{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TLT7ZLH4DQFLSF3ZUL4TMEONEM","short_pith_number":"pith:TLT7ZLH4","canonical_record":{"source":{"id":"1906.09551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T04:34:14Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"cbeded080e3e6531d4aea3e7d6df9d5385b604729ef76a8d384b2559cbd2fbff","abstract_canon_sha256":"06e748fe4df474f08ba42bf393ed1c22f1af84107108c67f0dae2ebd797360e0"},"schema_version":"1.0"},"canonical_sha256":"9ae7fcacfc1c0ab91779a2f93611cd230feee17841f6670c5c7456e2b968c57c","source":{"kind":"arxiv","id":"1906.09551","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09551","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09551v1","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09551","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"TLT7ZLH4DQFL","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TLT7ZLH4DQFLSF3Z","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TLT7ZLH4","created_at":"2026-05-18T12:33:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TLT7ZLH4DQFLSF3ZUL4TMEONEM","target":"record","payload":{"canonical_record":{"source":{"id":"1906.09551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T04:34:14Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"cbeded080e3e6531d4aea3e7d6df9d5385b604729ef76a8d384b2559cbd2fbff","abstract_canon_sha256":"06e748fe4df474f08ba42bf393ed1c22f1af84107108c67f0dae2ebd797360e0"},"schema_version":"1.0"},"canonical_sha256":"9ae7fcacfc1c0ab91779a2f93611cd230feee17841f6670c5c7456e2b968c57c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:37.598369Z","signature_b64":"S5MNYAqUcZjELzDOjq2dgk6WsGWzpKaIS0gPuAbknQmnXhQ9eS6hAEvt95kzm3Df58CAjLCzSdQYuBoCVF0sDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ae7fcacfc1c0ab91779a2f93611cd230feee17841f6670c5c7456e2b968c57c","last_reissued_at":"2026-05-17T23:42:37.597573Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:37.597573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.09551","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":"2026-05-17T23:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pOFFdTXCiVako2nAtVH/iNcOxAPvbgUefniWISNJXlwl/1z+Z8bdH67SpM8pMbv9E6ASGgpYBkNS8GEO1EACAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:09:37.710380Z"},"content_sha256":"4609fd06765257170a1746ce6fc0ba31badd2e8e9bf4d38150ab442354051d76","schema_version":"1.0","event_id":"sha256:4609fd06765257170a1746ce6fc0ba31badd2e8e9bf4d38150ab442354051d76"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TLT7ZLH4DQFLSF3ZUL4TMEONEM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Confidence Calibration for Convolutional Neural Networks Using Structured Dropout","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adrian V. Dalca, Mert R. Sabuncu, Zhilu Zhang","submitted_at":"2019-06-23T04:34:14Z","abstract_excerpt":"In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify uncertainty in neural network models. However, as previously demonstrated, confidence estimates computed with a naive implementation of dropout can be poorly calibrated, particularly when using convolutional networks. In this paper, through the lens of ensemble learning, we associate calibration error with the correlation between the models sampled with dro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09551","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":""},"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":"2026-05-17T23:42:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yv/Nk9/wel1KFF9OUatkKBnW+kvAKA+NHpjZAzY+6PF6FYZcR+yZtMnoKiJ+A5LN2m7rsH7ec65XOw4dLbgkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T13:09:37.710749Z"},"content_sha256":"749d1ba7580f3cf056d0b42087c69aaec14e1027a788cb9f545d9abe9a571d1b","schema_version":"1.0","event_id":"sha256:749d1ba7580f3cf056d0b42087c69aaec14e1027a788cb9f545d9abe9a571d1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM/bundle.json","state_url":"https://pith.science/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM/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":"2026-06-02T13:09:37Z","links":{"resolver":"https://pith.science/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM","bundle":"https://pith.science/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM/bundle.json","state":"https://pith.science/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TLT7ZLH4DQFLSF3ZUL4TMEONEM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TLT7ZLH4DQFLSF3ZUL4TMEONEM","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":"06e748fe4df474f08ba42bf393ed1c22f1af84107108c67f0dae2ebd797360e0","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T04:34:14Z","title_canon_sha256":"cbeded080e3e6531d4aea3e7d6df9d5385b604729ef76a8d384b2559cbd2fbff"},"schema_version":"1.0","source":{"id":"1906.09551","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.09551","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"arxiv_version","alias_value":"1906.09551v1","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.09551","created_at":"2026-05-17T23:42:37Z"},{"alias_kind":"pith_short_12","alias_value":"TLT7ZLH4DQFL","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_16","alias_value":"TLT7ZLH4DQFLSF3Z","created_at":"2026-05-18T12:33:30Z"},{"alias_kind":"pith_short_8","alias_value":"TLT7ZLH4","created_at":"2026-05-18T12:33:30Z"}],"graph_snapshots":[{"event_id":"sha256:749d1ba7580f3cf056d0b42087c69aaec14e1027a788cb9f545d9abe9a571d1b","target":"graph","created_at":"2026-05-17T23:42:37Z","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":"In classification applications, we often want probabilistic predictions to reflect confidence or uncertainty. Dropout, a commonly used training technique, has recently been linked to Bayesian inference, yielding an efficient way to quantify uncertainty in neural network models. However, as previously demonstrated, confidence estimates computed with a naive implementation of dropout can be poorly calibrated, particularly when using convolutional networks. In this paper, through the lens of ensemble learning, we associate calibration error with the correlation between the models sampled with dro","authors_text":"Adrian V. Dalca, Mert R. Sabuncu, Zhilu Zhang","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T04:34:14Z","title":"Confidence Calibration for Convolutional Neural Networks Using Structured Dropout"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.09551","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":"sha256:4609fd06765257170a1746ce6fc0ba31badd2e8e9bf4d38150ab442354051d76","target":"record","created_at":"2026-05-17T23:42:37Z","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":"06e748fe4df474f08ba42bf393ed1c22f1af84107108c67f0dae2ebd797360e0","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-23T04:34:14Z","title_canon_sha256":"cbeded080e3e6531d4aea3e7d6df9d5385b604729ef76a8d384b2559cbd2fbff"},"schema_version":"1.0","source":{"id":"1906.09551","kind":"arxiv","version":1}},"canonical_sha256":"9ae7fcacfc1c0ab91779a2f93611cd230feee17841f6670c5c7456e2b968c57c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ae7fcacfc1c0ab91779a2f93611cd230feee17841f6670c5c7456e2b968c57c","first_computed_at":"2026-05-17T23:42:37.597573Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:42:37.597573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S5MNYAqUcZjELzDOjq2dgk6WsGWzpKaIS0gPuAbknQmnXhQ9eS6hAEvt95kzm3Df58CAjLCzSdQYuBoCVF0sDQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:42:37.598369Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.09551","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4609fd06765257170a1746ce6fc0ba31badd2e8e9bf4d38150ab442354051d76","sha256:749d1ba7580f3cf056d0b42087c69aaec14e1027a788cb9f545d9abe9a571d1b"],"state_sha256":"2750dd97fe7e0bfe1cfb858cca5be1839e1359b61842184cf4cce87eec2be8e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZQC9/A5jNPJm4vjVd6IEjroBz/ESCijYnSNoz65wKEUpCuINQEYzRywtRUZTnBllS8+aFpPQF4CmsQZK5PYQCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T13:09:37.712782Z","bundle_sha256":"c5841b9e6a0e35c3679ab77abc01684a4121675b0eeb5d876da211eb9fb73743"}}