{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:57L7NTEB5AFO7K5ANWQQKFMDKS","short_pith_number":"pith:57L7NTEB","canonical_record":{"source":{"id":"1810.11586","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T03:03:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f39a9c28b4d424745aa5365ddc49e180b1df833f06e5fc01aa6eaba914d1e51a","abstract_canon_sha256":"7dec1ab1eaf3eea9fe06a478c776b233869f3778616fd560e4a18a28a6059c06"},"schema_version":"1.0"},"canonical_sha256":"efd7f6cc81e80aefaba06da105158354b5618f402562b023bc406d5026a3e948","source":{"kind":"arxiv","id":"1810.11586","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11586","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11586v3","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11586","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"57L7NTEB5AFO","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"57L7NTEB5AFO7K5A","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"57L7NTEB","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:57L7NTEB5AFO7K5ANWQQKFMDKS","target":"record","payload":{"canonical_record":{"source":{"id":"1810.11586","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T03:03:57Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"f39a9c28b4d424745aa5365ddc49e180b1df833f06e5fc01aa6eaba914d1e51a","abstract_canon_sha256":"7dec1ab1eaf3eea9fe06a478c776b233869f3778616fd560e4a18a28a6059c06"},"schema_version":"1.0"},"canonical_sha256":"efd7f6cc81e80aefaba06da105158354b5618f402562b023bc406d5026a3e948","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:41.462484Z","signature_b64":"yYwKG6tg8LwY7awb2RCdqcXDudJEKj8QFPtEB2uR7E5fMPreuhi7rrTp2HR8TVkKxj0DPPUyjppB3UaCj07rDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efd7f6cc81e80aefaba06da105158354b5618f402562b023bc406d5026a3e948","last_reissued_at":"2026-05-17T23:46:41.461702Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:41.461702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1810.11586","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R/0LawAmEg2lkBPiz9aMt9Ba6/OL1wbjUyobkk/MfgId63g7nD1WFBxHRyR8kDokRnUHHR+obS//SQ2R0J+2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:51:29.708914Z"},"content_sha256":"a6a2085c642ad2e21bd5c7b771a6f003e08c4d670aeb443a15cd0356fccb2520","schema_version":"1.0","event_id":"sha256:a6a2085c642ad2e21bd5c7b771a6f003e08c4d670aeb443a15cd0356fccb2520"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:57L7NTEB5AFO7K5ANWQQKFMDKS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Azadeh Sadat Mozafari, Christian Gagn\\'e, Hugo Siqueira Gomes, Steeven Janny, Wilson Le\\~ao","submitted_at":"2018-10-27T03:03:57Z","abstract_excerpt":"Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the confidence of deep networks plays an important role to bring the trust and reliability to the system. To calibrate the deep networks' confidence, many probabilistic and measure-based approaches are proposed. Temperature Scaling (TS) is a state-of-the-art among measure-based calibration methods which has low time and memory complexity as well as effectiveness. I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11586","kind":"arxiv","version":3},"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":"2026-05-17T23:46:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j9i1KfVrOEuIgE166kXEff6wje0TqjbUF7Bldk47/2w95pL7wIgVJ9ZBLyInf2VCGFWhelKXDSVOhuensSmrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T14:51:29.709722Z"},"content_sha256":"b2745fde2ab1f05577b6da5a75d815fa6f51d0915aacf0a0abc89bf84f302f12","schema_version":"1.0","event_id":"sha256:b2745fde2ab1f05577b6da5a75d815fa6f51d0915aacf0a0abc89bf84f302f12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57L7NTEB5AFO7K5ANWQQKFMDKS/bundle.json","state_url":"https://pith.science/pith/57L7NTEB5AFO7K5ANWQQKFMDKS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57L7NTEB5AFO7K5ANWQQKFMDKS/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":"2026-05-30T14:51:29Z","links":{"resolver":"https://pith.science/pith/57L7NTEB5AFO7K5ANWQQKFMDKS","bundle":"https://pith.science/pith/57L7NTEB5AFO7K5ANWQQKFMDKS/bundle.json","state":"https://pith.science/pith/57L7NTEB5AFO7K5ANWQQKFMDKS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57L7NTEB5AFO7K5ANWQQKFMDKS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:57L7NTEB5AFO7K5ANWQQKFMDKS","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":"7dec1ab1eaf3eea9fe06a478c776b233869f3778616fd560e4a18a28a6059c06","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T03:03:57Z","title_canon_sha256":"f39a9c28b4d424745aa5365ddc49e180b1df833f06e5fc01aa6eaba914d1e51a"},"schema_version":"1.0","source":{"id":"1810.11586","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1810.11586","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"arxiv_version","alias_value":"1810.11586v3","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.11586","created_at":"2026-05-17T23:46:41Z"},{"alias_kind":"pith_short_12","alias_value":"57L7NTEB5AFO","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"57L7NTEB5AFO7K5A","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"57L7NTEB","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:b2745fde2ab1f05577b6da5a75d815fa6f51d0915aacf0a0abc89bf84f302f12","target":"graph","created_at":"2026-05-17T23:46:41Z","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":"Recently, Deep Neural Networks (DNNs) have been achieving impressive results on wide range of tasks. However, they suffer from being well-calibrated. In decision-making applications, such as autonomous driving or medical diagnosing, the confidence of deep networks plays an important role to bring the trust and reliability to the system. To calibrate the deep networks' confidence, many probabilistic and measure-based approaches are proposed. Temperature Scaling (TS) is a state-of-the-art among measure-based calibration methods which has low time and memory complexity as well as effectiveness. I","authors_text":"Azadeh Sadat Mozafari, Christian Gagn\\'e, Hugo Siqueira Gomes, Steeven Janny, Wilson Le\\~ao","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T03:03:57Z","title":"Attended Temperature Scaling: A Practical Approach for Calibrating Deep Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.11586","kind":"arxiv","version":3},"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:a6a2085c642ad2e21bd5c7b771a6f003e08c4d670aeb443a15cd0356fccb2520","target":"record","created_at":"2026-05-17T23:46:41Z","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":"7dec1ab1eaf3eea9fe06a478c776b233869f3778616fd560e4a18a28a6059c06","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-27T03:03:57Z","title_canon_sha256":"f39a9c28b4d424745aa5365ddc49e180b1df833f06e5fc01aa6eaba914d1e51a"},"schema_version":"1.0","source":{"id":"1810.11586","kind":"arxiv","version":3}},"canonical_sha256":"efd7f6cc81e80aefaba06da105158354b5618f402562b023bc406d5026a3e948","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efd7f6cc81e80aefaba06da105158354b5618f402562b023bc406d5026a3e948","first_computed_at":"2026-05-17T23:46:41.461702Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:41.461702Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yYwKG6tg8LwY7awb2RCdqcXDudJEKj8QFPtEB2uR7E5fMPreuhi7rrTp2HR8TVkKxj0DPPUyjppB3UaCj07rDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:41.462484Z","signed_message":"canonical_sha256_bytes"},"source_id":"1810.11586","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6a2085c642ad2e21bd5c7b771a6f003e08c4d670aeb443a15cd0356fccb2520","sha256:b2745fde2ab1f05577b6da5a75d815fa6f51d0915aacf0a0abc89bf84f302f12"],"state_sha256":"a0cb9931e69180e64bae2147a67d0cd701701142fd2a39106a17f96dc34f6cb4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AceV/8wf/QgQCT9f1eKSgumvFq9FUUGuttuMoWnSwAK29UsaVVo3N1fvk/A7P0oA/N3UXK49FhuY090/LKOTBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T14:51:29.713882Z","bundle_sha256":"767606e6e8550032353a48aeb6117624adc1f46066f56a768511a09ff2f3558a"}}