{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:RSYAEHQUY5NEDNXJMJBICPZPZP","short_pith_number":"pith:RSYAEHQU","canonical_record":{"source":{"id":"1802.07881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-22T13:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"9372d09e102f3c360a5017e8a1759f84370257e3c0fdfadc7f746606af86e34e","abstract_canon_sha256":"73e62ecfdf4edf6fbb0f3eb50f70a88297e54e4332075f226bce81960842915a"},"schema_version":"1.0"},"canonical_sha256":"8cb0021e14c75a41b6e96242813f2fcbd68cbcb9678011fb3988424cfbde25ff","source":{"kind":"arxiv","id":"1802.07881","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07881","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07881v1","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07881","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"RSYAEHQUY5NE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RSYAEHQUY5NEDNXJ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RSYAEHQU","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:RSYAEHQUY5NEDNXJMJBICPZPZP","target":"record","payload":{"canonical_record":{"source":{"id":"1802.07881","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-22T13:24:09Z","cross_cats_sorted":[],"title_canon_sha256":"9372d09e102f3c360a5017e8a1759f84370257e3c0fdfadc7f746606af86e34e","abstract_canon_sha256":"73e62ecfdf4edf6fbb0f3eb50f70a88297e54e4332075f226bce81960842915a"},"schema_version":"1.0"},"canonical_sha256":"8cb0021e14c75a41b6e96242813f2fcbd68cbcb9678011fb3988424cfbde25ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:22:48.692195Z","signature_b64":"/aMOIIgqo2x5KTxDy9H446cDQTdVIsUlYhWqNRoNp4jGP0CEfLdDS+FoWGHqIcDNeaPCwCZIG25YarXiaiQYDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cb0021e14c75a41b6e96242813f2fcbd68cbcb9678011fb3988424cfbde25ff","last_reissued_at":"2026-05-18T00:22:48.691707Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:22:48.691707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1802.07881","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":"2026-05-18T00:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P+NNxuFS8FDosweM71qiIfsB8o+mYNV59UsuLeX9rbCqPkhbYX4aguuJvE4VA8JbMMK4iPa4F6Vl9iyCuI/LDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T07:16:38.580071Z"},"content_sha256":"dd25cb1b78d809987123016f50988a4ff4ef5f83017c8994803e1f2355ca5f60","schema_version":"1.0","event_id":"sha256:dd25cb1b78d809987123016f50988a4ff4ef5f83017c8994803e1f2355ca5f60"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:RSYAEHQUY5NEDNXJMJBICPZPZP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diversity regularization in deep ensembles","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Azadeh Sadat Mozafari, Changjian Shui, Christian Gagn\\'e, Ihsen Hedhli, Jonathan Marek","submitted_at":"2018-02-22T13:24:09Z","abstract_excerpt":"Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been reported that deep neural network models are often too poorly calibrated for achieving complex tasks requiring reliable uncertainty estimates in their prediction. In this work, we are proposing a strategy for training deep ensembles with a diversity function regularization, which improves the calibration property while maintaining a similar prediction accuracy."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07881","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":"2026-05-18T00:22:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I5OXKkWAuatrkx2Hs/he4RO0r+UQVB/JaqTraAtRAFKDc2uDRP4CL83SJm7KfHjlxYQT1kYeYBdtd+KyrZ8pDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T07:16:38.580426Z"},"content_sha256":"e0516a953261f6d3d3c53b1f4cd635e0339b9d60a8a25780ca4a3c8b34194bd4","schema_version":"1.0","event_id":"sha256:e0516a953261f6d3d3c53b1f4cd635e0339b9d60a8a25780ca4a3c8b34194bd4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RSYAEHQUY5NEDNXJMJBICPZPZP/bundle.json","state_url":"https://pith.science/pith/RSYAEHQUY5NEDNXJMJBICPZPZP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RSYAEHQUY5NEDNXJMJBICPZPZP/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":"2026-06-28T07:16:38Z","links":{"resolver":"https://pith.science/pith/RSYAEHQUY5NEDNXJMJBICPZPZP","bundle":"https://pith.science/pith/RSYAEHQUY5NEDNXJMJBICPZPZP/bundle.json","state":"https://pith.science/pith/RSYAEHQUY5NEDNXJMJBICPZPZP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RSYAEHQUY5NEDNXJMJBICPZPZP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:RSYAEHQUY5NEDNXJMJBICPZPZP","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":"73e62ecfdf4edf6fbb0f3eb50f70a88297e54e4332075f226bce81960842915a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-22T13:24:09Z","title_canon_sha256":"9372d09e102f3c360a5017e8a1759f84370257e3c0fdfadc7f746606af86e34e"},"schema_version":"1.0","source":{"id":"1802.07881","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1802.07881","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"arxiv_version","alias_value":"1802.07881v1","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1802.07881","created_at":"2026-05-18T00:22:48Z"},{"alias_kind":"pith_short_12","alias_value":"RSYAEHQUY5NE","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"RSYAEHQUY5NEDNXJ","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"RSYAEHQU","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:e0516a953261f6d3d3c53b1f4cd635e0339b9d60a8a25780ca4a3c8b34194bd4","target":"graph","created_at":"2026-05-18T00:22:48Z","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":"Calibrating the confidence of supervised learning models is important for a variety of contexts where the certainty over predictions should be reliable. However, it has been reported that deep neural network models are often too poorly calibrated for achieving complex tasks requiring reliable uncertainty estimates in their prediction. In this work, we are proposing a strategy for training deep ensembles with a diversity function regularization, which improves the calibration property while maintaining a similar prediction accuracy.","authors_text":"Azadeh Sadat Mozafari, Changjian Shui, Christian Gagn\\'e, Ihsen Hedhli, Jonathan Marek","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-22T13:24:09Z","title":"Diversity regularization in deep ensembles"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1802.07881","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:dd25cb1b78d809987123016f50988a4ff4ef5f83017c8994803e1f2355ca5f60","target":"record","created_at":"2026-05-18T00:22:48Z","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":"73e62ecfdf4edf6fbb0f3eb50f70a88297e54e4332075f226bce81960842915a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2018-02-22T13:24:09Z","title_canon_sha256":"9372d09e102f3c360a5017e8a1759f84370257e3c0fdfadc7f746606af86e34e"},"schema_version":"1.0","source":{"id":"1802.07881","kind":"arxiv","version":1}},"canonical_sha256":"8cb0021e14c75a41b6e96242813f2fcbd68cbcb9678011fb3988424cfbde25ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8cb0021e14c75a41b6e96242813f2fcbd68cbcb9678011fb3988424cfbde25ff","first_computed_at":"2026-05-18T00:22:48.691707Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:22:48.691707Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/aMOIIgqo2x5KTxDy9H446cDQTdVIsUlYhWqNRoNp4jGP0CEfLdDS+FoWGHqIcDNeaPCwCZIG25YarXiaiQYDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:22:48.692195Z","signed_message":"canonical_sha256_bytes"},"source_id":"1802.07881","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd25cb1b78d809987123016f50988a4ff4ef5f83017c8994803e1f2355ca5f60","sha256:e0516a953261f6d3d3c53b1f4cd635e0339b9d60a8a25780ca4a3c8b34194bd4"],"state_sha256":"72867c38e6ea6a17cf5e7b4cc0c5bc5d07a798d9b8ca632349027423356a9261"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEKLX8pKbx5ByUUvd71rqu4tx4Xzw0+Gc6M+mTmvQLvGx5iuKz/3BrCtdiM5eSruB4eCa1xddzEfpDJ8E+1ICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T07:16:38.582447Z","bundle_sha256":"be2092486ac4dfaf84e850115b9381ad0e167a4e813dfa2dcaf9da79d876c741"}}