{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CW7HKKLRM5YYVCP7KY5WCTT27Z","short_pith_number":"pith:CW7HKKLR","schema_version":"1.0","canonical_sha256":"15be75297167718a89ff563b614e7afe768546445fe5679a4926197b527e82f6","source":{"kind":"arxiv","id":"2303.17071","version":1},"attestation_state":"computed","paper":{"title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anitha Kannan, Elliot Schumacher, Geoffrey Tso, Varun Nair","submitted_at":"2023-03-30T00:30:19Z","abstract_excerpt":"Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate outputs that are factually accurate and complete. In this work, we present dialog-enabled resolving agents (DERA). DERA is a paradigm made possible by the increased conversational abilities of LLMs, namely GPT-4. It provides a simple, interpretable forum for models to communicate feedback and iteratively improve output. We frame our dialog as a discussion between two ag"},"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":"2303.17071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-03-30T00:30:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ef6197054c706ecda5dd6f8bd05c43de99fccf03af6a9da201b258d5232d8bab","abstract_canon_sha256":"fb8e88e1e2083a0838cc1c9edfb36891da1b9ec80c1f9beaca43bd2379d9ead3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:56:19.112310Z","signature_b64":"8JEnIT+69TS1paNihXfWYdHMQwY2LNFhgqyMfA2F60OitZawRoMTlpwHZOCqSZHaINdTKpmXk/mq6Kttr6hFDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15be75297167718a89ff563b614e7afe768546445fe5679a4926197b527e82f6","last_reissued_at":"2026-07-05T05:56:19.111916Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:56:19.111916Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DERA: Enhancing Large Language Model Completions with Dialog-Enabled Resolving Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Anitha Kannan, Elliot Schumacher, Geoffrey Tso, Varun Nair","submitted_at":"2023-03-30T00:30:19Z","abstract_excerpt":"Large language models (LLMs) have emerged as valuable tools for many natural language understanding tasks. In safety-critical applications such as healthcare, the utility of these models is governed by their ability to generate outputs that are factually accurate and complete. In this work, we present dialog-enabled resolving agents (DERA). DERA is a paradigm made possible by the increased conversational abilities of LLMs, namely GPT-4. It provides a simple, interpretable forum for models to communicate feedback and iteratively improve output. We frame our dialog as a discussion between two ag"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17071","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/2303.17071/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":"2303.17071","created_at":"2026-07-05T05:56:19.111974+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17071v1","created_at":"2026-07-05T05:56:19.111974+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17071","created_at":"2026-07-05T05:56:19.111974+00:00"},{"alias_kind":"pith_short_12","alias_value":"CW7HKKLRM5YY","created_at":"2026-07-05T05:56:19.111974+00:00"},{"alias_kind":"pith_short_16","alias_value":"CW7HKKLRM5YYVCP7","created_at":"2026-07-05T05:56:19.111974+00:00"},{"alias_kind":"pith_short_8","alias_value":"CW7HKKLR","created_at":"2026-07-05T05:56:19.111974+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.09617","citing_title":"Towards Expert-Level Medical Question Answering with Large Language Models","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2309.03409","citing_title":"Large Language Models as Optimizers","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2304.05128","citing_title":"Teaching Large Language Models to Self-Debug","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2502.18864","citing_title":"Towards an AI co-scientist","ref_index":199,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2303.11366","citing_title":"Reflexion: Language Agents with Verbal Reinforcement Learning","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2305.16291","citing_title":"Voyager: An Open-Ended Embodied Agent with Large Language Models","ref_index":81,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z","json":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z.json","graph_json":"https://pith.science/api/pith-number/CW7HKKLRM5YYVCP7KY5WCTT27Z/graph.json","events_json":"https://pith.science/api/pith-number/CW7HKKLRM5YYVCP7KY5WCTT27Z/events.json","paper":"https://pith.science/paper/CW7HKKLR"},"agent_actions":{"view_html":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z","download_json":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z.json","view_paper":"https://pith.science/paper/CW7HKKLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17071&json=true","fetch_graph":"https://pith.science/api/pith-number/CW7HKKLRM5YYVCP7KY5WCTT27Z/graph.json","fetch_events":"https://pith.science/api/pith-number/CW7HKKLRM5YYVCP7KY5WCTT27Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z/action/storage_attestation","attest_author":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z/action/author_attestation","sign_citation":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z/action/citation_signature","submit_replication":"https://pith.science/pith/CW7HKKLRM5YYVCP7KY5WCTT27Z/action/replication_record"}},"created_at":"2026-07-05T05:56:19.111974+00:00","updated_at":"2026-07-05T05:56:19.111974+00:00"}