{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7WGCDAJUXRY6ORLHHTACDRV4LG","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":"d4e32f266f4674de5348109866578758852ade635ad9f5e09b405d2d5088f9d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-28T17:38:29Z","title_canon_sha256":"2aabdd0a125d37d4a29039481b4b2f82708e48ffd000954623cc342ee08d1737"},"schema_version":"1.0","source":{"id":"2507.21017","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.21017","created_at":"2026-07-05T11:44:29Z"},{"alias_kind":"arxiv_version","alias_value":"2507.21017v1","created_at":"2026-07-05T11:44:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21017","created_at":"2026-07-05T11:44:29Z"},{"alias_kind":"pith_short_12","alias_value":"7WGCDAJUXRY6","created_at":"2026-07-05T11:44:29Z"},{"alias_kind":"pith_short_16","alias_value":"7WGCDAJUXRY6ORLH","created_at":"2026-07-05T11:44:29Z"},{"alias_kind":"pith_short_8","alias_value":"7WGCDAJU","created_at":"2026-07-05T11:44:29Z"}],"graph_snapshots":[{"event_id":"sha256:adf69cfeca751835e3e0c1a2a3eca0f42a8dcf63da7bdd9efc89b4001472da4e","target":"graph","created_at":"2026-07-05T11:44:29Z","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/2507.21017/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hallucinations pose critical risks for large language model (LLM)-based agents, often manifesting as hallucinative actions resulting from fabricated or misinterpreted information within the cognitive context. While recent studies have exposed such failures, existing evaluations remain fragmented and lack a principled testbed. In this paper, we present MIRAGE-Bench--Measuring Illusions in Risky AGEnt settings--the first unified benchmark for eliciting and evaluating hallucinations in interactive LLM-agent scenarios. We begin by introducing a three-part taxonomy to address agentic hallucinations","authors_text":"Dawn Song, Heyue Lin, Jiayue Pu, Pohao Huang, Weichen Zhang, Yiyou Sun","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-28T17:38:29Z","title":"MIRAGE-Bench: LLM Agent is Hallucinating and Where to Find Them"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21017","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":"sha256:45c480dd948392dcc7e18f284b2f43c36504ed276b4f0c55c3afda6721ecb145","target":"record","created_at":"2026-07-05T11:44:29Z","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":"d4e32f266f4674de5348109866578758852ade635ad9f5e09b405d2d5088f9d4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-07-28T17:38:29Z","title_canon_sha256":"2aabdd0a125d37d4a29039481b4b2f82708e48ffd000954623cc342ee08d1737"},"schema_version":"1.0","source":{"id":"2507.21017","kind":"arxiv","version":1}},"canonical_sha256":"fd8c218134bc71e745673cc021c6bc59b320566530c0ee45b335eab65d3b62aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fd8c218134bc71e745673cc021c6bc59b320566530c0ee45b335eab65d3b62aa","first_computed_at":"2026-07-05T11:44:29.884685Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:29.884685Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9UYBYX0slVJJj5xSriYjyZJWZHgvWbgLxXwtxRLe66d4WZ7XSugP+io5M8OAtNv/x8jdNZwqhroB/3hpPbC9DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:29.885172Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.21017","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:45c480dd948392dcc7e18f284b2f43c36504ed276b4f0c55c3afda6721ecb145","sha256:adf69cfeca751835e3e0c1a2a3eca0f42a8dcf63da7bdd9efc89b4001472da4e"],"state_sha256":"7639ba25c728a381ec012344dd49c32d33d4a75bd7810f3cfb4a67e7670231d2"}