{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2AEWQCR4I7ABKW4DHL75E5XEMZ","short_pith_number":"pith:2AEWQCR4","schema_version":"1.0","canonical_sha256":"d009680a3c47c0155b833affd276e4666bed55f5f39fee277240b29bd32a4ec9","source":{"kind":"arxiv","id":"2501.13946","version":1},"attestation_state":"computed","paper":{"title":"Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Deborah A. Dahl, Diego Gosmar","submitted_at":"2025-01-19T11:19:25Z","abstract_excerpt":"Hallucinations remain a significant challenge in current Generative AI models, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized Artificial Intelligent Agents can help mitigate such hallucinations, with a focus on systems leveraging Natural Language Processing (NLP) to facilitate seamless agent interactions. To achieve this, we design a pipeline that introduces over three hundred prompts, purposefully crafted to induce hallucinations, into a front-end agent. The outputs are then systematically reviewed and refined by second- a"},"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":"2501.13946","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T11:19:25Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"9fc9b6d601df20b27babd373d0167599b43648e50b6fb33e6f5e9a7b152f5aff","abstract_canon_sha256":"51743e0a6d7223479a0c8f300284b2860292a52f8b9519df7fc7a10ff1d703f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:04:42.911109Z","signature_b64":"dOJnWQnPaWhfiknIJ4GTOx7hPz+2NKdzJZwMUt5RK9G3I2LSXcNt03rNoqaEg2n/5fEDYm8tOndYMEwEO0BfDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d009680a3c47c0155b833affd276e4666bed55f5f39fee277240b29bd32a4ec9","last_reissued_at":"2026-07-05T10:04:42.910704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:04:42.910704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hallucination Mitigation using Agentic AI Natural Language-Based Frameworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Deborah A. Dahl, Diego Gosmar","submitted_at":"2025-01-19T11:19:25Z","abstract_excerpt":"Hallucinations remain a significant challenge in current Generative AI models, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized Artificial Intelligent Agents can help mitigate such hallucinations, with a focus on systems leveraging Natural Language Processing (NLP) to facilitate seamless agent interactions. To achieve this, we design a pipeline that introduces over three hundred prompts, purposefully crafted to induce hallucinations, into a front-end agent. The outputs are then systematically reviewed and refined by second- a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13946","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/2501.13946/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":"2501.13946","created_at":"2026-07-05T10:04:42.910758+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13946v1","created_at":"2026-07-05T10:04:42.910758+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13946","created_at":"2026-07-05T10:04:42.910758+00:00"},{"alias_kind":"pith_short_12","alias_value":"2AEWQCR4I7AB","created_at":"2026-07-05T10:04:42.910758+00:00"},{"alias_kind":"pith_short_16","alias_value":"2AEWQCR4I7ABKW4D","created_at":"2026-07-05T10:04:42.910758+00:00"},{"alias_kind":"pith_short_8","alias_value":"2AEWQCR4","created_at":"2026-07-05T10:04:42.910758+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26879","citing_title":"A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26879","citing_title":"A Pipeline for Generating Longitudinal Synthetic Clinical Notes Using Large Language Models","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29055","citing_title":"Hallucination Mitigation with Agentic AI, Nested Learning, and AI Sustainability via Semantic Caching","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17159","citing_title":"MADP: A Multi-Agent Pipeline for Sustainable Document Processing with Human-in-the-Loop","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27274","citing_title":"The Inverse-Wisdom Law: Architectural Tribalism and the Consensus Paradox in Agentic Swarms","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ","json":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ.json","graph_json":"https://pith.science/api/pith-number/2AEWQCR4I7ABKW4DHL75E5XEMZ/graph.json","events_json":"https://pith.science/api/pith-number/2AEWQCR4I7ABKW4DHL75E5XEMZ/events.json","paper":"https://pith.science/paper/2AEWQCR4"},"agent_actions":{"view_html":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ","download_json":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ.json","view_paper":"https://pith.science/paper/2AEWQCR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13946&json=true","fetch_graph":"https://pith.science/api/pith-number/2AEWQCR4I7ABKW4DHL75E5XEMZ/graph.json","fetch_events":"https://pith.science/api/pith-number/2AEWQCR4I7ABKW4DHL75E5XEMZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ/action/storage_attestation","attest_author":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ/action/author_attestation","sign_citation":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ/action/citation_signature","submit_replication":"https://pith.science/pith/2AEWQCR4I7ABKW4DHL75E5XEMZ/action/replication_record"}},"created_at":"2026-07-05T10:04:42.910758+00:00","updated_at":"2026-07-05T10:04:42.910758+00:00"}