{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:4VENTA4GW5FYDSN4Z5CDNVG444","short_pith_number":"pith:4VENTA4G","canonical_record":{"source":{"id":"2106.09385","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T11:04:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d3dd09252ee27f8c0b63989486b17c8b45b813ad5187f5e1dfc2adf2bbf3327b","abstract_canon_sha256":"e23f414805271c73808d8331f5056addc8cef95b785a920d0ef8ef8cbdaacf1e"},"schema_version":"1.0"},"canonical_sha256":"e548d98386b74b81c9bccf4436d4dce7129ae5e0ef50c61285dead895935d5e6","source":{"kind":"arxiv","id":"2106.09385","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09385","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09385v3","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09385","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"pith_short_12","alias_value":"4VENTA4GW5FY","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"pith_short_16","alias_value":"4VENTA4GW5FYDSN4","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"pith_short_8","alias_value":"4VENTA4G","created_at":"2026-07-05T04:20:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:4VENTA4GW5FYDSN4Z5CDNVG444","target":"record","payload":{"canonical_record":{"source":{"id":"2106.09385","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T11:04:14Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"d3dd09252ee27f8c0b63989486b17c8b45b813ad5187f5e1dfc2adf2bbf3327b","abstract_canon_sha256":"e23f414805271c73808d8331f5056addc8cef95b785a920d0ef8ef8cbdaacf1e"},"schema_version":"1.0"},"canonical_sha256":"e548d98386b74b81c9bccf4436d4dce7129ae5e0ef50c61285dead895935d5e6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:20:15.004413Z","signature_b64":"JYg+j0WUxpxBWhk4Xmt0YGdGNXaWFuoNGI4gUaHCvhHFDW54k6xyCchdTnXQcoLz3qIVuZ+WbuF4YwC2KefPAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e548d98386b74b81c9bccf4436d4dce7129ae5e0ef50c61285dead895935d5e6","last_reissued_at":"2026-07-05T04:20:15.003940Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:20:15.003940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.09385","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":"2026-07-05T04:20:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rrf+ellKPSgg9vpFqI9njh20nXUD/KHQLsVGhzujSyhVsxySocDC+cRQLp4e5ZDoq3THAqjZzFH6W7MSTxZZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:49:50.133425Z"},"content_sha256":"3f0dc5ce76af3f197811d7d094f6c6525134f518ca02bb4705477cfae7499739","schema_version":"1.0","event_id":"sha256:3f0dc5ce76af3f197811d7d094f6c6525134f518ca02bb4705477cfae7499739"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:4VENTA4GW5FYDSN4Z5CDNVG444","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On Deep Neural Network Calibration by Regularization and its Impact on Refinement","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Aditya Singh, Alessandro Bay, Andrea Mirabile, Biswa Sengupta","submitted_at":"2021-06-17T11:04:14Z","abstract_excerpt":"Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many recently proposed approaches to mitigate this have demonstrated substantial progress in improving DNN calibration. However, they hardly touch upon refinement, which historically has been an essential aspect of calibration. Refinement indicates separability of a network's correct and incorrect predictions. This paper presents a theoretically and empirically su"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09385","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2106.09385/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":"2026-07-05T04:20:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9khzmxi/PSrufEkA+GseO+9Wam4VgCy/6yxK7tsvwpyz32CwAcUH+GCIe6T2/hTGgXGUnMswDYbe/A2IGvNVDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T15:49:50.133982Z"},"content_sha256":"dd6c8ced9c6bce60c7b02242a4eaf84f5ab8ca0d6520ff62f341df6852271173","schema_version":"1.0","event_id":"sha256:dd6c8ced9c6bce60c7b02242a4eaf84f5ab8ca0d6520ff62f341df6852271173"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4VENTA4GW5FYDSN4Z5CDNVG444/bundle.json","state_url":"https://pith.science/pith/4VENTA4GW5FYDSN4Z5CDNVG444/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4VENTA4GW5FYDSN4Z5CDNVG444/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":"2026-08-21T15:49:50Z","links":{"resolver":"https://pith.science/pith/4VENTA4GW5FYDSN4Z5CDNVG444","bundle":"https://pith.science/pith/4VENTA4GW5FYDSN4Z5CDNVG444/bundle.json","state":"https://pith.science/pith/4VENTA4GW5FYDSN4Z5CDNVG444/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4VENTA4GW5FYDSN4Z5CDNVG444/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4VENTA4GW5FYDSN4Z5CDNVG444","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":"e23f414805271c73808d8331f5056addc8cef95b785a920d0ef8ef8cbdaacf1e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T11:04:14Z","title_canon_sha256":"d3dd09252ee27f8c0b63989486b17c8b45b813ad5187f5e1dfc2adf2bbf3327b"},"schema_version":"1.0","source":{"id":"2106.09385","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09385","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09385v3","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09385","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"pith_short_12","alias_value":"4VENTA4GW5FY","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"pith_short_16","alias_value":"4VENTA4GW5FYDSN4","created_at":"2026-07-05T04:20:15Z"},{"alias_kind":"pith_short_8","alias_value":"4VENTA4G","created_at":"2026-07-05T04:20:15Z"}],"graph_snapshots":[{"event_id":"sha256:dd6c8ced9c6bce60c7b02242a4eaf84f5ab8ca0d6520ff62f341df6852271173","target":"graph","created_at":"2026-07-05T04:20:15Z","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/2106.09385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deep neural networks have been shown to be highly miscalibrated. often they tend to be overconfident in their predictions. It poses a significant challenge for safety-critical systems to utilise deep neural networks (DNNs), reliably. Many recently proposed approaches to mitigate this have demonstrated substantial progress in improving DNN calibration. However, they hardly touch upon refinement, which historically has been an essential aspect of calibration. Refinement indicates separability of a network's correct and incorrect predictions. This paper presents a theoretically and empirically su","authors_text":"Aditya Singh, Alessandro Bay, Andrea Mirabile, Biswa Sengupta","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T11:04:14Z","title":"On Deep Neural Network Calibration by Regularization and its Impact on Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09385","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":"sha256:3f0dc5ce76af3f197811d7d094f6c6525134f518ca02bb4705477cfae7499739","target":"record","created_at":"2026-07-05T04:20:15Z","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":"e23f414805271c73808d8331f5056addc8cef95b785a920d0ef8ef8cbdaacf1e","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-17T11:04:14Z","title_canon_sha256":"d3dd09252ee27f8c0b63989486b17c8b45b813ad5187f5e1dfc2adf2bbf3327b"},"schema_version":"1.0","source":{"id":"2106.09385","kind":"arxiv","version":3}},"canonical_sha256":"e548d98386b74b81c9bccf4436d4dce7129ae5e0ef50c61285dead895935d5e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e548d98386b74b81c9bccf4436d4dce7129ae5e0ef50c61285dead895935d5e6","first_computed_at":"2026-07-05T04:20:15.003940Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:20:15.003940Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JYg+j0WUxpxBWhk4Xmt0YGdGNXaWFuoNGI4gUaHCvhHFDW54k6xyCchdTnXQcoLz3qIVuZ+WbuF4YwC2KefPAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:20:15.004413Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09385","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f0dc5ce76af3f197811d7d094f6c6525134f518ca02bb4705477cfae7499739","sha256:dd6c8ced9c6bce60c7b02242a4eaf84f5ab8ca0d6520ff62f341df6852271173"],"state_sha256":"423dd77b63832acbc916497323b848593605fc87239fa93f5e01d740b831282f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BZk+AJefwFXRDvST12zv9Y2PuxKbYN5OS670GYPQmUVz/ITRs7Elv7q2aMywxT0bRgsJ1AbK+N+AcM1wWXrqBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T15:49:50.140080Z","bundle_sha256":"b68dcc3fe92a5bae1bc766575c976ec97a187ac8cc224472509b254092b401b2"}}