{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3SZUNEXQY3R56JMGXZ3DTUB4TX","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":"b88627f3af26f6b5065f809623e270bbdafa55261e473d281bcb2073e8808827","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-25T16:00:45Z","title_canon_sha256":"0b20d28b2f8dd4aac82c1aee51b2a66fbd0ae804a4964be15465ddd3de69aa7c"},"schema_version":"1.0","source":{"id":"2607.23263","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23263","created_at":"2026-07-28T01:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23263v1","created_at":"2026-07-28T01:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23263","created_at":"2026-07-28T01:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"3SZUNEXQY3R5","created_at":"2026-07-28T01:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"3SZUNEXQY3R56JMG","created_at":"2026-07-28T01:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"3SZUNEXQ","created_at":"2026-07-28T01:22:44Z"}],"graph_snapshots":[{"event_id":"sha256:8ef08164535bfcf6a783650df9a1ee2c741a41e76c24061a627c85661bf2d945","target":"graph","created_at":"2026-07-28T01:22:44Z","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/2607.23263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Deciding whether a trajectory actually fulfills its instruction governs how we measure computer-use agents on long-horizon graphical-user-interface tasks and how we train them with reinforcement learning. This judgment has long relied on rule-based evaluation, which struggles to align with human intention and goes stale when an app updates or its online content drifts. Existing model-based judges attempt to address these problems but still leave a performance gap to the rule-based evaluation. We propose the \\textbf{SeekJudge} framework, in which four role-specialized agents, a Condense, a Grou","authors_text":"Jierui Wang, Linchao Zhu, Yang Wan, Zhenhao Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-25T16:00:45Z","title":"SeekJudge: A Practical Reward Framework for Reinforcement Learning in Computer-Use Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23263","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":"sha256:31239e6ce6da7e0d57c1b9900f586682f9ac9b7175ac23ee201caef562eb15e7","target":"record","created_at":"2026-07-28T01:22:44Z","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":"b88627f3af26f6b5065f809623e270bbdafa55261e473d281bcb2073e8808827","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-25T16:00:45Z","title_canon_sha256":"0b20d28b2f8dd4aac82c1aee51b2a66fbd0ae804a4964be15465ddd3de69aa7c"},"schema_version":"1.0","source":{"id":"2607.23263","kind":"arxiv","version":1}},"canonical_sha256":"dcb34692f0c6e3df2586be7639d03c9dc28cc81510c07e3b890648921b86b9ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dcb34692f0c6e3df2586be7639d03c9dc28cc81510c07e3b890648921b86b9ca","first_computed_at":"2026-07-28T01:22:44.656432Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:22:44.656432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hZBjkMtKNBtY3TfXrE5EthYsTs5OP6jMddQMCutZHpn5jSRxvTTDcvUVo2HGuZUN/4fSGyr63o6EdLAforEYBA==","signature_status":"signed_v1","signed_at":"2026-07-28T01:22:44.657298Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23263","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:31239e6ce6da7e0d57c1b9900f586682f9ac9b7175ac23ee201caef562eb15e7","sha256:8ef08164535bfcf6a783650df9a1ee2c741a41e76c24061a627c85661bf2d945"],"state_sha256":"abe1499857963357aed7621333400af374ce883f3ea1acab075245bd455ab88a"}