{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M2NKBJBSXAJSFKMXXRRTKASRBF","short_pith_number":"pith:M2NKBJBS","schema_version":"1.0","canonical_sha256":"669aa0a432b81322a997bc633502510978cd88199e5e40902158e31f8b76c840","source":{"kind":"arxiv","id":"2507.11875","version":1},"attestation_state":"computed","paper":{"title":"DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingshen Zhang, Ruiying Niu, Tianyou Huang, Xinglu Chen, Xinying Qiu","submitted_at":"2025-07-16T03:39:36Z","abstract_excerpt":"This paper introduces DualReward, a novel reinforcement learning framework for automatic distractor generation in cloze tests. Unlike conventional approaches that rely primarily on supervised learning or static generative models, our method employs a dual reward structure with adaptive scaling that differentiates between human-created gold standard distractors and model-generated candidates. The framework dynamically adjusts reward signal intensity based on model performance and confidence. We evaluate our approach on both passage-level (CLOTH-F) and sentence-level (MCQ) cloze test datasets, d"},"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":"2507.11875","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-16T03:39:36Z","cross_cats_sorted":[],"title_canon_sha256":"fc15016f25b5d3df72d2583eaf1ca25ad4620d9ed5a6a17aa862fa9885afc0a6","abstract_canon_sha256":"2e90b7b86414e063d9f8cbc1e0ccc0bccec5628d08d10cca3d513e3c9cdb03f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:37:52.521172Z","signature_b64":"9n/jd28BWVaTccdcyYgrprU2Z4GW4yDaAKWUpHAFB1BLcKkPysBoyHTAR1DHrxfmrGr5Q9qUhC/+JbaHN4YOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669aa0a432b81322a997bc633502510978cd88199e5e40902158e31f8b76c840","last_reissued_at":"2026-07-05T11:37:52.520665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:37:52.520665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DualReward: A Dynamic Reinforcement Learning Framework for Cloze Tests Distractor Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jingshen Zhang, Ruiying Niu, Tianyou Huang, Xinglu Chen, Xinying Qiu","submitted_at":"2025-07-16T03:39:36Z","abstract_excerpt":"This paper introduces DualReward, a novel reinforcement learning framework for automatic distractor generation in cloze tests. Unlike conventional approaches that rely primarily on supervised learning or static generative models, our method employs a dual reward structure with adaptive scaling that differentiates between human-created gold standard distractors and model-generated candidates. The framework dynamically adjusts reward signal intensity based on model performance and confidence. We evaluate our approach on both passage-level (CLOTH-F) and sentence-level (MCQ) cloze test datasets, d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.11875","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/2507.11875/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":"2507.11875","created_at":"2026-07-05T11:37:52.520737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.11875v1","created_at":"2026-07-05T11:37:52.520737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.11875","created_at":"2026-07-05T11:37:52.520737+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2NKBJBSXAJS","created_at":"2026-07-05T11:37:52.520737+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2NKBJBSXAJSFKMX","created_at":"2026-07-05T11:37:52.520737+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2NKBJBS","created_at":"2026-07-05T11:37:52.520737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF","json":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF.json","graph_json":"https://pith.science/api/pith-number/M2NKBJBSXAJSFKMXXRRTKASRBF/graph.json","events_json":"https://pith.science/api/pith-number/M2NKBJBSXAJSFKMXXRRTKASRBF/events.json","paper":"https://pith.science/paper/M2NKBJBS"},"agent_actions":{"view_html":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF","download_json":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF.json","view_paper":"https://pith.science/paper/M2NKBJBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.11875&json=true","fetch_graph":"https://pith.science/api/pith-number/M2NKBJBSXAJSFKMXXRRTKASRBF/graph.json","fetch_events":"https://pith.science/api/pith-number/M2NKBJBSXAJSFKMXXRRTKASRBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF/action/storage_attestation","attest_author":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF/action/author_attestation","sign_citation":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF/action/citation_signature","submit_replication":"https://pith.science/pith/M2NKBJBSXAJSFKMXXRRTKASRBF/action/replication_record"}},"created_at":"2026-07-05T11:37:52.520737+00:00","updated_at":"2026-07-05T11:37:52.520737+00:00"}