{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JSALUNU6ZPQLUVOBOVMFV5VSJC","short_pith_number":"pith:JSALUNU6","schema_version":"1.0","canonical_sha256":"4c80ba369ecbe0ba55c175585af6b24886744c78575c1b5257dfda7d36f640a9","source":{"kind":"arxiv","id":"2605.18045","version":1},"attestation_state":"computed","paper":{"title":"Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Daniel Haeufle, Jhon P.F. Charaja, Johannes A. Gaus","submitted_at":"2026-05-18T08:35:27Z","abstract_excerpt":"Robotic systems often use predictive uncertainty to decide whether to act autonomously or defer to a fallback policy. In threshold-gated autonomy, uncertainty matters mainly through its ability to rank likely errors. Standard metrics such as expected calibration error and AUROC do not directly test whether uncertainty changes act/defer decisions. We therefore evaluate uncertainty using Spearman rank correlation, paired bootstrap equivalence testing, and act/defer agreement. Across three temporal activity-recognition benchmarks, we find a dataset-dependent competence regime below which uncertai"},"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":"2605.18045","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-05-18T08:35:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13f6f270a4d2454a47fa1188db59bc9d22c5dd0d8b10cee860f70b097967ad47","abstract_canon_sha256":"62d4fce1b6b06b4eaff6511a19917ab1e94cd0923e4c81a25a2f1108dbaf05bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:12.989201Z","signature_b64":"DyuM2rWL1aRtgSIuUYB5UygqNh/5GT0CNFQPRnbLMNxtftGSadlIyx7e4bcbCgmPZ0cbBShzYW/xE3VChQayCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c80ba369ecbe0ba55c175585af6b24886744c78575c1b5257dfda7d36f640a9","last_reissued_at":"2026-05-20T00:05:12.988375Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:12.988375Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Confidence-Gated Robot Autonomy: When Does Uncertainty Actually Help?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Daniel Haeufle, Jhon P.F. Charaja, Johannes A. Gaus","submitted_at":"2026-05-18T08:35:27Z","abstract_excerpt":"Robotic systems often use predictive uncertainty to decide whether to act autonomously or defer to a fallback policy. In threshold-gated autonomy, uncertainty matters mainly through its ability to rank likely errors. Standard metrics such as expected calibration error and AUROC do not directly test whether uncertainty changes act/defer decisions. We therefore evaluate uncertainty using Spearman rank correlation, paired bootstrap equivalence testing, and act/defer agreement. Across three temporal activity-recognition benchmarks, we find a dataset-dependent competence regime below which uncertai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18045","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/2605.18045/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T23:41:59.299065Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:35.492039Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"79975badb83dcf8307a15a8b23d063228c6a6e922c163bb140dc51571f7fba8e"},"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":"2605.18045","created_at":"2026-05-20T00:05:12.988517+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18045v1","created_at":"2026-05-20T00:05:12.988517+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18045","created_at":"2026-05-20T00:05:12.988517+00:00"},{"alias_kind":"pith_short_12","alias_value":"JSALUNU6ZPQL","created_at":"2026-05-20T00:05:12.988517+00:00"},{"alias_kind":"pith_short_16","alias_value":"JSALUNU6ZPQLUVOB","created_at":"2026-05-20T00:05:12.988517+00:00"},{"alias_kind":"pith_short_8","alias_value":"JSALUNU6","created_at":"2026-05-20T00:05:12.988517+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/JSALUNU6ZPQLUVOBOVMFV5VSJC","json":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC.json","graph_json":"https://pith.science/api/pith-number/JSALUNU6ZPQLUVOBOVMFV5VSJC/graph.json","events_json":"https://pith.science/api/pith-number/JSALUNU6ZPQLUVOBOVMFV5VSJC/events.json","paper":"https://pith.science/paper/JSALUNU6"},"agent_actions":{"view_html":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC","download_json":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC.json","view_paper":"https://pith.science/paper/JSALUNU6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18045&json=true","fetch_graph":"https://pith.science/api/pith-number/JSALUNU6ZPQLUVOBOVMFV5VSJC/graph.json","fetch_events":"https://pith.science/api/pith-number/JSALUNU6ZPQLUVOBOVMFV5VSJC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC/action/storage_attestation","attest_author":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC/action/author_attestation","sign_citation":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC/action/citation_signature","submit_replication":"https://pith.science/pith/JSALUNU6ZPQLUVOBOVMFV5VSJC/action/replication_record"}},"created_at":"2026-05-20T00:05:12.988517+00:00","updated_at":"2026-05-20T00:05:12.988517+00:00"}