{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TTQM4VDIB4HXBHBWSAKMX5EJME","short_pith_number":"pith:TTQM4VDI","schema_version":"1.0","canonical_sha256":"9ce0ce54680f0f709c369014cbf4896133da3c8e0e5f16a00ce5aab3222e465d","source":{"kind":"arxiv","id":"2608.12100","version":1},"attestation_state":"computed","paper":{"title":"Confidence Calibration of Deep Learning Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Coby Penso","submitted_at":"2026-08-12T14:23:14Z","abstract_excerpt":"In high-stakes applications, reliable confidence estimates are as important as the predictions themselves. Confidence calibration ensures that predicted probabilities reflect the likelihood of correctness, making it essential for safe deployment of deep learning models. However, existing methods typically assume access to clean validation data, which is often unrealistic due to label noise and domain shifts. This thesis develops methods for improving calibration under these conditions.\n  First, we address calibration under label noise. Standard methods can produce misleading confidence estimat"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2608.12100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T14:23:14Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"417151639790014b8d8a69766f041458110e99970704e5bc870a725369b016e7","abstract_canon_sha256":"778a4bcc464b0471aa048082bb7e2626dc086dc5845ac4eb275f86c15ddde9f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:29:58.671047Z","signature_b64":"iwLQe2Zo4T/U4ubj+tlkzbDzdWQNHfSDfoq16zGGMFJUh9ccMbvqu+wFjmlGJNrXAHHJuTJZdkSNJ0czvQYPCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ce0ce54680f0f709c369014cbf4896133da3c8e0e5f16a00ce5aab3222e465d","last_reissued_at":"2026-08-13T01:29:58.668583Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:29:58.668583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence Calibration of Deep Learning Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Coby Penso","submitted_at":"2026-08-12T14:23:14Z","abstract_excerpt":"In high-stakes applications, reliable confidence estimates are as important as the predictions themselves. Confidence calibration ensures that predicted probabilities reflect the likelihood of correctness, making it essential for safe deployment of deep learning models. However, existing methods typically assume access to clean validation data, which is often unrealistic due to label noise and domain shifts. This thesis develops methods for improving calibration under these conditions.\n  First, we address calibration under label noise. Standard methods can produce misleading confidence estimat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12100","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/2608.12100/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2608.12100","created_at":"2026-08-13T01:29:58.669766+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.12100v1","created_at":"2026-08-13T01:29:58.669766+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12100","created_at":"2026-08-13T01:29:58.669766+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTQM4VDIB4HX","created_at":"2026-08-13T01:29:58.669766+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTQM4VDIB4HXBHBW","created_at":"2026-08-13T01:29:58.669766+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTQM4VDI","created_at":"2026-08-13T01:29:58.669766+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME","json":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME.json","graph_json":"https://pith.science/api/pith-number/TTQM4VDIB4HXBHBWSAKMX5EJME/graph.json","events_json":"https://pith.science/api/pith-number/TTQM4VDIB4HXBHBWSAKMX5EJME/events.json","paper":"https://pith.science/paper/TTQM4VDI"},"agent_actions":{"view_html":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME","download_json":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME.json","view_paper":"https://pith.science/paper/TTQM4VDI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.12100&json=true","fetch_graph":"https://pith.science/api/pith-number/TTQM4VDIB4HXBHBWSAKMX5EJME/graph.json","fetch_events":"https://pith.science/api/pith-number/TTQM4VDIB4HXBHBWSAKMX5EJME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME/action/storage_attestation","attest_author":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME/action/author_attestation","sign_citation":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME/action/citation_signature","submit_replication":"https://pith.science/pith/TTQM4VDIB4HXBHBWSAKMX5EJME/action/replication_record"}},"created_at":"2026-08-13T01:29:58.669766+00:00","updated_at":"2026-08-13T01:29:58.669766+00:00"}