{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:X2G7R2UIW3NWUH7QYBGBIHNLGF","short_pith_number":"pith:X2G7R2UI","schema_version":"1.0","canonical_sha256":"be8df8ea88b6db6a1ff0c04c141dab317982dcd21e6a39d548765ff08eb6fc33","source":{"kind":"arxiv","id":"2407.09897","version":2},"attestation_state":"computed","paper":{"title":"Cohesive Conversations: Enhancing Authenticity in Multi-Agent Simulated Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hideki Nakayama, KuanChao Chu, Yi-Pei Chen","submitted_at":"2024-07-13T14:24:45Z","abstract_excerpt":"This paper investigates the quality of multi-agent dialogues in simulations powered by Large Language Models (LLMs). Analyzing dialogues and memory over multiple sessions revealed significant issues such as repetition, inconsistency, and hallucination, exacerbated by the propagation of erroneous information. To combat these challenges, we propose a novel Screening, Diagnosis, and Regeneration (SDR) framework that detects and corrects utterance errors through a comprehensive process involving immediate issue identification, evidence gathering from past dialogues, and LLM analysis for utterance "},"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":"2407.09897","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-13T14:24:45Z","cross_cats_sorted":[],"title_canon_sha256":"2d576b75e92516ab508dfd33052ce4083f3f2e77b4d7d38173d7631a5ae10e96","abstract_canon_sha256":"a24b72357eac3bf7e72fe9d10ecf98dd5126af11360546357929788496a2fa25"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:15.562709Z","signature_b64":"tZKkFBIxTd6xu0zVi79JuJh/5yoQSYiEmcBHBF+C2wQZ5f4xWzy14pqjNVINp0c4eK9SZW4cc+khvDyQTt6QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be8df8ea88b6db6a1ff0c04c141dab317982dcd21e6a39d548765ff08eb6fc33","last_reissued_at":"2026-07-05T08:54:15.562215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:15.562215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cohesive Conversations: Enhancing Authenticity in Multi-Agent Simulated Dialogues","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hideki Nakayama, KuanChao Chu, Yi-Pei Chen","submitted_at":"2024-07-13T14:24:45Z","abstract_excerpt":"This paper investigates the quality of multi-agent dialogues in simulations powered by Large Language Models (LLMs). Analyzing dialogues and memory over multiple sessions revealed significant issues such as repetition, inconsistency, and hallucination, exacerbated by the propagation of erroneous information. To combat these challenges, we propose a novel Screening, Diagnosis, and Regeneration (SDR) framework that detects and corrects utterance errors through a comprehensive process involving immediate issue identification, evidence gathering from past dialogues, and LLM analysis for utterance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.09897","kind":"arxiv","version":2},"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/2407.09897/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":"2407.09897","created_at":"2026-07-05T08:54:15.562276+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.09897v2","created_at":"2026-07-05T08:54:15.562276+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.09897","created_at":"2026-07-05T08:54:15.562276+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2G7R2UIW3NW","created_at":"2026-07-05T08:54:15.562276+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2G7R2UIW3NWUH7Q","created_at":"2026-07-05T08:54:15.562276+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2G7R2UI","created_at":"2026-07-05T08:54:15.562276+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06149","citing_title":"Scaling Personality Control in LLMs with Big Five Scaler Prompts","ref_index":2024,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF","json":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF.json","graph_json":"https://pith.science/api/pith-number/X2G7R2UIW3NWUH7QYBGBIHNLGF/graph.json","events_json":"https://pith.science/api/pith-number/X2G7R2UIW3NWUH7QYBGBIHNLGF/events.json","paper":"https://pith.science/paper/X2G7R2UI"},"agent_actions":{"view_html":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF","download_json":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF.json","view_paper":"https://pith.science/paper/X2G7R2UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.09897&json=true","fetch_graph":"https://pith.science/api/pith-number/X2G7R2UIW3NWUH7QYBGBIHNLGF/graph.json","fetch_events":"https://pith.science/api/pith-number/X2G7R2UIW3NWUH7QYBGBIHNLGF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF/action/storage_attestation","attest_author":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF/action/author_attestation","sign_citation":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF/action/citation_signature","submit_replication":"https://pith.science/pith/X2G7R2UIW3NWUH7QYBGBIHNLGF/action/replication_record"}},"created_at":"2026-07-05T08:54:15.562276+00:00","updated_at":"2026-07-05T08:54:15.562276+00:00"}