{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:EHFOLWZXEVFB3JC2RPFG4V3FN2","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":"2ed1d3b80fab83d8e5513e2d127f5b120d0c918a775e1614397f89a6141139f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T07:36:22Z","title_canon_sha256":"df88e892ec8f4b2fba91b3fd3a0dac0f374d749afe5fba068d5706e93bed09fa"},"schema_version":"1.0","source":{"id":"2503.00771","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.00771","created_at":"2026-07-05T10:48:26Z"},{"alias_kind":"arxiv_version","alias_value":"2503.00771v2","created_at":"2026-07-05T10:48:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.00771","created_at":"2026-07-05T10:48:26Z"},{"alias_kind":"pith_short_12","alias_value":"EHFOLWZXEVFB","created_at":"2026-07-05T10:48:26Z"},{"alias_kind":"pith_short_16","alias_value":"EHFOLWZXEVFB3JC2","created_at":"2026-07-05T10:48:26Z"},{"alias_kind":"pith_short_8","alias_value":"EHFOLWZX","created_at":"2026-07-05T10:48:26Z"}],"graph_snapshots":[{"event_id":"sha256:53843929141628922bb29a47968b6e43cd6e2c769e2fc6147d2dabf481413f96","target":"graph","created_at":"2026-07-05T10:48:26Z","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/2503.00771/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. However, most of the current benchmarks primarily focus on either personalization of text generation or direct tool-utilizing, without considering both. In this work, we introduce a novel benchmark ETAPP for evaluating personalized tool invocation, establishing a sandbox environment, and a comprehensive dataset of 800 testing cases covering diverse user profiles. To improve the accuracy of our evaluation, we propose a key-point-based LLM evaluat","authors_text":"Huanxuan Liao, Jun Zhao, Kang Liu, Pengfei Cao, Yubo Chen, Yupu Hao, Zhuoran Jin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T07:36:22Z","title":"Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.00771","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":"sha256:1b923446c25cba4469d3392606d84f9452e222044770b2f806bd948638821b37","target":"record","created_at":"2026-07-05T10:48:26Z","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":"2ed1d3b80fab83d8e5513e2d127f5b120d0c918a775e1614397f89a6141139f8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-02T07:36:22Z","title_canon_sha256":"df88e892ec8f4b2fba91b3fd3a0dac0f374d749afe5fba068d5706e93bed09fa"},"schema_version":"1.0","source":{"id":"2503.00771","kind":"arxiv","version":2}},"canonical_sha256":"21cae5db37254a1da45a8bca6e57656eac99446fa39a45c4e19e1f9a3112af8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"21cae5db37254a1da45a8bca6e57656eac99446fa39a45c4e19e1f9a3112af8d","first_computed_at":"2026-07-05T10:48:26.096194Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:26.096194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XzdBAuDDEA7nV5Ruppx+V8zvRueWRpQdukhOOOkbacMjoL77wy5pcGWyw3YXhm68q0J5/eeNlNFqAkNFHs18Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:26.096741Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.00771","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b923446c25cba4469d3392606d84f9452e222044770b2f806bd948638821b37","sha256:53843929141628922bb29a47968b6e43cd6e2c769e2fc6147d2dabf481413f96"],"state_sha256":"d89cb8aa2c9f0469ba5be54cf508b166bafe5e35cdf2525a7d77ac91a924cd74"}