{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:B3JHLRETC74Z3JAQVCI6AUVZNW","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":"74e389daf04c130f67dfaabeb4b303affd4a94890c2a6088f2a526e49502b7b0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:23:54Z","title_canon_sha256":"caa1709f44ade493cbc8821068cadd19f4dd1c5c1abb4265fd4c92886728ba78"},"schema_version":"1.0","source":{"id":"2606.13608","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.13608","created_at":"2026-06-12T01:10:13Z"},{"alias_kind":"arxiv_version","alias_value":"2606.13608v1","created_at":"2026-06-12T01:10:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.13608","created_at":"2026-06-12T01:10:13Z"},{"alias_kind":"pith_short_12","alias_value":"B3JHLRETC74Z","created_at":"2026-06-12T01:10:13Z"},{"alias_kind":"pith_short_16","alias_value":"B3JHLRETC74Z3JAQ","created_at":"2026-06-12T01:10:13Z"},{"alias_kind":"pith_short_8","alias_value":"B3JHLRET","created_at":"2026-06-12T01:10:13Z"}],"graph_snapshots":[{"event_id":"sha256:1be7609ffb5c2295288dd7037bfe074881773753baa6b29567442e9feb9d66a3","target":"graph","created_at":"2026-06-12T01:10:13Z","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/2606.13608/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, create test-production mismatch, and limit fair comparison across diverse agent designs. The root problem is the lack of an open, agent-agnostic assessment interface. We advocate Agentified Agent Assessment (AAA), where evaluation is performed by judge agents and all participants interact through standardized protocols: A2A for task management and MCP for tool access. Conventional benchmarking defines two separate inte","authors_text":"Alexandre Drouin, Alexandre Lacoste, Andrew Low, Chenguang Wang, Daniel Miao, David Marn, Dawn Song, Donghyun Lee, Elham Tabassi, Elron Bandel, Evan Sandoval, Gal Gantar, Jianhong Tu, Mauro Staver, Michal Shmueli-Scheuer, Nick Hynes, Peter J. Gilbert, Ramayya Krishnan, Sihan Ren, Siva Reddy, Siyuan Xie, Tianneng Shi, Victor Barres, Warren He, Wenbo Guo, Xiaoyuan Liu, Xi Zhang, Yuqi Chen, Yu Su","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:23:54Z","title":"AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.13608","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:fd0cfca8b4bd419c313dcce3f5e56fa446ff4368fb7c32cd3821fb2af882408a","target":"record","created_at":"2026-06-12T01:10:13Z","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":"74e389daf04c130f67dfaabeb4b303affd4a94890c2a6088f2a526e49502b7b0","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-11T17:23:54Z","title_canon_sha256":"caa1709f44ade493cbc8821068cadd19f4dd1c5c1abb4265fd4c92886728ba78"},"schema_version":"1.0","source":{"id":"2606.13608","kind":"arxiv","version":1}},"canonical_sha256":"0ed275c49317f99da410a891e052b96dbbfc77e89d0621945b11f91b079c9cc7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ed275c49317f99da410a891e052b96dbbfc77e89d0621945b11f91b079c9cc7","first_computed_at":"2026-06-12T01:10:13.000524Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-12T01:10:13.000524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TF50mkgSVuuNT4E2Eq5KeOiJNHxEr4CKegQCL+rCLIpCFGHVV2aYiNVGrH6Aydk334Zvd1qebyez7QgKtFC0BA==","signature_status":"signed_v1","signed_at":"2026-06-12T01:10:13.001467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.13608","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd0cfca8b4bd419c313dcce3f5e56fa446ff4368fb7c32cd3821fb2af882408a","sha256:1be7609ffb5c2295288dd7037bfe074881773753baa6b29567442e9feb9d66a3"],"state_sha256":"ed55eac59437b293d183ce132b7300471539fce40584d43e34852a12e01cbdaa"}