{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6P5ERI27Y7OGORTWVPPGQOHWOA","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":"77c09e00b54726b06cad25ace5f62a175859499f45dd23729a4575ba25ea9bac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T14:58:35Z","title_canon_sha256":"7ca61ce66b910231de29ce0aeb411065452effff17121b498e48fb73905b1dd7"},"schema_version":"1.0","source":{"id":"2501.11067","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11067","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11067v1","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11067","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_12","alias_value":"6P5ERI27Y7OG","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_16","alias_value":"6P5ERI27Y7OGORTW","created_at":"2026-07-05T10:03:02Z"},{"alias_kind":"pith_short_8","alias_value":"6P5ERI27","created_at":"2026-07-05T10:03:02Z"}],"graph_snapshots":[{"event_id":"sha256:f5a061f9767d4be468ba3f35314f40e22d286c47bd14117422ce523c19f8c936","target":"graph","created_at":"2026-07-05T10:03:02Z","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/2501.11067/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) are transforming artificial intelligence, evolving into task-oriented systems capable of autonomous planning and execution. One of the primary applications of LLMs is conversational AI systems, which must navigate multi-turn dialogues, integrate domain-specific APIs, and adhere to strict policy constraints. However, evaluating these agents remains a significant challenge, as traditional methods fail to capture the complexity and variability of real-world interactions. We introduce IntellAgent, a scalable, open-source multi-agent framework designed to evaluate conve","authors_text":"Elad Levi, Ilan Kadar","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T14:58:35Z","title":"IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11067","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":"sha256:168d235e1429787ccffbdbf76fab7ec54bae717c47f4766eab3ec6ef43166133","target":"record","created_at":"2026-07-05T10:03:02Z","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":"77c09e00b54726b06cad25ace5f62a175859499f45dd23729a4575ba25ea9bac","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T14:58:35Z","title_canon_sha256":"7ca61ce66b910231de29ce0aeb411065452effff17121b498e48fb73905b1dd7"},"schema_version":"1.0","source":{"id":"2501.11067","kind":"arxiv","version":1}},"canonical_sha256":"f3fa48a35fc7dc674676abde6838f67005370723255dd0b47839f800d418f5ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f3fa48a35fc7dc674676abde6838f67005370723255dd0b47839f800d418f5ed","first_computed_at":"2026-07-05T10:03:02.855929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:03:02.855929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zRBhFgn9gc8h5oDAJVq54hKGGmA56Uk6gHmyfrxATr0mno6T5i9PvDZYhoR5vagN+l8+8ZC6ki0OJloGGX7OBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:03:02.856359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11067","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:168d235e1429787ccffbdbf76fab7ec54bae717c47f4766eab3ec6ef43166133","sha256:f5a061f9767d4be468ba3f35314f40e22d286c47bd14117422ce523c19f8c936"],"state_sha256":"b2f26cdf179dc6abb234721a49630187a5cf23da5949367843f06ad76c74dca9"}