{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2E52HR3JXOGPZRU5NCEE6P744M","short_pith_number":"pith:2E52HR3J","canonical_record":{"source":{"id":"2505.18622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T10:07:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5286c77f138dab32773786a69c4b5f7f4be47fba289b762399ef2977fda45d5b","abstract_canon_sha256":"d34afb040a205838fe20497df07d9ac67a024df19285b18e6db9c100a8c71966"},"schema_version":"1.0"},"canonical_sha256":"d13ba3c769bb8cfcc69d68884f3ffce305bb5010f6760e2abfeda1567786131d","source":{"kind":"arxiv","id":"2505.18622","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18622","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18622v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18622","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"2E52HR3JXOGP","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"2E52HR3JXOGPZRU5","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"2E52HR3J","created_at":"2026-07-05T11:09:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2E52HR3JXOGPZRU5NCEE6P744M","target":"record","payload":{"canonical_record":{"source":{"id":"2505.18622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T10:07:48Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"5286c77f138dab32773786a69c4b5f7f4be47fba289b762399ef2977fda45d5b","abstract_canon_sha256":"d34afb040a205838fe20497df07d9ac67a024df19285b18e6db9c100a8c71966"},"schema_version":"1.0"},"canonical_sha256":"d13ba3c769bb8cfcc69d68884f3ffce305bb5010f6760e2abfeda1567786131d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:16.585811Z","signature_b64":"NOD6yGbo7Ghw7pTSz0XHqlbuNnhXz+D+gYV5idKTDSicl0+b44O4ETY6mWt9byNb1M0xgTvLywY1sgF3rJ4hAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d13ba3c769bb8cfcc69d68884f3ffce305bb5010f6760e2abfeda1567786131d","last_reissued_at":"2026-07-05T11:09:16.585292Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:16.585292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.18622","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":"2026-07-05T11:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f71hEBYP5Wizbz9JDqpeD5+4FcC0etBHeguLyUNH7eb7B8hLiJbu77C0esmDH8srHGTgChIZmfHsO6ANoZFxCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:19:54.572749Z"},"content_sha256":"44751f5cbd5530a087b54ca51cce9a2e3595c1ca340c0e823cb41178b61bc9ef","schema_version":"1.0","event_id":"sha256:44751f5cbd5530a087b54ca51cce9a2e3595c1ca340c0e823cb41178b61bc9ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2E52HR3JXOGPZRU5NCEE6P744M","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Trust, or Don't Predict: Introducing the CWSA Family for Confidence-Aware Model Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Kourosh Shahnazari, Mohammadali Keshtparvar, Pegah Ghaffari, Seyed Moein Ayyoubzadeh","submitted_at":"2025-05-24T10:07:48Z","abstract_excerpt":"In recent machine learning systems, confidence scores are being utilized more and more to manage selective prediction, whereby a model can abstain from making a prediction when it is unconfident. Yet, conventional metrics like accuracy, expected calibration error (ECE), and area under the risk-coverage curve (AURC) do not capture the actual reliability of predictions. These metrics either disregard confidence entirely, dilute valuable localized information through averaging, or neglect to suitably penalize overconfident misclassifications, which can be particularly detrimental in real-world sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18622","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/2505.18622/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":"2026-07-05T11:09:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wJosnxpanIusycdQbRfqCGEWqYWeEMbX35Amc4Udq0hm2SfyVrRWHPhV0tBqXSHqNMJLkou4BE0DVtku1tI6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:19:54.573084Z"},"content_sha256":"14b6656d4c65edc32e63336e351f58fb537fc2a28b564f7523b44d8ef74d2fc4","schema_version":"1.0","event_id":"sha256:14b6656d4c65edc32e63336e351f58fb537fc2a28b564f7523b44d8ef74d2fc4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2E52HR3JXOGPZRU5NCEE6P744M/bundle.json","state_url":"https://pith.science/pith/2E52HR3JXOGPZRU5NCEE6P744M/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2E52HR3JXOGPZRU5NCEE6P744M/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":"2026-08-05T13:19:54Z","links":{"resolver":"https://pith.science/pith/2E52HR3JXOGPZRU5NCEE6P744M","bundle":"https://pith.science/pith/2E52HR3JXOGPZRU5NCEE6P744M/bundle.json","state":"https://pith.science/pith/2E52HR3JXOGPZRU5NCEE6P744M/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2E52HR3JXOGPZRU5NCEE6P744M/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2E52HR3JXOGPZRU5NCEE6P744M","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":"d34afb040a205838fe20497df07d9ac67a024df19285b18e6db9c100a8c71966","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T10:07:48Z","title_canon_sha256":"5286c77f138dab32773786a69c4b5f7f4be47fba289b762399ef2977fda45d5b"},"schema_version":"1.0","source":{"id":"2505.18622","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18622","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18622v1","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18622","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_12","alias_value":"2E52HR3JXOGP","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_16","alias_value":"2E52HR3JXOGPZRU5","created_at":"2026-07-05T11:09:16Z"},{"alias_kind":"pith_short_8","alias_value":"2E52HR3J","created_at":"2026-07-05T11:09:16Z"}],"graph_snapshots":[{"event_id":"sha256:14b6656d4c65edc32e63336e351f58fb537fc2a28b564f7523b44d8ef74d2fc4","target":"graph","created_at":"2026-07-05T11:09:16Z","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/2505.18622/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent machine learning systems, confidence scores are being utilized more and more to manage selective prediction, whereby a model can abstain from making a prediction when it is unconfident. Yet, conventional metrics like accuracy, expected calibration error (ECE), and area under the risk-coverage curve (AURC) do not capture the actual reliability of predictions. These metrics either disregard confidence entirely, dilute valuable localized information through averaging, or neglect to suitably penalize overconfident misclassifications, which can be particularly detrimental in real-world sy","authors_text":"Kourosh Shahnazari, Mohammadali Keshtparvar, Pegah Ghaffari, Seyed Moein Ayyoubzadeh","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T10:07:48Z","title":"Trust, or Don't Predict: Introducing the CWSA Family for Confidence-Aware Model Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18622","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":"sha256:44751f5cbd5530a087b54ca51cce9a2e3595c1ca340c0e823cb41178b61bc9ef","target":"record","created_at":"2026-07-05T11:09:16Z","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":"d34afb040a205838fe20497df07d9ac67a024df19285b18e6db9c100a8c71966","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T10:07:48Z","title_canon_sha256":"5286c77f138dab32773786a69c4b5f7f4be47fba289b762399ef2977fda45d5b"},"schema_version":"1.0","source":{"id":"2505.18622","kind":"arxiv","version":1}},"canonical_sha256":"d13ba3c769bb8cfcc69d68884f3ffce305bb5010f6760e2abfeda1567786131d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d13ba3c769bb8cfcc69d68884f3ffce305bb5010f6760e2abfeda1567786131d","first_computed_at":"2026-07-05T11:09:16.585292Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:16.585292Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NOD6yGbo7Ghw7pTSz0XHqlbuNnhXz+D+gYV5idKTDSicl0+b44O4ETY6mWt9byNb1M0xgTvLywY1sgF3rJ4hAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:16.585811Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18622","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44751f5cbd5530a087b54ca51cce9a2e3595c1ca340c0e823cb41178b61bc9ef","sha256:14b6656d4c65edc32e63336e351f58fb537fc2a28b564f7523b44d8ef74d2fc4"],"state_sha256":"4170866174a89015da48d734f14a837b5a54252657f0b2a2c93e92f35f63eb61"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FEvFDvRbR+WNdGqQsTUNxKf+XDnvF2x6PjsI9uy2GTHgWEB9Q+cqp0BrTCmCGDqt6YDhNfTBJX9vnWu8rbdECw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:19:54.576233Z","bundle_sha256":"241d7751e9b1e6b1eb4f7b9aed771d32ad3a7054ff69ae4fba01d04fedaa733f"}}