{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:SWTY73GO4TBIDCMKG53ZMVAH55","short_pith_number":"pith:SWTY73GO","schema_version":"1.0","canonical_sha256":"95a78feccee4c281898a3777965407ef6d1c2b316e1608241a265c14a552fb7b","source":{"kind":"arxiv","id":"2506.15850","version":2},"attestation_state":"computed","paper":{"title":"Uncertainty Estimation by Human Perception versus Neural Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Garlan, Paolo Romano, Pedro Mendes","submitted_at":"2025-06-18T20:00:20Z","abstract_excerpt":"Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses serious challenges in applications where reliable uncertainty estimates are critical. In this work, we investigate how human perceptual uncertainty compares to uncertainty estimated by NNs. Using three vision benchmarks annotated with both human disagreement and crowdsourced confidence, we assess the correlation between model-predicted uncertainty and human-perceived uncertainty. Our results show that current methods only "},"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":"2506.15850","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-18T20:00:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9440eab4f712db1a6379fcf0e14b5487892db67424eec044ec96fada97dbab42","abstract_canon_sha256":"f5a81aa352ec6d93252ebae18144a5fd1c90364d0eefc7d833903ab4bca7b34f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:08:37.447880Z","signature_b64":"kyKnHJ1+hw1SvSDDmdLn9jy36wYGk/j+5z1qMESujGnUKSHO1VLlnap7HZ6A5zcNIcQf7n9z2IgXb6y9f/AMAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95a78feccee4c281898a3777965407ef6d1c2b316e1608241a265c14a552fb7b","last_reissued_at":"2026-07-05T12:08:37.447382Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:08:37.447382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Estimation by Human Perception versus Neural Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"David Garlan, Paolo Romano, Pedro Mendes","submitted_at":"2025-06-18T20:00:20Z","abstract_excerpt":"Modern neural networks (NNs) often achieve high predictive accuracy but are poorly calibrated, producing overconfident predictions even when wrong. This miscalibration poses serious challenges in applications where reliable uncertainty estimates are critical. In this work, we investigate how human perceptual uncertainty compares to uncertainty estimated by NNs. Using three vision benchmarks annotated with both human disagreement and crowdsourced confidence, we assess the correlation between model-predicted uncertainty and human-perceived uncertainty. Our results show that current methods only "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15850","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/2506.15850/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":"2506.15850","created_at":"2026-07-05T12:08:37.447447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.15850v2","created_at":"2026-07-05T12:08:37.447447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15850","created_at":"2026-07-05T12:08:37.447447+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWTY73GO4TBI","created_at":"2026-07-05T12:08:37.447447+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWTY73GO4TBIDCMK","created_at":"2026-07-05T12:08:37.447447+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWTY73GO","created_at":"2026-07-05T12:08:37.447447+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/SWTY73GO4TBIDCMKG53ZMVAH55","json":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55.json","graph_json":"https://pith.science/api/pith-number/SWTY73GO4TBIDCMKG53ZMVAH55/graph.json","events_json":"https://pith.science/api/pith-number/SWTY73GO4TBIDCMKG53ZMVAH55/events.json","paper":"https://pith.science/paper/SWTY73GO"},"agent_actions":{"view_html":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55","download_json":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55.json","view_paper":"https://pith.science/paper/SWTY73GO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.15850&json=true","fetch_graph":"https://pith.science/api/pith-number/SWTY73GO4TBIDCMKG53ZMVAH55/graph.json","fetch_events":"https://pith.science/api/pith-number/SWTY73GO4TBIDCMKG53ZMVAH55/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55/action/storage_attestation","attest_author":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55/action/author_attestation","sign_citation":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55/action/citation_signature","submit_replication":"https://pith.science/pith/SWTY73GO4TBIDCMKG53ZMVAH55/action/replication_record"}},"created_at":"2026-07-05T12:08:37.447447+00:00","updated_at":"2026-07-05T12:08:37.447447+00:00"}