{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GOAWQEKR2MUIU55VWBFHVFLNON","short_pith_number":"pith:GOAWQEKR","schema_version":"1.0","canonical_sha256":"3381681151d3288a77b5b04a7a956d736bd6dff11b339c15d80eda9b8c5850bd","source":{"kind":"arxiv","id":"2603.14987","version":2},"attestation_state":"computed","paper":{"title":"Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Irwin King, Jinhu Qi, Minghao Zhao, Wentao Zhang, Yaoman Li, Yifan Li, Zijian Zhang","submitted_at":"2026-03-16T08:51:33Z","abstract_excerpt":"Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated benchmark slices, and \"trustworthiness\" is frequently invoked but rarely defined operationally.\n  We argue the central limitation is twofold: (i) the absence of a measurable specification of what agent trustworthiness means, and (ii) the lack of a principled notion of representativeness allowing assessment over a socio-technical scenario distribution rather"},"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":"2603.14987","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-16T08:51:33Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"f68cc1370a65cee990e9bb2bfba473df584ac301f94182684fa760a2f9e6862a","abstract_canon_sha256":"6d6803a24072214939fab55d728ad324f8accef7fe70c7206af37d1bb9798793"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:00.227703Z","signature_b64":"nRhGmfjrWIhCQaZT1UvZJvf4aBILlaZOJkkAFRjB+wMObCUm3fOEOd9FLRRkPdEcPwhEibOec6GXdcMCjSnYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3381681151d3288a77b5b04a7a956d736bd6dff11b339c15d80eda9b8c5850bd","last_reissued_at":"2026-05-22T01:04:00.227074Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:00.227074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.CL","authors_text":"Irwin King, Jinhu Qi, Minghao Zhao, Wentao Zhang, Yaoman Li, Yifan Li, Zijian Zhang","submitted_at":"2026-03-16T08:51:33Z","abstract_excerpt":"Agentic AI systems increasingly act through tool-augmented, multi-step workflows whose failures (unsafe tool use, unauthorised actions, social harm) carry deployment-level consequences. Evaluation practice remains fragmented across isolated benchmark slices, and \"trustworthiness\" is frequently invoked but rarely defined operationally.\n  We argue the central limitation is twofold: (i) the absence of a measurable specification of what agent trustworthiness means, and (ii) the lack of a principled notion of representativeness allowing assessment over a socio-technical scenario distribution rather"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14987","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/2603.14987/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":"2603.14987","created_at":"2026-05-22T01:04:00.227164+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14987v2","created_at":"2026-05-22T01:04:00.227164+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14987","created_at":"2026-05-22T01:04:00.227164+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOAWQEKR2MUI","created_at":"2026-05-22T01:04:00.227164+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOAWQEKR2MUIU55V","created_at":"2026-05-22T01:04:00.227164+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOAWQEKR","created_at":"2026-05-22T01:04:00.227164+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/GOAWQEKR2MUIU55VWBFHVFLNON","json":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON.json","graph_json":"https://pith.science/api/pith-number/GOAWQEKR2MUIU55VWBFHVFLNON/graph.json","events_json":"https://pith.science/api/pith-number/GOAWQEKR2MUIU55VWBFHVFLNON/events.json","paper":"https://pith.science/paper/GOAWQEKR"},"agent_actions":{"view_html":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON","download_json":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON.json","view_paper":"https://pith.science/paper/GOAWQEKR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14987&json=true","fetch_graph":"https://pith.science/api/pith-number/GOAWQEKR2MUIU55VWBFHVFLNON/graph.json","fetch_events":"https://pith.science/api/pith-number/GOAWQEKR2MUIU55VWBFHVFLNON/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON/action/storage_attestation","attest_author":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON/action/author_attestation","sign_citation":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON/action/citation_signature","submit_replication":"https://pith.science/pith/GOAWQEKR2MUIU55VWBFHVFLNON/action/replication_record"}},"created_at":"2026-05-22T01:04:00.227164+00:00","updated_at":"2026-05-22T01:04:00.227164+00:00"}