{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UTOCIAGET3SLAXZL4OKQEA5UGG","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":"fa27cd93cc719943bbf082bfca871b7ef5a2132750cf368c4f41c9ddf7f6ee8b","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T21:00:46Z","title_canon_sha256":"4e7b1db35196428c8a70a39a51809222959c9e38c933711e7a55947df17966a9"},"schema_version":"1.0","source":{"id":"2608.11434","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.11434","created_at":"2026-08-13T00:21:50Z"},{"alias_kind":"arxiv_version","alias_value":"2608.11434v1","created_at":"2026-08-13T00:21:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.11434","created_at":"2026-08-13T00:21:50Z"},{"alias_kind":"pith_short_12","alias_value":"UTOCIAGET3SL","created_at":"2026-08-13T00:21:50Z"},{"alias_kind":"pith_short_16","alias_value":"UTOCIAGET3SLAXZL","created_at":"2026-08-13T00:21:50Z"},{"alias_kind":"pith_short_8","alias_value":"UTOCIAGE","created_at":"2026-08-13T00:21:50Z"}],"graph_snapshots":[{"event_id":"sha256:ca66cd107ab40a4bac8262171424854609af9dbabf46c73cd5f4ee9d1d491014","target":"graph","created_at":"2026-08-13T00:21:50Z","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/2608.11434/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mobile agent benchmarks increasingly rely on LLM-based judges to evaluate task completion, yet the reliability of these judges on mobile agent trajectories remains largely unexamined. We introduce MobileJudgeBench, a benchmark for systematically evaluating LLM-as-judge methods on mobile agent trajectories. Our benchmark comprises 931 human-annotated trajectories spanning 6 mobile agent benchmarks, 4 agent models, and 68 apps. We evaluate 6 judge methods (five adapted from SPA-Bench, A3 with two modes, AndroidArena, and AgentRewardBench, plus a simple baseline we design) across multiple LLM bac","authors_text":"Li Gu, Seyed Mehdi Ayyoubzadeh, Yang Wang, Yuanhao Yu, Zhi Liu, Zhixiang Chi, Ziqiang Wan","cross_cats":["cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T21:00:46Z","title":"Benchmarking LLM Judges for Mobile Agent Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.11434","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":"sha256:23e9bba891bb8706102ed6729be056336acc5757cbb53a1178502cd0d42b155c","target":"record","created_at":"2026-08-13T00:21:50Z","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":"fa27cd93cc719943bbf082bfca871b7ef5a2132750cf368c4f41c9ddf7f6ee8b","cross_cats_sorted":["cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-11T21:00:46Z","title_canon_sha256":"4e7b1db35196428c8a70a39a51809222959c9e38c933711e7a55947df17966a9"},"schema_version":"1.0","source":{"id":"2608.11434","kind":"arxiv","version":1}},"canonical_sha256":"a4dc2400c49ee4b05f2be3950203b43187abd0ed799090a5b956a36185b0ea9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4dc2400c49ee4b05f2be3950203b43187abd0ed799090a5b956a36185b0ea9d","first_computed_at":"2026-08-13T00:21:50.949351Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T00:21:50.949351Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I7eSqDrmqJf/M07dmO9LAWMVAl/x7vffVK1cvSOz+eJRv58H8tYQCbZrg2QSxh16qg4RHoASsbb/tcxAsvTEBg==","signature_status":"signed_v1","signed_at":"2026-08-13T00:21:50.950766Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.11434","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:23e9bba891bb8706102ed6729be056336acc5757cbb53a1178502cd0d42b155c","sha256:ca66cd107ab40a4bac8262171424854609af9dbabf46c73cd5f4ee9d1d491014"],"state_sha256":"4992cff50cc9cf8a370cf48f2b56e1e7a0b6f2820dc02e138010c771a1f421e5"}