JmDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca8c2f902d297d85303b8b13fbc9578c9170fffc0dcf88082214f6b5c0ee9480","last_reissued_at":"2026-07-05T00:30:14.344528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:30:14.344528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.11001","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:30:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"617huq3PLnLUghXFgOYlTFXtPJloJENrJ6RmjLKjHQHvRPD7SmihIrubIucq0WCZViO6msQYkx9gXYSStvV9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:59:46.234933Z"},"content_sha256":"73c8ed28aed116e3375b43bd598e3c00f6d41b6040202a8013cb5313af2c2246","schema_version":"1.0","event_id":"sha256:73c8ed28aed116e3375b43bd598e3c00f6d41b6040202a8013cb5313af2c2246"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZKGC7EBNFF6YKMB3RMJ7XSKXRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Gopinath Chennupati, Jeff Bilmes, Sarah Michalak, Sunil Thulasidasan, Tanmoy Bhattacharya","submitted_at":"2019-05-27T07:00:33Z","abstract_excerpt":"Mixup~\\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to implement, it has been shown to be a surprisingly effective method of data augmentation for image classification: DNNs trained with mixup show noticeable gains in classification performance on a number of image classification benchmarks. In this work, we discuss a hitherto untouched aspect of mixup training -- the calibration and predictive uncertainty of model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11001","kind":"arxiv","version":5},"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/1905.11001/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":"2026-07-05T00:30:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QLEHXu905FE9vpWEf2eZL7Sma07sF+z/8AOOY+7c0B0/qT4H17+t321D1VG+zmXJ5CIhBlrxpDqxMsdOtZnTAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T03:59:46.235867Z"},"content_sha256":"d0df905889ba42eeecf0d8f6817802c95b06cf84150edf88238d438664445b28","schema_version":"1.0","event_id":"sha256:d0df905889ba42eeecf0d8f6817802c95b06cf84150edf88238d438664445b28"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS/bundle.json","state_url":"https://pith.science/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS/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":"2026-08-12T03:59:46Z","links":{"resolver":"https://pith.science/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS","bundle":"https://pith.science/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS/bundle.json","state":"https://pith.science/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZKGC7EBNFF6YKMB3RMJ7XSKXRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZKGC7EBNFF6YKMB3RMJ7XSKXRS","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":"ba2a06629904299c4fe6b2a59ad768f104a52bbc141f664ac347eeaae17dca49","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T07:00:33Z","title_canon_sha256":"b41e4703c9a0f695dc20505c3d424468861c8a131de993c2831142cb27513d33"},"schema_version":"1.0","source":{"id":"1905.11001","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.11001","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"arxiv_version","alias_value":"1905.11001v5","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.11001","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"pith_short_12","alias_value":"ZKGC7EBNFF6Y","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"pith_short_16","alias_value":"ZKGC7EBNFF6YKMB3","created_at":"2026-07-05T00:30:14Z"},{"alias_kind":"pith_short_8","alias_value":"ZKGC7EBN","created_at":"2026-07-05T00:30:14Z"}],"graph_snapshots":[{"event_id":"sha256:d0df905889ba42eeecf0d8f6817802c95b06cf84150edf88238d438664445b28","target":"graph","created_at":"2026-07-05T00:30:14Z","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/1905.11001/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixup~\\cite{zhang2017mixup} is a recently proposed method for training deep neural networks where additional samples are generated during training by convexly combining random pairs of images and their associated labels. While simple to implement, it has been shown to be a surprisingly effective method of data augmentation for image classification: DNNs trained with mixup show noticeable gains in classification performance on a number of image classification benchmarks. In this work, we discuss a hitherto untouched aspect of mixup training -- the calibration and predictive uncertainty of model","authors_text":"Gopinath Chennupati, Jeff Bilmes, Sarah Michalak, Sunil Thulasidasan, Tanmoy Bhattacharya","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T07:00:33Z","title":"On Mixup Training: Improved Calibration and Predictive Uncertainty for Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.11001","kind":"arxiv","version":5},"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":"sha256:73c8ed28aed116e3375b43bd598e3c00f6d41b6040202a8013cb5313af2c2246","target":"record","created_at":"2026-07-05T00:30:14Z","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":"ba2a06629904299c4fe6b2a59ad768f104a52bbc141f664ac347eeaae17dca49","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-05-27T07:00:33Z","title_canon_sha256":"b41e4703c9a0f695dc20505c3d424468861c8a131de993c2831142cb27513d33"},"schema_version":"1.0","source":{"id":"1905.11001","kind":"arxiv","version":5}},"canonical_sha256":"ca8c2f902d297d85303b8b13fbc9578c9170fffc0dcf88082214f6b5c0ee9480","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ca8c2f902d297d85303b8b13fbc9578c9170fffc0dcf88082214f6b5c0ee9480","first_computed_at":"2026-07-05T00:30:14.344528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:30:14.344528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nPepNnHoRyqowGDW5SUOW4VBX8E1+xfbxCgllvFsdiog6LZv6VOb/v5Y/AJUUgNd06tDys5dsdZPIcRqO2JmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:30:14.344994Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.11001","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73c8ed28aed116e3375b43bd598e3c00f6d41b6040202a8013cb5313af2c2246","sha256:d0df905889ba42eeecf0d8f6817802c95b06cf84150edf88238d438664445b28"],"state_sha256":"2de9a49fc9bb56b54276b158a22f4b0d182c0a14ca01e3453a084cf677066d83"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eyiN5hTJTotyU4SpN018CTyQdQkpZgihTZXXkagx0FmPkqMdMdh2IILLxzXwH3cnK/b9Fd5Z9r6VxStT8YSMDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T03:59:46.242943Z","bundle_sha256":"f01bf7b5c800778a547862f87d7ca241690884af65b4b91cd93c7729d7dc07ea"}}