{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2FJFGMOO3D3CW2P5FBPH3Z5PFM","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":"1ef5461f3dcf084253b4e0efd4d5e8bcd87107555d1a91efaa0af8f2b86dd25b","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T11:11:17Z","title_canon_sha256":"a8b4b3aa5d5c9346961f374159686aca09bcc1c9831b7cca24d4ab0fef62a738"},"schema_version":"1.0","source":{"id":"2607.13705","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.13705","created_at":"2026-07-16T01:23:02Z"},{"alias_kind":"arxiv_version","alias_value":"2607.13705v1","created_at":"2026-07-16T01:23:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13705","created_at":"2026-07-16T01:23:02Z"},{"alias_kind":"pith_short_12","alias_value":"2FJFGMOO3D3C","created_at":"2026-07-16T01:23:02Z"},{"alias_kind":"pith_short_16","alias_value":"2FJFGMOO3D3CW2P5","created_at":"2026-07-16T01:23:02Z"},{"alias_kind":"pith_short_8","alias_value":"2FJFGMOO","created_at":"2026-07-16T01:23:02Z"}],"graph_snapshots":[{"event_id":"sha256:59f88202c1d75928b6152e54b4b49c6cf5c62244e51422b71cd221d05e9c3746","target":"graph","created_at":"2026-07-16T01:23:02Z","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/2607.13705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) evolve into autonomous agents, the need for unified evaluation infrastructure becomes critical. However, current evaluation pipelines remain highly fragmented and tightly coupled, hindering reproducibility and causing redundant engineering. To address this, we introduce AgentCompass, an open-source, lightweight, and extensible infrastructure for evaluating LLM-based agents. AgentCompass organizes the evaluation process around three independent components, namely Benchmark, Harness, and Environment, thereby enabling flexible configurations without requiring the r","authors_text":"Bowen Yang, Dingbo Yuan, Dongsheng Zhu, Jiaye Ge, Jun Xu, Kai Chen, Liwei Wu, Mo Li, Peiheng Zhou, Qingqiu Li, Qi Zhang, Shudong Liu, Shufan Jiang, Songyang Zhang, Tiaohao Liang, Wenhui Tian, Zehao Li, Zerun Ma, Zhenyu Wu, Zichen Ding, Zixing Shang, Zonglin Li, Zun Wang","cross_cats":["cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T11:11:17Z","title":"AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13705","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":"sha256:1576bb1b296f5474efcbc541670401e1476b6ef733f36cec150986553a7d7b72","target":"record","created_at":"2026-07-16T01:23:02Z","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":"1ef5461f3dcf084253b4e0efd4d5e8bcd87107555d1a91efaa0af8f2b86dd25b","cross_cats_sorted":["cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-15T11:11:17Z","title_canon_sha256":"a8b4b3aa5d5c9346961f374159686aca09bcc1c9831b7cca24d4ab0fef62a738"},"schema_version":"1.0","source":{"id":"2607.13705","kind":"arxiv","version":1}},"canonical_sha256":"d1525331ced8f62b69fd285e7de7af2b1d438a203af65b348eff202b4f5d42e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d1525331ced8f62b69fd285e7de7af2b1d438a203af65b348eff202b4f5d42e3","first_computed_at":"2026-07-16T01:23:02.167656Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-16T01:23:02.167656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8vrFnTg/jD5WLmLvDNaKKyidq29zXEDNjj6UKDWVF8U4Iw9G4umWr+X7N6sv3uCbQu3vjYjUTOi3Q55kqtiTBQ==","signature_status":"signed_v1","signed_at":"2026-07-16T01:23:02.168520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.13705","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1576bb1b296f5474efcbc541670401e1476b6ef733f36cec150986553a7d7b72","sha256:59f88202c1d75928b6152e54b4b49c6cf5c62244e51422b71cd221d05e9c3746"],"state_sha256":"5cf635421a14ac3cef791e680da9e825bf698179704a2b417697d0b972371b2e"}