{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GJYYOQIICH7EBEEI3ZBRLHOC3X","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":"a360345f4845537a201d0c3c05fd899619f6acb2c7f0a4bb4ff86b50fe09623b","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T13:44:26Z","title_canon_sha256":"7024b8f747ae6a4e3c5cb38acc5743d198b6d7235965de00646acf6024f2a9b4"},"schema_version":"1.0","source":{"id":"2608.08709","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08709","created_at":"2026-08-11T01:25:06Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08709v1","created_at":"2026-08-11T01:25:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08709","created_at":"2026-08-11T01:25:06Z"},{"alias_kind":"pith_short_12","alias_value":"GJYYOQIICH7E","created_at":"2026-08-11T01:25:06Z"},{"alias_kind":"pith_short_16","alias_value":"GJYYOQIICH7EBEEI","created_at":"2026-08-11T01:25:06Z"},{"alias_kind":"pith_short_8","alias_value":"GJYYOQII","created_at":"2026-08-11T01:25:06Z"}],"graph_snapshots":[{"event_id":"sha256:f704ebdf7ca452a2f15b930cd3d34809993044f580f69454533fe12a36091b6a","target":"graph","created_at":"2026-08-11T01:25:06Z","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/2608.08709/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The reliability of AI generative models is typically measured by output correctness, yet in practice it depends on the effort required to verify those outputs. We argue that current evaluation metrics overlook a critical failure mode: Verification-Cost Errors (VCEs), defined as incorrect input-output pairs that a declared fraction of the verifier population fails to identify within the verification budget available in a given deployment context. Unlike standard notions of \"hallucination\", VCEs are defined operationally, by the failure of correct identification within budget rather than by any ","authors_text":"Fabio Persia, Generoso Immediato, Stefania Costantini, Viviana Crescitelli","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T13:44:26Z","title":"AI Evaluation Should Measure Verification Cost, Not Correctness Alone"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08709","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:bbd10e1b63aafa3d57d6d63d339998c81d91618714092aaeb694cf3df8883a2c","target":"record","created_at":"2026-08-11T01:25:06Z","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":"a360345f4845537a201d0c3c05fd899619f6acb2c7f0a4bb4ff86b50fe09623b","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T13:44:26Z","title_canon_sha256":"7024b8f747ae6a4e3c5cb38acc5743d198b6d7235965de00646acf6024f2a9b4"},"schema_version":"1.0","source":{"id":"2608.08709","kind":"arxiv","version":1}},"canonical_sha256":"327187410811fe409088de43159dc2dde7a2ec664f635f3dc5d41bd24cf1e7e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"327187410811fe409088de43159dc2dde7a2ec664f635f3dc5d41bd24cf1e7e5","first_computed_at":"2026-08-11T01:25:06.673211Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:25:06.673211Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PhNCeqxzbFIYZHJstPJM0/YaY9D1L0+FPgA/XEWg9+ShYFbSgLHKR8/X0wm/4gdJCmgLJbTUlwKw5w6EOaIkCw==","signature_status":"signed_v1","signed_at":"2026-08-11T01:25:06.675588Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08709","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd10e1b63aafa3d57d6d63d339998c81d91618714092aaeb694cf3df8883a2c","sha256:f704ebdf7ca452a2f15b930cd3d34809993044f580f69454533fe12a36091b6a"],"state_sha256":"a32028b8646a55b4e1bde6e48fe294cd77b48b16db518e7c08bc6b40a11946ff"}