{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:AI7ISGNFNFPWZLHK3ILS5Y7NF2","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":"7bf07b8dab26032f0f869d50a8d4e3f46fa6230e5d011114849b46362545911d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-08T12:46:03Z","title_canon_sha256":"b34e8c8af2d6170ee63cee937cdd2ddf17429b129299391fdd12ec2674800f13"},"schema_version":"1.0","source":{"id":"2604.07028","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.07028","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2604.07028v2","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.07028","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"AI7ISGNFNFPW","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"AI7ISGNFNFPWZLHK","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"AI7ISGNF","created_at":"2026-05-27T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:b19061f4eb37235387d7f750b5740cd043085ed6927ba940a731ee8816a04c6c","target":"graph","created_at":"2026-05-27T01:04:57Z","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":"heterogeneous teams with complementary traits consistently outperform homogeneous configurations, that moderate interaction depth yields more stable verdicts, and that certain traits (notably quantitative and charismatic) contribute disproportionately to persuasive success. We further introduce a reinforcement-learning-based Trait Orchestrator that dynamically generates defense traits conditioned on the case and opposing team, discovering strategies that outperform static, human-designed trait combinations."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That conditioning LLMs on the nine interpretable traits produces consistent, controllable rhetorical and strategic behaviors that meaningfully approximate real legal persuasion mechanisms, and that verdicts from the synthetic cases provide a valid proxy for strategic success."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Multi-agent LLM simulations with trait-conditioned agents and a reinforcement-learning orchestrator show heterogeneous teams and dynamic trait selection outperform static configurations in simulated legal argumentation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Heterogeneous teams of trait-conditioned language model agents outperform uniform groups in simulated legal arguments, and a learned orchestrator finds even better strategies."}],"snapshot_sha256":"b77bf4233c039b44bcb5c0816fa8d8130dc6e74178044f270a8a61fa23cd5f44"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.07028/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Strategic interaction in adversarial domains such as law, diplomacy, and negotiation is mediated by language, yet most game-theoretic models abstract away the mechanisms of persuasion that operate through discourse. We present the Strategic Courtroom Framework, a multi-agent simulation environment in which prosecution and defense teams composed of trait-conditioned Large Language Model (LLM) agents engage in iterative, round-based legal argumentation. Agents are instantiated using nine interpretable traits organized into four archetypes, enabling systematic control over rhetorical style and st","authors_text":"Philipp D. Siedler","cross_cats":["cs.AI","cs.CL"],"headline":"Heterogeneous teams of trait-conditioned language model agents outperform uniform groups in simulated legal arguments, and a learned orchestrator finds even better strategies.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-08T12:46:03Z","title":"Strategic Persuasion with Trait-Conditioned Multi-Agent Systems for Iterative Legal Argumentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.07028","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:12:29.744992Z","id":"d313a071-e777-4022-b111-19756d517540","model_set":{"reader":"grok-4.3"},"one_line_summary":"Multi-agent LLM simulations with trait-conditioned agents and a reinforcement-learning orchestrator show heterogeneous teams and dynamic trait selection outperform static configurations in simulated legal argumentation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Heterogeneous teams of trait-conditioned language model agents outperform uniform groups in simulated legal arguments, and a learned orchestrator finds even better strategies.","strongest_claim":"heterogeneous teams with complementary traits consistently outperform homogeneous configurations, that moderate interaction depth yields more stable verdicts, and that certain traits (notably quantitative and charismatic) contribute disproportionately to persuasive success. We further introduce a reinforcement-learning-based Trait Orchestrator that dynamically generates defense traits conditioned on the case and opposing team, discovering strategies that outperform static, human-designed trait combinations.","weakest_assumption":"That conditioning LLMs on the nine interpretable traits produces consistent, controllable rhetorical and strategic behaviors that meaningfully approximate real legal persuasion mechanisms, and that verdicts from the synthetic cases provide a valid proxy for strategic success."}},"verdict_id":"d313a071-e777-4022-b111-19756d517540"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c08c37cc6603feda6e779885c6dcee632c32c12d6e224ddb8f428effe1c62da0","target":"record","created_at":"2026-05-27T01:04:57Z","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":"7bf07b8dab26032f0f869d50a8d4e3f46fa6230e5d011114849b46362545911d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.MA","submitted_at":"2026-04-08T12:46:03Z","title_canon_sha256":"b34e8c8af2d6170ee63cee937cdd2ddf17429b129299391fdd12ec2674800f13"},"schema_version":"1.0","source":{"id":"2604.07028","kind":"arxiv","version":2}},"canonical_sha256":"023e8919a5695f6caceada172ee3ed2e99349dad54a0ceae5db70c1c0414cadb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"023e8919a5695f6caceada172ee3ed2e99349dad54a0ceae5db70c1c0414cadb","first_computed_at":"2026-05-27T01:04:57.727222Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:57.727222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OpdX2sDBREyOTakwvbhPSKomryND6W1vnJEas1eGl8cQsphhgUCEovYTBDkRUNxh0wGGyvZSrEk1a05XkeJACg==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:57.727771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.07028","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c08c37cc6603feda6e779885c6dcee632c32c12d6e224ddb8f428effe1c62da0","sha256:b19061f4eb37235387d7f750b5740cd043085ed6927ba940a731ee8816a04c6c"],"state_sha256":"a19ae2948ecc38f643430c61fa50e7a18db2de4df7bb347100b78f344bdc8a22"}