{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3URZWC37CXINPDCJC52SQKJ6MY","merge_version":"pith-open-graph-merge-v1","event_count":5,"valid_event_count":5,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"48f8c1460856cbe77c13bcae9fe14d6f6d6bcd22e409afe67559c9cd46587daf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T17:59:32Z","title_canon_sha256":"42fcca74432c744f0c4135fe64e4f00791e7323259789ab293d03368023dede9"},"schema_version":"1.0","source":{"id":"2607.08768","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08768","created_at":"2026-07-10T01:19:59Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08768v1","created_at":"2026-07-10T01:19:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08768","created_at":"2026-07-10T01:19:59Z"},{"alias_kind":"pith_short_12","alias_value":"3URZWC37CXIN","created_at":"2026-07-10T01:19:59Z"},{"alias_kind":"pith_short_16","alias_value":"3URZWC37CXINPDCJ","created_at":"2026-07-10T01:19:59Z"},{"alias_kind":"pith_short_8","alias_value":"3URZWC37","created_at":"2026-07-10T01:19:59Z"}],"graph_snapshots":[{"event_id":"sha256:f9859aa6b875a390f8c5c99bd460c1150c45354f5ff5562f080a4d54c2703f34","target":"graph","created_at":"2026-07-10T01:19:59Z","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/2607.08768/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid development of large language models and multimodal large language models has accelerated the emergence of proactive agents capable of operating everyday tools and assisting users in real-world environments. However, existing benchmarks struggle to evaluate such agents effectively, as they often rely on sandboxed environments and single-turn evaluation paradigms. Moreover, their scenario-based task taxonomies mix multiple model capabilities within the same task category, making it difficult to identify the root causes of agent failures. To address these limitations, we introduce UniC","authors_text":"Bohao Li, Chengqi Duan, Kaiyue Sun, Manyuan Zhang, Xihui Liu, Yuqing Wang, Zhekai Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T17:59:32Z","title":"UniClawBench: A Universal Benchmark for Proactive Agents on Real-World Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08768","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":"sha256:6b7c9d8a5b9a344c0f449a5eaa884c9229a233c8dbf4e0e8511012d3b9a5fc04","target":"record","created_at":"2026-07-10T01:19:59Z","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":"48f8c1460856cbe77c13bcae9fe14d6f6d6bcd22e409afe67559c9cd46587daf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-09T17:59:32Z","title_canon_sha256":"42fcca74432c744f0c4135fe64e4f00791e7323259789ab293d03368023dede9"},"schema_version":"1.0","source":{"id":"2607.08768","kind":"arxiv","version":1}},"canonical_sha256":"dd239b0b7f15d0d78c49177528293e661606d38825b5165de6960d21abee52e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dd239b0b7f15d0d78c49177528293e661606d38825b5165de6960d21abee52e5","first_computed_at":"2026-07-10T01:19:59.760829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:59.760829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FvjzH3NXXFTTSeJJbEiB9RqDexrdUb2atP9dvbi71TaiqooqhluXY8JsOUZIOhGZEJ1CJMRSDrAMBSUp2X+hDQ==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:59.761463Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08768","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:14f5da4c8d1b637cbf52259f0fe1e2b6af254d123ba80645e440415b6a3d5622","sha256:85d91884b120c617826e1135cad5624570a57f4814b24a0a1396e249cd3a08ca","sha256:ffb106c961061cd19be769f6cf3eb1d9d20b7a07ae6a5029739a2b8e158ca1bd"]}],"invalid_events":[],"applied_event_ids":["sha256:6b7c9d8a5b9a344c0f449a5eaa884c9229a233c8dbf4e0e8511012d3b9a5fc04","sha256:f9859aa6b875a390f8c5c99bd460c1150c45354f5ff5562f080a4d54c2703f34"],"state_sha256":"36f7bf8e19f27ac8badf70445fc93a1fb39a6653b1cfdbe319d6b56a6096527e"}