{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3RRJFQM52XKI4SY6VE5L3W4ICY","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":"446f5b670344a5712a2db2da04e88839ca3d9f2835501c0210bbeae5a738a857","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T06:37:29Z","title_canon_sha256":"33be3040037d03b6d04076c707452e1eea9021785082c23e8850ec6314fef8fe"},"schema_version":"1.0","source":{"id":"2504.18114","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18114","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18114v2","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18114","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"pith_short_12","alias_value":"3RRJFQM52XKI","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"pith_short_16","alias_value":"3RRJFQM52XKI4SY6","created_at":"2026-06-23T02:13:15Z"},{"alias_kind":"pith_short_8","alias_value":"3RRJFQM5","created_at":"2026-06-23T02:13:15Z"}],"graph_snapshots":[{"event_id":"sha256:8d5eac8d52417d6388d5d9326fdf7336f916ae94f4238a2c47b37077ce220e24","target":"graph","created_at":"2026-06-23T02:13:15Z","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/2504.18114/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucinations pose a significant obstacle to the reliability and widespread adoption of language models, yet their accurate measurement remains a persistent challenge. While many task- and domain-specific metrics have been proposed to assess faithfulness and factuality concerns, the robustness and generalization of these metrics are still untested. In this paper, we conduct a large-scale empirical evaluation of 6 diverse sets of hallucination detection metrics across 4 datasets, 37 language models from 5 families, and 5 decoding methods. Our extensive investigation reveals concerning gaps in ","authors_text":"Atharva Kulkarni, Bo-Hsiang Tseng, Dhivya Piraviperumal, Hong Yu, Joel Ruben Antony Moniz, Swabha Swayamdipta, Xiou Ge, Yuan Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T06:37:29Z","title":"Evaluating Evaluation Metrics -- The Mirage of Hallucination Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18114","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":"sha256:5321849f2c789efb1bff72b2409c05bcc9737379920d401e505e401ed757ea78","target":"record","created_at":"2026-06-23T02:13:15Z","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":"446f5b670344a5712a2db2da04e88839ca3d9f2835501c0210bbeae5a738a857","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T06:37:29Z","title_canon_sha256":"33be3040037d03b6d04076c707452e1eea9021785082c23e8850ec6314fef8fe"},"schema_version":"1.0","source":{"id":"2504.18114","kind":"arxiv","version":2}},"canonical_sha256":"dc6292c19dd5d48e4b1ea93abddb88162d794773b7160a2686af5d0906ecc603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dc6292c19dd5d48e4b1ea93abddb88162d794773b7160a2686af5d0906ecc603","first_computed_at":"2026-06-23T02:13:15.174219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:15.174219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b6GWlR9GBAgx7VVYRlmsR1nnX3tfwPRW+fFTU/alYDzIp2L58e2jCEjMy1DouYmrohOK1Fxl7SkKDGxTtBOxDQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:15.174692Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18114","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5321849f2c789efb1bff72b2409c05bcc9737379920d401e505e401ed757ea78","sha256:8d5eac8d52417d6388d5d9326fdf7336f916ae94f4238a2c47b37077ce220e24"],"state_sha256":"6008aefdfc69ed2ce8752ca7fc2530cf4bd65c778d07eadc11578221e1dba677"}