{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:BDEE6AVTJL6UMFMGV5ZKIGEYGJ","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":"0294bc9559e7c7d0bb48aa0785a2c5066872cf3345fbce462030f64c7170e188","cross_cats_sorted":["cs.AI","cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-03-03T22:15:27Z","title_canon_sha256":"bbd931d2cc6b4fe1230b6e7355037aa233bff7701d2a56a54391c3ecf348575b"},"schema_version":"1.0","source":{"id":"2603.03555","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03555","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03555v3","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03555","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"pith_short_12","alias_value":"BDEE6AVTJL6U","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"pith_short_16","alias_value":"BDEE6AVTJL6UMFMG","created_at":"2026-06-05T01:15:22Z"},{"alias_kind":"pith_short_8","alias_value":"BDEE6AVT","created_at":"2026-06-05T01:15:22Z"}],"graph_snapshots":[{"event_id":"sha256:0d2f997dc13404eae377da680adce05764ba82f85811689d1a3ddf86bdcb245b","target":"graph","created_at":"2026-06-05T01:15:22Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"By providing standardized evaluation tasks and empirical baselines, our framework enables the rigorous comparison of future multi-agent protocols and establishes evaluation itself as an object of scientific study."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the MoltBook Observatory Archive of 2.73M interactions among 90,704 agents is representative of genuine emergent coordination dynamics in real-world large-scale LLM populations and that the chosen metrics (silhouette score, power-law exponent, Cohen's d) adequately capture the relevant coordination phenomena."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Presents a benchmarking framework for emergent coordination in large LLM agent populations, with baselines from 2.73 million interactions showing strong core-periphery structure, heavy-tailed cascades, and high decentralized overhead."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents."}],"snapshot_sha256":"496df6d42c88315f68873b17dbe12eaa65bc516d610356875c7adafc07809867"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.03555/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As multi-agent Large Language Model (LLM) systems scale, evaluating their emergent coordination dynamics becomes increasingly critical. However, current evaluation paradigms-focused on single agents or small, explicitly structured groups-fail to capture the self-organization and viral information dynamics that arise in large, decentralized populations. We introduce a systematic evaluation framework to benchmark role specialization, information diffusion, and cooperative task resolution in open agent environments. We demonstrate this framework on the MoltBook Observatory Archive, a dataset of 2","authors_text":"Brandon Yee, Pairie Koh","cross_cats":["cs.AI","cs.SI"],"headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-03-03T22:15:27Z","title":"Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03555","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-15T16:03:47.772108Z","id":"4a4a47f9-da0e-4e70-8860-2936515cb116","model_set":{"reader":"grok-4.3"},"one_line_summary":"Presents a benchmarking framework for emergent coordination in large LLM agent populations, with baselines from 2.73 million interactions showing strong core-periphery structure, heavy-tailed cascades, and high decentralized overhead.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","strongest_claim":"By providing standardized evaluation tasks and empirical baselines, our framework enables the rigorous comparison of future multi-agent protocols and establishes evaluation itself as an object of scientific study.","weakest_assumption":"That the MoltBook Observatory Archive of 2.73M interactions among 90,704 agents is representative of genuine emergent coordination dynamics in real-world large-scale LLM populations and that the chosen metrics (silhouette score, power-law exponent, Cohen's d) adequately capture the relevant coordination phenomena."}},"verdict_id":"4a4a47f9-da0e-4e70-8860-2936515cb116"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a50fb7a1e0471dff96b9fff2a1532a85f79b39880430f78c020509f9077521c","target":"record","created_at":"2026-06-05T01:15:22Z","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":"0294bc9559e7c7d0bb48aa0785a2c5066872cf3345fbce462030f64c7170e188","cross_cats_sorted":["cs.AI","cs.SI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-03-03T22:15:27Z","title_canon_sha256":"bbd931d2cc6b4fe1230b6e7355037aa233bff7701d2a56a54391c3ecf348575b"},"schema_version":"1.0","source":{"id":"2603.03555","kind":"arxiv","version":3}},"canonical_sha256":"08c84f02b34afd461586af72a418983247d538d16d260430db9658c4f96e81ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"08c84f02b34afd461586af72a418983247d538d16d260430db9658c4f96e81ba","first_computed_at":"2026-06-05T01:15:22.629826Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:22.629826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1o9jKMVvnAIl//S5EJMS5efPCCpYEdQMCdYD6MlSMy71ExdOJN+HGlGx6b4O71MOmw7dd6AB+m02K1kLXngqDA==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:22.630389Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.03555","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a50fb7a1e0471dff96b9fff2a1532a85f79b39880430f78c020509f9077521c","sha256:0d2f997dc13404eae377da680adce05764ba82f85811689d1a3ddf86bdcb245b"],"state_sha256":"efd7cd950214e8620824c7b31397c163732e880f22e8421f49b2d27005bdcb6b"}