{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:BASOJIIEJ47LWQVFDNEDSGGS6J","short_pith_number":"pith:BASOJIIE","canonical_record":{"source":{"id":"2309.02636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T00:56:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"425e4d3d3c4bd545e7981742d4fc23bcf6a1d5a09294834e5e99d3fcea6af77b","abstract_canon_sha256":"e4a969761f3917ab721c8be215900e6c28c0b7035acaffcd8ddfa6e5d2ae4d44"},"schema_version":"1.0"},"canonical_sha256":"0824e4a1044f3ebb42a51b483918d2f24325c853a9f828898807ea3046b52df8","source":{"kind":"arxiv","id":"2309.02636","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02636","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02636v1","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02636","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"BASOJIIEJ47L","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"BASOJIIEJ47LWQVF","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"BASOJIIE","created_at":"2026-07-05T06:48:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:BASOJIIEJ47LWQVFDNEDSGGS6J","target":"record","payload":{"canonical_record":{"source":{"id":"2309.02636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T00:56:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"425e4d3d3c4bd545e7981742d4fc23bcf6a1d5a09294834e5e99d3fcea6af77b","abstract_canon_sha256":"e4a969761f3917ab721c8be215900e6c28c0b7035acaffcd8ddfa6e5d2ae4d44"},"schema_version":"1.0"},"canonical_sha256":"0824e4a1044f3ebb42a51b483918d2f24325c853a9f828898807ea3046b52df8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:48:15.242546Z","signature_b64":"qEl0pAtyvywSznW0DE/H29T1Dn9Ad+x1VVqkzALeLj/s39Bt3Lp9y32Fa8ywrQGxt2gRes4X7bfbFyG2hhbmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0824e4a1044f3ebb42a51b483918d2f24325c853a9f828898807ea3046b52df8","last_reissued_at":"2026-07-05T06:48:15.242094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:48:15.242094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.02636","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":"2026-07-05T06:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SSh8EsakW/UbdqMqy7W790WkqzeeCOxRSpgEX+g/QzpAf5W5Y5OdbRZfV7jwGEDdyCC5JcWSqeUajgj4coPaCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:40:07.493270Z"},"content_sha256":"fb46ae1b309e7206f07fc2be2b028240994983ed8f232b40857201490fcfd6e9","schema_version":"1.0","event_id":"sha256:fb46ae1b309e7206f07fc2be2b028240994983ed8f232b40857201490fcfd6e9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:BASOJIIEJ47LWQVFDNEDSGGS6J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiclass Alignment of Confidence and Certainty for Network Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Muhammad Haris Khan, Vinith Kugathasan","submitted_at":"2023-09-06T00:56:24Z","abstract_excerpt":"Deep neural networks (DNNs) have made great strides in pushing the state-of-the-art in several challenging domains. Recent studies reveal that they are prone to making overconfident predictions. This greatly reduces the overall trust in model predictions, especially in safety-critical applications. Early work in improving model calibration employs post-processing techniques which rely on limited parameters and require a hold-out set. Some recent train-time calibration methods, which involve all model parameters, can outperform the postprocessing methods. To this end, we propose a new train-tim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02636","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.02636/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":"2026-07-05T06:48:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uy6xwwB8pwnylURIdDDTPaYQ93qxLcNX6jKHQvMhJayKoxTZA32Ji9srvnk9U9pc7RFtvwnxIHnd2dMI7UAoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T07:40:07.493905Z"},"content_sha256":"18d45b84b5e60a3c5e6c972a971b16a4e6d5b600890ef72a621783000c767640","schema_version":"1.0","event_id":"sha256:18d45b84b5e60a3c5e6c972a971b16a4e6d5b600890ef72a621783000c767640"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BASOJIIEJ47LWQVFDNEDSGGS6J/bundle.json","state_url":"https://pith.science/pith/BASOJIIEJ47LWQVFDNEDSGGS6J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BASOJIIEJ47LWQVFDNEDSGGS6J/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":"2026-08-22T07:40:07Z","links":{"resolver":"https://pith.science/pith/BASOJIIEJ47LWQVFDNEDSGGS6J","bundle":"https://pith.science/pith/BASOJIIEJ47LWQVFDNEDSGGS6J/bundle.json","state":"https://pith.science/pith/BASOJIIEJ47LWQVFDNEDSGGS6J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BASOJIIEJ47LWQVFDNEDSGGS6J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:BASOJIIEJ47LWQVFDNEDSGGS6J","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":"e4a969761f3917ab721c8be215900e6c28c0b7035acaffcd8ddfa6e5d2ae4d44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T00:56:24Z","title_canon_sha256":"425e4d3d3c4bd545e7981742d4fc23bcf6a1d5a09294834e5e99d3fcea6af77b"},"schema_version":"1.0","source":{"id":"2309.02636","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02636","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02636v1","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02636","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_12","alias_value":"BASOJIIEJ47L","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_16","alias_value":"BASOJIIEJ47LWQVF","created_at":"2026-07-05T06:48:15Z"},{"alias_kind":"pith_short_8","alias_value":"BASOJIIE","created_at":"2026-07-05T06:48:15Z"}],"graph_snapshots":[{"event_id":"sha256:18d45b84b5e60a3c5e6c972a971b16a4e6d5b600890ef72a621783000c767640","target":"graph","created_at":"2026-07-05T06:48:15Z","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/2309.02636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks (DNNs) have made great strides in pushing the state-of-the-art in several challenging domains. Recent studies reveal that they are prone to making overconfident predictions. This greatly reduces the overall trust in model predictions, especially in safety-critical applications. Early work in improving model calibration employs post-processing techniques which rely on limited parameters and require a hold-out set. Some recent train-time calibration methods, which involve all model parameters, can outperform the postprocessing methods. To this end, we propose a new train-tim","authors_text":"Muhammad Haris Khan, Vinith Kugathasan","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T00:56:24Z","title":"Multiclass Alignment of Confidence and Certainty for Network Calibration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02636","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:fb46ae1b309e7206f07fc2be2b028240994983ed8f232b40857201490fcfd6e9","target":"record","created_at":"2026-07-05T06:48:15Z","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":"e4a969761f3917ab721c8be215900e6c28c0b7035acaffcd8ddfa6e5d2ae4d44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-09-06T00:56:24Z","title_canon_sha256":"425e4d3d3c4bd545e7981742d4fc23bcf6a1d5a09294834e5e99d3fcea6af77b"},"schema_version":"1.0","source":{"id":"2309.02636","kind":"arxiv","version":1}},"canonical_sha256":"0824e4a1044f3ebb42a51b483918d2f24325c853a9f828898807ea3046b52df8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0824e4a1044f3ebb42a51b483918d2f24325c853a9f828898807ea3046b52df8","first_computed_at":"2026-07-05T06:48:15.242094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:48:15.242094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qEl0pAtyvywSznW0DE/H29T1Dn9Ad+x1VVqkzALeLj/s39Bt3Lp9y32Fa8ywrQGxt2gRes4X7bfbFyG2hhbmCw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:48:15.242546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02636","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fb46ae1b309e7206f07fc2be2b028240994983ed8f232b40857201490fcfd6e9","sha256:18d45b84b5e60a3c5e6c972a971b16a4e6d5b600890ef72a621783000c767640"],"state_sha256":"33d198a525bf4f821c8cc420b7f65b27abfc0cd1b6b0dd89bc87f670bd4c388c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+24KX1oMwbFUjfmAWJ5I1x8EWkR6kHyYCpXJ41WIRKJi01YgnJ8jMcgibqP2fz47KO51DYHl57dYxNo8aMznDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T07:40:07.499977Z","bundle_sha256":"92306106419ca676c5b2d2da4a000c2136ba6378e5fa4af56c40f72d8a6a7c2b"}}