{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BXFS5E5DYFGA7WQZDDVHITIJ6E","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":"fa6b8ce76954724a00e9cae11ff741bcb304887da7289fe661e1e56f3c445229","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:16:23Z","title_canon_sha256":"71909ce1f7f38671cc3d49c044d1b6ef43998d1557b33bfee1b30cdd647a4324"},"schema_version":"1.0","source":{"id":"2606.12344","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.12344","created_at":"2026-06-11T01:11:02Z"},{"alias_kind":"arxiv_version","alias_value":"2606.12344v1","created_at":"2026-06-11T01:11:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.12344","created_at":"2026-06-11T01:11:02Z"},{"alias_kind":"pith_short_12","alias_value":"BXFS5E5DYFGA","created_at":"2026-06-11T01:11:02Z"},{"alias_kind":"pith_short_16","alias_value":"BXFS5E5DYFGA7WQZ","created_at":"2026-06-11T01:11:02Z"},{"alias_kind":"pith_short_8","alias_value":"BXFS5E5D","created_at":"2026-06-11T01:11:02Z"}],"graph_snapshots":[{"event_id":"sha256:0dd0637dc7b2732ef0e5124afcd61b30d38bedd25ab81b6d588d6cca12865dab","target":"graph","created_at":"2026-06-11T01:11:02Z","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/2606.12344/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not by itself satisfy the clean Docker workspace, patch, and prediction contract required for scoring. We introduce Claw-SWE-Bench, a multilingual SWE-bench-style benchmark and adapter protocol that makes heterogeneous agent harnesses, or claws, comparable under fair settings including a fixed prompt, runtime budget, workspace contract, patch extraction procedure, and evaluator. The full benchmark contains 350 GitHub issu","authors_text":"Boxun Li, Chao Xu, Guohao Dai, Hailin Hu, Haiyang Xu, Hang Zhou, Jianyuan Guo, Kai Han, Lin Ma, Lixue Xia, Mengyu Zheng, Wei He, Yuchuan Tian, Yunchao Wei, Yunhe Wang, Yu Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:16:23Z","title":"Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.12344","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":"sha256:2afc52db64f352aff286dbeb32efe99d653df4dc705cfb4a797cfa788550125b","target":"record","created_at":"2026-06-11T01:11:02Z","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":"fa6b8ce76954724a00e9cae11ff741bcb304887da7289fe661e1e56f3c445229","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-10T17:16:23Z","title_canon_sha256":"71909ce1f7f38671cc3d49c044d1b6ef43998d1557b33bfee1b30cdd647a4324"},"schema_version":"1.0","source":{"id":"2606.12344","kind":"arxiv","version":1}},"canonical_sha256":"0dcb2e93a3c14c0fda1918ea744d09f10eba94b520a6438bb81eb05f2b2d0e9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0dcb2e93a3c14c0fda1918ea744d09f10eba94b520a6438bb81eb05f2b2d0e9b","first_computed_at":"2026-06-11T01:11:02.904423Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:11:02.904423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2J5UueFak6rj0OMgBfhKARX5LMnC/H3bWnOfQvl/U8DKVVcmo86RhwF2Gt4nuhHxdD+XUFFo/oxgMPOgukRqCw==","signature_status":"signed_v1","signed_at":"2026-06-11T01:11:02.905235Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.12344","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2afc52db64f352aff286dbeb32efe99d653df4dc705cfb4a797cfa788550125b","sha256:0dd0637dc7b2732ef0e5124afcd61b30d38bedd25ab81b6d588d6cca12865dab"],"state_sha256":"70d8256a033c4e64fb8124ebe3da2c434343e6d1c01b822139d42f2a77d85e49"}