{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SUP4V5MBLAI5KIY4TRPF57IQWL","short_pith_number":"pith:SUP4V5MB","schema_version":"1.0","canonical_sha256":"951fcaf5815811d5231c9c5e5efd10b2c7f5682721bb2f70a00f4631193a816e","source":{"kind":"arxiv","id":"2402.06634","version":1},"attestation_state":"computed","paper":{"title":"SocraSynth: Multi-LLM Reasoning with Conditional Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Edward Y. Chang","submitted_at":"2024-01-19T07:16:21Z","abstract_excerpt":"Large language models (LLMs), while promising, face criticisms for biases, hallucinations, and a lack of reasoning capability. This paper introduces SocraSynth, a multi-LLM agent reasoning platform developed to mitigate these issues. SocraSynth utilizes conditional statistics and systematic context enhancement through continuous arguments, alongside adjustable debate contentiousness levels. The platform typically involves a human moderator and two LLM agents representing opposing viewpoints on a given subject. SocraSynth operates in two main phases: knowledge generation and reasoning evaluatio"},"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":"2402.06634","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-01-19T07:16:21Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"5fce7d3bf072e0dfce63e150209c125ea61a2841115e7aa2c177f02d72b4faf0","abstract_canon_sha256":"b77f06445d4657022bbf01d41f2172d58ea2607aa832e2415e904bb688ffaf3b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:36.029129Z","signature_b64":"x+Ma91NMdJXhiclPj8ozpYOj1CTS/YGm/one1A0Fe+0HVKQxK9HHMCNKoGT1+IOiFQJtAh6C45d3LTwjeQuzAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"951fcaf5815811d5231c9c5e5efd10b2c7f5682721bb2f70a00f4631193a816e","last_reissued_at":"2026-07-05T07:43:36.028655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:36.028655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SocraSynth: Multi-LLM Reasoning with Conditional Statistics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Edward Y. Chang","submitted_at":"2024-01-19T07:16:21Z","abstract_excerpt":"Large language models (LLMs), while promising, face criticisms for biases, hallucinations, and a lack of reasoning capability. This paper introduces SocraSynth, a multi-LLM agent reasoning platform developed to mitigate these issues. SocraSynth utilizes conditional statistics and systematic context enhancement through continuous arguments, alongside adjustable debate contentiousness levels. The platform typically involves a human moderator and two LLM agents representing opposing viewpoints on a given subject. SocraSynth operates in two main phases: knowledge generation and reasoning evaluatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.06634","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.06634/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":"2402.06634","created_at":"2026-07-05T07:43:36.028710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.06634v1","created_at":"2026-07-05T07:43:36.028710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.06634","created_at":"2026-07-05T07:43:36.028710+00:00"},{"alias_kind":"pith_short_12","alias_value":"SUP4V5MBLAI5","created_at":"2026-07-05T07:43:36.028710+00:00"},{"alias_kind":"pith_short_16","alias_value":"SUP4V5MBLAI5KIY4","created_at":"2026-07-05T07:43:36.028710+00:00"},{"alias_kind":"pith_short_8","alias_value":"SUP4V5MB","created_at":"2026-07-05T07:43:36.028710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23676","citing_title":"AI at the Front Lines of Platform Governance: Using LLMs to Support Illegal Content Reporting under the Digital Services Act","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23676","citing_title":"AI at the Front Lines of Platform Governance: Using LLMs to Support Illegal Content Reporting under the Digital Services Act","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01704","citing_title":"The Reasoning Trap: An Information-Theoretic Bound on Closed-System Multi-Step LLM Reasoning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL","json":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL.json","graph_json":"https://pith.science/api/pith-number/SUP4V5MBLAI5KIY4TRPF57IQWL/graph.json","events_json":"https://pith.science/api/pith-number/SUP4V5MBLAI5KIY4TRPF57IQWL/events.json","paper":"https://pith.science/paper/SUP4V5MB"},"agent_actions":{"view_html":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL","download_json":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL.json","view_paper":"https://pith.science/paper/SUP4V5MB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.06634&json=true","fetch_graph":"https://pith.science/api/pith-number/SUP4V5MBLAI5KIY4TRPF57IQWL/graph.json","fetch_events":"https://pith.science/api/pith-number/SUP4V5MBLAI5KIY4TRPF57IQWL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL/action/storage_attestation","attest_author":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL/action/author_attestation","sign_citation":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL/action/citation_signature","submit_replication":"https://pith.science/pith/SUP4V5MBLAI5KIY4TRPF57IQWL/action/replication_record"}},"created_at":"2026-07-05T07:43:36.028710+00:00","updated_at":"2026-07-05T07:43:36.028710+00:00"}