{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3ZGZIL2LC7AAZXMSYZH5U2EUCE","short_pith_number":"pith:3ZGZIL2L","canonical_record":{"source":{"id":"1912.01730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T22:51:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b62f12f41afec8f28955670ccffb743ed91e1bebf3892abede8d5b66f15d9a76","abstract_canon_sha256":"16be29ac8a382ccafcc8bcb90511bed44e2ead9cfd001a2f64f08cfbec7d2155"},"schema_version":"1.0"},"canonical_sha256":"de4d942f4b17c00cdd92c64fda6894110cd5bf864a337b79d231e04350123ca8","source":{"kind":"arxiv","id":"1912.01730","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.01730","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.01730v2","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01730","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"3ZGZIL2LC7AA","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"3ZGZIL2LC7AAZXMS","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"3ZGZIL2L","created_at":"2026-07-05T00:41:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3ZGZIL2LC7AAZXMSYZH5U2EUCE","target":"record","payload":{"canonical_record":{"source":{"id":"1912.01730","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T22:51:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"b62f12f41afec8f28955670ccffb743ed91e1bebf3892abede8d5b66f15d9a76","abstract_canon_sha256":"16be29ac8a382ccafcc8bcb90511bed44e2ead9cfd001a2f64f08cfbec7d2155"},"schema_version":"1.0"},"canonical_sha256":"de4d942f4b17c00cdd92c64fda6894110cd5bf864a337b79d231e04350123ca8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:41:13.491009Z","signature_b64":"s92sk5WuWyudN3/sf5P9GNIa6PECZ82TsetXBRrc9mcIFvHS8Zjr1bb1HWQENeWJCgPvc2ZLoa3e0CFjFLkUBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de4d942f4b17c00cdd92c64fda6894110cd5bf864a337b79d231e04350123ca8","last_reissued_at":"2026-07-05T00:41:13.490493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:41:13.490493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1912.01730","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:41:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nVbmzfnGQEg+m2vD9OHyfUr1AvU3JCgHLgKZwW9lxx+f3vNMz6rjGouhKaiC1T+YO0jCeg6JV/axSaPqsGitCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:45:38.525305Z"},"content_sha256":"9da10eb0051a94bb155aeee47babb9308e162b56f2637fc26f5dac36119e0c24","schema_version":"1.0","event_id":"sha256:9da10eb0051a94bb155aeee47babb9308e162b56f2637fc26f5dac36119e0c24"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3ZGZIL2LC7AAZXMSYZH5U2EUCE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distance-Based Learning from Errors for Confidence Calibration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Chen Xing, Sercan Arik, Tomas Pfister, Zizhao Zhang","submitted_at":"2019-12-03T22:51:51Z","abstract_excerpt":"Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence estimation on distances in the representation space. In DBLE, we first adapt prototypical learning to train classification models. It yields a representation space where the distance between a test sample and its ground truth class center can calibrate the model's classification performance. At inference, however, these distances are not available due to the lack "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01730","kind":"arxiv","version":2},"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/1912.01730/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":"2026-07-05T00:41:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GhTq6Jl3zVe1pU6JUa5ms74EqezulWjCfbCuqHJeRyD9Yjj4NNBIZ31TpDxDABi0NaxvSLDjFxLbLZlWNaaZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T13:45:38.525730Z"},"content_sha256":"d3d737f375b4b37e23be0d4c1ac2aa3bd80c51aacdaefd0f5bade3ef4aef4f9a","schema_version":"1.0","event_id":"sha256:d3d737f375b4b37e23be0d4c1ac2aa3bd80c51aacdaefd0f5bade3ef4aef4f9a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE/bundle.json","state_url":"https://pith.science/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE/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":"2026-07-10T13:45:38Z","links":{"resolver":"https://pith.science/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE","bundle":"https://pith.science/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE/bundle.json","state":"https://pith.science/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3ZGZIL2LC7AAZXMSYZH5U2EUCE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3ZGZIL2LC7AAZXMSYZH5U2EUCE","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":"16be29ac8a382ccafcc8bcb90511bed44e2ead9cfd001a2f64f08cfbec7d2155","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T22:51:51Z","title_canon_sha256":"b62f12f41afec8f28955670ccffb743ed91e1bebf3892abede8d5b66f15d9a76"},"schema_version":"1.0","source":{"id":"1912.01730","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1912.01730","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"arxiv_version","alias_value":"1912.01730v2","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01730","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"pith_short_12","alias_value":"3ZGZIL2LC7AA","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"pith_short_16","alias_value":"3ZGZIL2LC7AAZXMS","created_at":"2026-07-05T00:41:13Z"},{"alias_kind":"pith_short_8","alias_value":"3ZGZIL2L","created_at":"2026-07-05T00:41:13Z"}],"graph_snapshots":[{"event_id":"sha256:d3d737f375b4b37e23be0d4c1ac2aa3bd80c51aacdaefd0f5bade3ef4aef4f9a","target":"graph","created_at":"2026-07-05T00:41:13Z","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/1912.01730/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) are poorly calibrated when trained in conventional ways. To improve confidence calibration of DNNs, we propose a novel training method, distance-based learning from errors (DBLE). DBLE bases its confidence estimation on distances in the representation space. In DBLE, we first adapt prototypical learning to train classification models. It yields a representation space where the distance between a test sample and its ground truth class center can calibrate the model's classification performance. At inference, however, these distances are not available due to the lack ","authors_text":"Chen Xing, Sercan Arik, Tomas Pfister, Zizhao Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T22:51:51Z","title":"Distance-Based Learning from Errors for Confidence Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01730","kind":"arxiv","version":2},"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":"sha256:9da10eb0051a94bb155aeee47babb9308e162b56f2637fc26f5dac36119e0c24","target":"record","created_at":"2026-07-05T00:41:13Z","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":"16be29ac8a382ccafcc8bcb90511bed44e2ead9cfd001a2f64f08cfbec7d2155","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-12-03T22:51:51Z","title_canon_sha256":"b62f12f41afec8f28955670ccffb743ed91e1bebf3892abede8d5b66f15d9a76"},"schema_version":"1.0","source":{"id":"1912.01730","kind":"arxiv","version":2}},"canonical_sha256":"de4d942f4b17c00cdd92c64fda6894110cd5bf864a337b79d231e04350123ca8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"de4d942f4b17c00cdd92c64fda6894110cd5bf864a337b79d231e04350123ca8","first_computed_at":"2026-07-05T00:41:13.490493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:41:13.490493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s92sk5WuWyudN3/sf5P9GNIa6PECZ82TsetXBRrc9mcIFvHS8Zjr1bb1HWQENeWJCgPvc2ZLoa3e0CFjFLkUBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:41:13.491009Z","signed_message":"canonical_sha256_bytes"},"source_id":"1912.01730","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9da10eb0051a94bb155aeee47babb9308e162b56f2637fc26f5dac36119e0c24","sha256:d3d737f375b4b37e23be0d4c1ac2aa3bd80c51aacdaefd0f5bade3ef4aef4f9a"],"state_sha256":"42b00cccfc71d78a0a0e95c992fef60460e950e88d8da028c3bd3bb6f5cdee9b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SjpxQ8XSvQcMRHBocccdSBKPjsnViqfXlH+piZeZFLpyWfBWyqCE/7vx6C+CUC4GJyYXr0BB84Zal3vGjy1YBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T13:45:38.527723Z","bundle_sha256":"b23c891938f0e50f2bc55b9e4d7ffe555a89c05a823f511c1ef042ed6dc21e2c"}}