{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4OH7QF4YJWPBOOZZCCDDARIYGP","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":"821b04af947581e5bf78405471649bbd7c546b2e9687550e0d18ab2c8ccdb76c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T09:38:52Z","title_canon_sha256":"0c8ba66becd85fd87d0d967e18fc61f7634d10fe89a4c3cb2ee105243c990f09"},"schema_version":"1.0","source":{"id":"2608.08605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.08605","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"arxiv_version","alias_value":"2608.08605v1","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.08605","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"pith_short_12","alias_value":"4OH7QF4YJWPB","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"pith_short_16","alias_value":"4OH7QF4YJWPBOOZZ","created_at":"2026-08-11T01:23:08Z"},{"alias_kind":"pith_short_8","alias_value":"4OH7QF4Y","created_at":"2026-08-11T01:23:08Z"}],"graph_snapshots":[{"event_id":"sha256:9eb1996d8307d0465282c3e2b4d4f0bcfc9646254ad46cb5cedeaceb730f5deb","target":"graph","created_at":"2026-08-11T01:23:08Z","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/2608.08605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-agent systems (MAS) built on Large Language Models (LLMs) are proliferating rapidly, but their heterogeneous execution traces provide no common basis for evaluation across methods. Outcome-only benchmarks discard collaborations, whereas LLM-as-Judge evaluation requires additional, model-dependent inference and can vary with the LLM and rubric. We introduce a generalizable evaluation framework that maps native MAS traces into a shared space of unified collaboration graphs, enabling different methods to be evaluated under the same representation, reference set, and metric panel. Candidate ","authors_text":"Bingbing Xu, Guo Chen, Haibo Shi, Junjie Huang, Reed Li, Yu Lu, Ziwen Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T09:38:52Z","title":"ForestBench: A Unified Graph Framework for Evaluating Multi-Agent Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.08605","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":"sha256:94eea547ddb9bb19beaff7a21459c64354d30124bae87e99935ad7e8f4a14b0a","target":"record","created_at":"2026-08-11T01:23:08Z","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":"821b04af947581e5bf78405471649bbd7c546b2e9687550e0d18ab2c8ccdb76c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-08-09T09:38:52Z","title_canon_sha256":"0c8ba66becd85fd87d0d967e18fc61f7634d10fe89a4c3cb2ee105243c990f09"},"schema_version":"1.0","source":{"id":"2608.08605","kind":"arxiv","version":1}},"canonical_sha256":"e38ff817984d9e173b39108630451833f127f56cc3f8f504b3ca58daf4f41191","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e38ff817984d9e173b39108630451833f127f56cc3f8f504b3ca58daf4f41191","first_computed_at":"2026-08-11T01:23:08.330724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:23:08.330724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S2nwX/ZqTq46qXvRDim/SJExDFvgnBQZ+F1707AWTuzuQGykgZgUC8MY49+F+lAP9UuLknztiFHiolmkcZZ/BA==","signature_status":"signed_v1","signed_at":"2026-08-11T01:23:08.333513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.08605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94eea547ddb9bb19beaff7a21459c64354d30124bae87e99935ad7e8f4a14b0a","sha256:9eb1996d8307d0465282c3e2b4d4f0bcfc9646254ad46cb5cedeaceb730f5deb"],"state_sha256":"e404cede0c5c0402dd0ded34d9eaa5b76f76373efa639b6bb33557ec2c412d4d"}