{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I27P55JDB5NRYAP5YK3EHURXTE","short_pith_number":"pith:I27P55JD","schema_version":"1.0","canonical_sha256":"46befef5230f5b1c01fdc2b643d237992aa5ad81492be862c3cb9bb482768b99","source":{"kind":"arxiv","id":"2305.08135","version":2},"attestation_state":"computed","paper":{"title":"Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Guohai Xu, Ji Zhang, Luo Si, Ming Yan, Qianglong Chen, Yin Zhang","submitted_at":"2023-05-14T12:12:24Z","abstract_excerpt":"Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the properties of retrieved knowledge, they still have trouble benefiting from both the knowledge relevance and distinguishment simultaneously. To address the challenge, we propose CPACE, a Concept-centric Prompt-bAsed Contrastive Explanation Generation model, which aims to convert obtained symbolic knowledge into a contrastive explanation for better distinguishing the differences among given candidates. Firstly, following "},"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":"2305.08135","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-14T12:12:24Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4bce60884cba30d2b1dc7ff0903f339f3d79cdc90b67da89f9065245e42748f3","abstract_canon_sha256":"d676b7718733877b98b9fd44d41b230c18b821fc969604cc5ec20662cedf6a0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:02.838667Z","signature_b64":"QzwLN1YQNkON4vVa9YOUia6Enj6MtaPPtVYiT7JrFBBz/XkbA1+P7bqROdoj8LHkoSwmj9efJPDWjgTTpcKnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46befef5230f5b1c01fdc2b643d237992aa5ad81492be862c3cb9bb482768b99","last_reissued_at":"2026-07-05T06:12:02.838329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:02.838329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distinguish Before Answer: Generating Contrastive Explanation as Knowledge for Commonsense Question Answering","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Guohai Xu, Ji Zhang, Luo Si, Ming Yan, Qianglong Chen, Yin Zhang","submitted_at":"2023-05-14T12:12:24Z","abstract_excerpt":"Existing knowledge-enhanced methods have achieved remarkable results in certain QA tasks via obtaining diverse knowledge from different knowledge bases. However, limited by the properties of retrieved knowledge, they still have trouble benefiting from both the knowledge relevance and distinguishment simultaneously. To address the challenge, we propose CPACE, a Concept-centric Prompt-bAsed Contrastive Explanation Generation model, which aims to convert obtained symbolic knowledge into a contrastive explanation for better distinguishing the differences among given candidates. Firstly, following "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.08135","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/2305.08135/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":"2305.08135","created_at":"2026-07-05T06:12:02.838385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.08135v2","created_at":"2026-07-05T06:12:02.838385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.08135","created_at":"2026-07-05T06:12:02.838385+00:00"},{"alias_kind":"pith_short_12","alias_value":"I27P55JDB5NR","created_at":"2026-07-05T06:12:02.838385+00:00"},{"alias_kind":"pith_short_16","alias_value":"I27P55JDB5NRYAP5","created_at":"2026-07-05T06:12:02.838385+00:00"},{"alias_kind":"pith_short_8","alias_value":"I27P55JD","created_at":"2026-07-05T06:12:02.838385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.05614","citing_title":"Which Prompting Technique Should I Use? An Empirical Investigation of Prompting Techniques for Software Engineering Tasks","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE","json":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE.json","graph_json":"https://pith.science/api/pith-number/I27P55JDB5NRYAP5YK3EHURXTE/graph.json","events_json":"https://pith.science/api/pith-number/I27P55JDB5NRYAP5YK3EHURXTE/events.json","paper":"https://pith.science/paper/I27P55JD"},"agent_actions":{"view_html":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE","download_json":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE.json","view_paper":"https://pith.science/paper/I27P55JD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.08135&json=true","fetch_graph":"https://pith.science/api/pith-number/I27P55JDB5NRYAP5YK3EHURXTE/graph.json","fetch_events":"https://pith.science/api/pith-number/I27P55JDB5NRYAP5YK3EHURXTE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE/action/storage_attestation","attest_author":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE/action/author_attestation","sign_citation":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE/action/citation_signature","submit_replication":"https://pith.science/pith/I27P55JDB5NRYAP5YK3EHURXTE/action/replication_record"}},"created_at":"2026-07-05T06:12:02.838385+00:00","updated_at":"2026-07-05T06:12:02.838385+00:00"}