{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BDEE6AVTJL6UMFMGV5ZKIGEYGJ","short_pith_number":"pith:BDEE6AVT","schema_version":"1.0","canonical_sha256":"08c84f02b34afd461586af72a418983247d538d16d260430db9658c4f96e81ba","source":{"kind":"arxiv","id":"2603.03555","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.MA","authors_text":"Brandon Yee, Pairie Koh","submitted_at":"2026-03-03T22:15:27Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2603.03555","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-03-03T22:15:27Z","cross_cats_sorted":["cs.AI","cs.SI"],"title_canon_sha256":"bbd931d2cc6b4fe1230b6e7355037aa233bff7701d2a56a54391c3ecf348575b","abstract_canon_sha256":"0294bc9559e7c7d0bb48aa0785a2c5066872cf3345fbce462030f64c7170e188"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:22.630389Z","signature_b64":"1o9jKMVvnAIl//S5EJMS5efPCCpYEdQMCdYD6MlSMy71ExdOJN+HGlGx6b4O71MOmw7dd6AB+m02K1kLXngqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08c84f02b34afd461586af72a418983247d538d16d260430db9658c4f96e81ba","last_reissued_at":"2026-06-05T01:15:22.629826Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:22.629826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Emergent Coordination in Large-Scale LLM Populations: An Evaluation Framework on the MoltBook Archive","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","cross_cats":["cs.AI","cs.SI"],"primary_cat":"cs.MA","authors_text":"Brandon Yee, Pairie Koh","submitted_at":"2026-03-03T22:15:27Z","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"},"claims":{"count":4,"items":[{"kind":"strongest_claim","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.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","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.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","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.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"496df6d42c88315f68873b17dbe12eaa65bc516d610356875c7adafc07809867"},"source":{"id":"2603.03555","kind":"arxiv","version":3},"verdict":{"id":"4a4a47f9-da0e-4e70-8860-2936515cb116","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T16:03:47.772108Z","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.","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","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.","pith_extraction_headline":"A new framework applies standardized metrics to 2.73 million interactions to benchmark emergent coordination among 90,704 LLM agents."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.03555/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2603.03555","created_at":"2026-06-05T01:15:22.629894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03555v3","created_at":"2026-06-05T01:15:22.629894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03555","created_at":"2026-06-05T01:15:22.629894+00:00"},{"alias_kind":"pith_short_12","alias_value":"BDEE6AVTJL6U","created_at":"2026-06-05T01:15:22.629894+00:00"},{"alias_kind":"pith_short_16","alias_value":"BDEE6AVTJL6UMFMG","created_at":"2026-06-05T01:15:22.629894+00:00"},{"alias_kind":"pith_short_8","alias_value":"BDEE6AVT","created_at":"2026-06-05T01:15:22.629894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2603.07880","citing_title":"What Do AI Agents Talk About? Discourse and Architectural Constraints in the First AI-Only Social Network","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":122,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ","json":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ.json","graph_json":"https://pith.science/api/pith-number/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/graph.json","events_json":"https://pith.science/api/pith-number/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/events.json","paper":"https://pith.science/paper/BDEE6AVT"},"agent_actions":{"view_html":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ","download_json":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ.json","view_paper":"https://pith.science/paper/BDEE6AVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03555&json=true","fetch_graph":"https://pith.science/api/pith-number/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/graph.json","fetch_events":"https://pith.science/api/pith-number/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/action/storage_attestation","attest_author":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/action/author_attestation","sign_citation":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/action/citation_signature","submit_replication":"https://pith.science/pith/BDEE6AVTJL6UMFMGV5ZKIGEYGJ/action/replication_record"}},"created_at":"2026-06-05T01:15:22.629894+00:00","updated_at":"2026-06-05T01:15:22.629894+00:00"}