{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2CRPD4MTYD4VLPLS5MFFNSPJ7S","short_pith_number":"pith:2CRPD4MT","schema_version":"1.0","canonical_sha256":"d0a2f1f193c0f955bd72eb0a56c9e9fca6685c192334c94b2e83cc515bf265bf","source":{"kind":"arxiv","id":"2204.03025","version":1},"attestation_state":"computed","paper":{"title":"Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie C.K. Cheung, Prakhar Sharma, Siva Reddy, Xing Han Lu, Zichao Li","submitted_at":"2022-04-06T18:17:09Z","abstract_excerpt":"Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further \\emph{post-}deployment based on user interactions? We focus on two kinds of improvements: 1) improving the QA system's performance itself, and 2) providing the model with the ability to explain the correctness or incorrectness of an answer. We collect a retrieval-based QA dataset, FeedbackQA, which contains interactive feedback from users. We collect this dataset by deploying a base QA system to crowdwork"},"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":"2204.03025","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-06T18:17:09Z","cross_cats_sorted":[],"title_canon_sha256":"94b19b19180f65915a7499868448d952f4c79af0e2fcd4e68da2b2a56d62960d","abstract_canon_sha256":"c1519cfa779aea6d791f62a0954b5084b1a0299693e79132e35904eb5f6270ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:52:07.285628Z","signature_b64":"hHg1lhwsKFEoMuBAZWGT9OQO4UnqvcgmEH0zRGdKSl8o8704s26yjgAv/7pBkpvLdYtrOJHb7kbAl7/1pjutCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0a2f1f193c0f955bd72eb0a56c9e9fca6685c192334c94b2e83cc515bf265bf","last_reissued_at":"2026-07-05T05:52:07.285209Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:52:07.285209Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jackie C.K. Cheung, Prakhar Sharma, Siva Reddy, Xing Han Lu, Zichao Li","submitted_at":"2022-04-06T18:17:09Z","abstract_excerpt":"Most research on question answering focuses on the pre-deployment stage; i.e., building an accurate model for deployment. In this paper, we ask the question: Can we improve QA systems further \\emph{post-}deployment based on user interactions? We focus on two kinds of improvements: 1) improving the QA system's performance itself, and 2) providing the model with the ability to explain the correctness or incorrectness of an answer. We collect a retrieval-based QA dataset, FeedbackQA, which contains interactive feedback from users. We collect this dataset by deploying a base QA system to crowdwork"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03025","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/2204.03025/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":"2204.03025","created_at":"2026-07-05T05:52:07.285269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.03025v1","created_at":"2026-07-05T05:52:07.285269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03025","created_at":"2026-07-05T05:52:07.285269+00:00"},{"alias_kind":"pith_short_12","alias_value":"2CRPD4MTYD4V","created_at":"2026-07-05T05:52:07.285269+00:00"},{"alias_kind":"pith_short_16","alias_value":"2CRPD4MTYD4VLPLS","created_at":"2026-07-05T05:52:07.285269+00:00"},{"alias_kind":"pith_short_8","alias_value":"2CRPD4MT","created_at":"2026-07-05T05:52:07.285269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05353","citing_title":"Evidence Lock Before Commitment: A Frozen Interface Degrades LLM-as-Judge Evaluation","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S","json":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S.json","graph_json":"https://pith.science/api/pith-number/2CRPD4MTYD4VLPLS5MFFNSPJ7S/graph.json","events_json":"https://pith.science/api/pith-number/2CRPD4MTYD4VLPLS5MFFNSPJ7S/events.json","paper":"https://pith.science/paper/2CRPD4MT"},"agent_actions":{"view_html":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S","download_json":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S.json","view_paper":"https://pith.science/paper/2CRPD4MT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.03025&json=true","fetch_graph":"https://pith.science/api/pith-number/2CRPD4MTYD4VLPLS5MFFNSPJ7S/graph.json","fetch_events":"https://pith.science/api/pith-number/2CRPD4MTYD4VLPLS5MFFNSPJ7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S/action/storage_attestation","attest_author":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S/action/author_attestation","sign_citation":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S/action/citation_signature","submit_replication":"https://pith.science/pith/2CRPD4MTYD4VLPLS5MFFNSPJ7S/action/replication_record"}},"created_at":"2026-07-05T05:52:07.285269+00:00","updated_at":"2026-07-05T05:52:07.285269+00:00"}