{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HPIJY6GJI76EOFHBY6UU7W4DF6","short_pith_number":"pith:HPIJY6GJ","schema_version":"1.0","canonical_sha256":"3bd09c78c947fc4714e1c7a94fdb832fa3b910fd566f839ac0f0df9bfb1c9095","source":{"kind":"arxiv","id":"2311.09513","version":1},"attestation_state":"computed","paper":{"title":"Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Grace Hui Yang, Quinn Patwardhan","submitted_at":"2023-11-16T02:37:58Z","abstract_excerpt":"This paper contains what the Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG across various cut numbers and in overall success rate. Our approach uses a Generate-Retrieve-Generate method, which we've found to greatly outpace Retrieve-Then-Generate approaches for the purposes of iKAT. Our solution involves the use of Large Language Models (LLMs) for initial answers, answer grounding by BM25, passage quality filtering by logistic regr"},"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":"2311.09513","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-11-16T02:37:58Z","cross_cats_sorted":[],"title_canon_sha256":"86b1d687af1198d081171ada265f388241176776110f88a47a789df2e2a7da57","abstract_canon_sha256":"0e1bec00ae72af58620ace4052691a48b421368a904d5063e6ac55421a266bed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:13:29.083275Z","signature_b64":"LSYZjYjRHDhuQmOrY4X1KI95Abw/R1yyP52WyTtssGywQ/4Q7UZNnYmXxzv7r+ir4eI3FbpTkGEnovtS14YLDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd09c78c947fc4714e1c7a94fdb832fa3b910fd566f839ac0f0df9bfb1c9095","last_reissued_at":"2026-07-05T07:13:29.082772Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:13:29.082772Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sequencing Matters: A Generate-Retrieve-Generate Model for Building Conversational Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Grace Hui Yang, Quinn Patwardhan","submitted_at":"2023-11-16T02:37:58Z","abstract_excerpt":"This paper contains what the Georgetown InfoSense group has done in regard to solving the challenges presented by TREC iKAT 2023. Our submitted runs outperform the median runs by a significant margin, exhibiting superior performance in nDCG across various cut numbers and in overall success rate. Our approach uses a Generate-Retrieve-Generate method, which we've found to greatly outpace Retrieve-Then-Generate approaches for the purposes of iKAT. Our solution involves the use of Large Language Models (LLMs) for initial answers, answer grounding by BM25, passage quality filtering by logistic regr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.09513","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/2311.09513/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":"2311.09513","created_at":"2026-07-05T07:13:29.082835+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.09513v1","created_at":"2026-07-05T07:13:29.082835+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.09513","created_at":"2026-07-05T07:13:29.082835+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPIJY6GJI76E","created_at":"2026-07-05T07:13:29.082835+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPIJY6GJI76EOFHB","created_at":"2026-07-05T07:13:29.082835+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPIJY6GJ","created_at":"2026-07-05T07:13:29.082835+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.08634","citing_title":"Adaptive Personalized Conversational Information Retrieval","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6","json":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6.json","graph_json":"https://pith.science/api/pith-number/HPIJY6GJI76EOFHBY6UU7W4DF6/graph.json","events_json":"https://pith.science/api/pith-number/HPIJY6GJI76EOFHBY6UU7W4DF6/events.json","paper":"https://pith.science/paper/HPIJY6GJ"},"agent_actions":{"view_html":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6","download_json":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6.json","view_paper":"https://pith.science/paper/HPIJY6GJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.09513&json=true","fetch_graph":"https://pith.science/api/pith-number/HPIJY6GJI76EOFHBY6UU7W4DF6/graph.json","fetch_events":"https://pith.science/api/pith-number/HPIJY6GJI76EOFHBY6UU7W4DF6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6/action/storage_attestation","attest_author":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6/action/author_attestation","sign_citation":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6/action/citation_signature","submit_replication":"https://pith.science/pith/HPIJY6GJI76EOFHBY6UU7W4DF6/action/replication_record"}},"created_at":"2026-07-05T07:13:29.082835+00:00","updated_at":"2026-07-05T07:13:29.082835+00:00"}