{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LKBGVP72L2DEN2UOOB4XWMKCTE","short_pith_number":"pith:LKBGVP72","schema_version":"1.0","canonical_sha256":"5a826abffa5e8646ea8e70797b3142992e9fa08c80d9d64760ef872e3b9512a5","source":{"kind":"arxiv","id":"2405.00442","version":1},"attestation_state":"computed","paper":{"title":"Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Hiroki Naganuma, Masanari Kimura","submitted_at":"2024-05-01T10:53:54Z","abstract_excerpt":"The key factor in implementing machine learning algorithms in decision-making situations is not only the accuracy of the model but also its confidence level. The confidence level of a model in a classification problem is often given by the output vector of a softmax function for convenience. However, these values are known to deviate significantly from the actual expected model confidence. This problem is called model calibration and has been studied extensively. One of the simplest techniques to tackle this task is focal loss, a generalization of cross-entropy by introducing one positive para"},"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":"2405.00442","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-05-01T10:53:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2f550a1797f6537770d51e33a0f32d69126080c32f463ff4ac2aa3fd4421bb0f","abstract_canon_sha256":"68ec1251260677ebbc1af3f33c7dbcc0f76efe36f374d31c26fb2fd84b275f1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:13.091720Z","signature_b64":"n6pdMp4o4Lk4Uf7xtGtdeeh3fiNl5p/OazbwAWQ8zdkDBZKPbP0hVD9micA235mxWV6NDYniSqxFGmAV0YfXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a826abffa5e8646ea8e70797b3142992e9fa08c80d9d64760ef872e3b9512a5","last_reissued_at":"2026-07-05T08:14:13.091307Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:13.091307Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric Insights into Focal Loss: Reducing Curvature for Enhanced Model Calibration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Hiroki Naganuma, Masanari Kimura","submitted_at":"2024-05-01T10:53:54Z","abstract_excerpt":"The key factor in implementing machine learning algorithms in decision-making situations is not only the accuracy of the model but also its confidence level. The confidence level of a model in a classification problem is often given by the output vector of a softmax function for convenience. However, these values are known to deviate significantly from the actual expected model confidence. This problem is called model calibration and has been studied extensively. One of the simplest techniques to tackle this task is focal loss, a generalization of cross-entropy by introducing one positive para"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00442","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/2405.00442/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":"2405.00442","created_at":"2026-07-05T08:14:13.091369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.00442v1","created_at":"2026-07-05T08:14:13.091369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00442","created_at":"2026-07-05T08:14:13.091369+00:00"},{"alias_kind":"pith_short_12","alias_value":"LKBGVP72L2DE","created_at":"2026-07-05T08:14:13.091369+00:00"},{"alias_kind":"pith_short_16","alias_value":"LKBGVP72L2DEN2UO","created_at":"2026-07-05T08:14:13.091369+00:00"},{"alias_kind":"pith_short_8","alias_value":"LKBGVP72","created_at":"2026-07-05T08:14:13.091369+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/LKBGVP72L2DEN2UOOB4XWMKCTE","json":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE.json","graph_json":"https://pith.science/api/pith-number/LKBGVP72L2DEN2UOOB4XWMKCTE/graph.json","events_json":"https://pith.science/api/pith-number/LKBGVP72L2DEN2UOOB4XWMKCTE/events.json","paper":"https://pith.science/paper/LKBGVP72"},"agent_actions":{"view_html":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE","download_json":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE.json","view_paper":"https://pith.science/paper/LKBGVP72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.00442&json=true","fetch_graph":"https://pith.science/api/pith-number/LKBGVP72L2DEN2UOOB4XWMKCTE/graph.json","fetch_events":"https://pith.science/api/pith-number/LKBGVP72L2DEN2UOOB4XWMKCTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE/action/storage_attestation","attest_author":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE/action/author_attestation","sign_citation":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE/action/citation_signature","submit_replication":"https://pith.science/pith/LKBGVP72L2DEN2UOOB4XWMKCTE/action/replication_record"}},"created_at":"2026-07-05T08:14:13.091369+00:00","updated_at":"2026-07-05T08:14:13.091369+00:00"}