{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:PFLLA7XHVRVP6QSMLN3NKGJD4A","short_pith_number":"pith:PFLLA7XH","schema_version":"1.0","canonical_sha256":"7956b07ee7ac6aff424c5b76d51923e01706d24c0cfd7862905ae607e7729453","source":{"kind":"arxiv","id":"2006.12807","version":2},"attestation_state":"computed","paper":{"title":"Post-hoc Calibration of Neural Networks by g-Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Rahimi, Cristian Sminchisescu, Kartik Gupta, Richard Hartley, Thalaiyasingam Ajanthan, Thomas Mensink","submitted_at":"2020-06-23T07:55:10Z","abstract_excerpt":"Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions are equally important as the decisions themselves. In recent years, there is a surge of research on neural network calibration and the majority of the works can be categorized into post-hoc calibration methods, defined as methods that learn an additional function to calibrate an already trained base network. In this work, we intend to understand the post-hoc calibration methods from a theoretical point of view. Especi"},"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":"2006.12807","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-23T07:55:10Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"10ed6c7653fc9dd2edc2486e7560242bab48fd732823d983bdab81857afaf0b3","abstract_canon_sha256":"1f020873bbc8b67c86f9f00405ca53a11b51d43a2f4a8ae482b91ab796868afd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:58:32.437054Z","signature_b64":"dNkLQjTllQNqhud7+pPMbihCDiqr6Ojhc1qa68wnpIXaWowmx5t7E//h+gQ+T8Qtu0A3F5Et6Xw9/og3sWBoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7956b07ee7ac6aff424c5b76d51923e01706d24c0cfd7862905ae607e7729453","last_reissued_at":"2026-07-05T03:58:32.436576Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:58:32.436576Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Post-hoc Calibration of Neural Networks by g-Layers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Amir Rahimi, Cristian Sminchisescu, Kartik Gupta, Richard Hartley, Thalaiyasingam Ajanthan, Thomas Mensink","submitted_at":"2020-06-23T07:55:10Z","abstract_excerpt":"Calibration of neural networks is a critical aspect to consider when incorporating machine learning models in real-world decision-making systems where the confidence of decisions are equally important as the decisions themselves. In recent years, there is a surge of research on neural network calibration and the majority of the works can be categorized into post-hoc calibration methods, defined as methods that learn an additional function to calibrate an already trained base network. In this work, we intend to understand the post-hoc calibration methods from a theoretical point of view. Especi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.12807","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/2006.12807/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":"2006.12807","created_at":"2026-07-05T03:58:32.436635+00:00"},{"alias_kind":"arxiv_version","alias_value":"2006.12807v2","created_at":"2026-07-05T03:58:32.436635+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.12807","created_at":"2026-07-05T03:58:32.436635+00:00"},{"alias_kind":"pith_short_12","alias_value":"PFLLA7XHVRVP","created_at":"2026-07-05T03:58:32.436635+00:00"},{"alias_kind":"pith_short_16","alias_value":"PFLLA7XHVRVP6QSM","created_at":"2026-07-05T03:58:32.436635+00:00"},{"alias_kind":"pith_short_8","alias_value":"PFLLA7XH","created_at":"2026-07-05T03:58:32.436635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.06516","citing_title":"Instance-Wise Monotonic Calibration by Constrained Transformation","ref_index":2022,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A","json":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A.json","graph_json":"https://pith.science/api/pith-number/PFLLA7XHVRVP6QSMLN3NKGJD4A/graph.json","events_json":"https://pith.science/api/pith-number/PFLLA7XHVRVP6QSMLN3NKGJD4A/events.json","paper":"https://pith.science/paper/PFLLA7XH"},"agent_actions":{"view_html":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A","download_json":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A.json","view_paper":"https://pith.science/paper/PFLLA7XH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2006.12807&json=true","fetch_graph":"https://pith.science/api/pith-number/PFLLA7XHVRVP6QSMLN3NKGJD4A/graph.json","fetch_events":"https://pith.science/api/pith-number/PFLLA7XHVRVP6QSMLN3NKGJD4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A/action/storage_attestation","attest_author":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A/action/author_attestation","sign_citation":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A/action/citation_signature","submit_replication":"https://pith.science/pith/PFLLA7XHVRVP6QSMLN3NKGJD4A/action/replication_record"}},"created_at":"2026-07-05T03:58:32.436635+00:00","updated_at":"2026-07-05T03:58:32.436635+00:00"}