{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GOAWQEKR2MUIU55VWBFHVFLNON","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":"6d6803a24072214939fab55d728ad324f8accef7fe70c7206af37d1bb9798793","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-16T08:51:33Z","title_canon_sha256":"f68cc1370a65cee990e9bb2bfba473df584ac301f94182684fa760a2f9e6862a"},"schema_version":"1.0","source":{"id":"2603.14987","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.14987","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"arxiv_version","alias_value":"2603.14987v2","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14987","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"pith_short_12","alias_value":"GOAWQEKR2MUI","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"pith_short_16","alias_value":"GOAWQEKR2MUIU55V","created_at":"2026-05-22T01:04:00Z"},{"alias_kind":"pith_short_8","alias_value":"GOAWQEKR","created_at":"2026-05-22T01:04:00Z"}],"graph_snapshots":[{"event_id":"sha256:9aedf2f2fa7af5eb60483a987e5243fedc2f32d9400f6135f171357427446d8b","target":"graph","created_at":"2026-05-22T01:04:00Z","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/2603.14987/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Irwin King, Jinhu Qi, Minghao Zhao, Wentao Zhang, Yaoman Li, Yifan Li, Zijian Zhang","cross_cats":["cs.DB"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-16T08:51:33Z","title":"Beyond Benchmark Islands: Toward Representative Trustworthiness Evaluation for Agentic AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14987","kind":"arxiv","version":2},"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":"sha256:80050916e74a1f905e1771ac7b2a36062ed6a670fc52e803478a8321e7d56f31","target":"record","created_at":"2026-05-22T01:04:00Z","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":"6d6803a24072214939fab55d728ad324f8accef7fe70c7206af37d1bb9798793","cross_cats_sorted":["cs.DB"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-16T08:51:33Z","title_canon_sha256":"f68cc1370a65cee990e9bb2bfba473df584ac301f94182684fa760a2f9e6862a"},"schema_version":"1.0","source":{"id":"2603.14987","kind":"arxiv","version":2}},"canonical_sha256":"3381681151d3288a77b5b04a7a956d736bd6dff11b339c15d80eda9b8c5850bd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3381681151d3288a77b5b04a7a956d736bd6dff11b339c15d80eda9b8c5850bd","first_computed_at":"2026-05-22T01:04:00.227074Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:04:00.227074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nRhGmfjrWIhCQaZT1UvZJvf4aBILlaZOJkkAFRjB+wMObCUm3fOEOd9FLRRkPdEcPwhEibOec6GXdcMCjSnYAQ==","signature_status":"signed_v1","signed_at":"2026-05-22T01:04:00.227703Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.14987","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80050916e74a1f905e1771ac7b2a36062ed6a670fc52e803478a8321e7d56f31","sha256:9aedf2f2fa7af5eb60483a987e5243fedc2f32d9400f6135f171357427446d8b"],"state_sha256":"329f7af492b60bf10d1e7d20947b4c9b8f6929f4b2baabdd278f1b8f37a1ebcb"}