{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:C75EE2KNLTYFT73TQOGGKYBXRE","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":"bf2362e25ed905446b6a7659fe37e2835e1e9f38a823d434c4ad55a707b728e6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T16:16:07Z","title_canon_sha256":"da64ed5335d75028b4432a1da0627604d14cdab70f6d6dda27ea5a86d147d3b5"},"schema_version":"1.0","source":{"id":"2506.09902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.09902","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.09902v1","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09902","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_12","alias_value":"C75EE2KNLTYF","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_16","alias_value":"C75EE2KNLTYFT73T","created_at":"2026-07-05T11:19:58Z"},{"alias_kind":"pith_short_8","alias_value":"C75EE2KN","created_at":"2026-07-05T11:19:58Z"}],"graph_snapshots":[{"event_id":"sha256:5ff91c84a898fad732e3d9a03618f35ae91d9e55ad8500971558af2e5612dad5","target":"graph","created_at":"2026-07-05T11:19:58Z","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/2506.09902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have advanced conversational AI assistants. However, systematically evaluating how well these assistants apply personalization--adapting to individual user preferences while completing tasks--remains challenging. Existing personalization benchmarks focus on chit-chat, non-conversational tasks, or narrow domains, failing to capture the complexities of personalized task-oriented assistance. To address this, we introduce PersonaLens, a comprehensive benchmark for evaluating personalization in task-oriented AI assistants. Our benchmark features diverse user profiles eq","authors_text":"Clara Vania, Emine Yilmaz, Naila Khan, Shay B. Cohen, Subhradeep Kayal, Zheng Zhao","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T16:16:07Z","title":"PersonaLens: A Benchmark for Personalization Evaluation in Conversational AI Assistants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09902","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":"sha256:5e740c4f692fda5eda96bef9f009557eaf9897f6fdcd802e7a3b9dc3f6082171","target":"record","created_at":"2026-07-05T11:19:58Z","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":"bf2362e25ed905446b6a7659fe37e2835e1e9f38a823d434c4ad55a707b728e6","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T16:16:07Z","title_canon_sha256":"da64ed5335d75028b4432a1da0627604d14cdab70f6d6dda27ea5a86d147d3b5"},"schema_version":"1.0","source":{"id":"2506.09902","kind":"arxiv","version":1}},"canonical_sha256":"17fa42694d5cf059ff73838c656037890b4cbbdffcc6d0dd741a0b59b820fae6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"17fa42694d5cf059ff73838c656037890b4cbbdffcc6d0dd741a0b59b820fae6","first_computed_at":"2026-07-05T11:19:58.547561Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:19:58.547561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7tCUpnB2PUgLJjjwvrBQ6iiS8DRgQLPr1gkyLiCZ4uthf2wq8B+JXPY5vzfalT8OghTeQd5LymU8vWjvXC3wDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:19:58.548045Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.09902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e740c4f692fda5eda96bef9f009557eaf9897f6fdcd802e7a3b9dc3f6082171","sha256:5ff91c84a898fad732e3d9a03618f35ae91d9e55ad8500971558af2e5612dad5"],"state_sha256":"1266806928c2a5137c111657b3901683be827251c5a4bd03b019b37493678ff1"}