{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:W5HW7MBFAFMLW4Z5MDG5PUVHV7","short_pith_number":"pith:W5HW7MBF","schema_version":"1.0","canonical_sha256":"b74f6fb0250158bb733d60cdd7d2a7afdeac89a83011715a830ab55bc63b0cd7","source":{"kind":"arxiv","id":"2011.01102","version":1},"attestation_state":"computed","paper":{"title":"Exploring Question-Specific Rewards for Generating Deep Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongzhe Wang, Liangming Pan, Min-Yen Kan, Yansong Feng, Yuxi Xie","submitted_at":"2020-11-02T16:37:30Z","abstract_excerpt":"Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with actual question quality, which is often reflected by certain global properties such as whether the question can be answered by the document. As such, we directly optimize for QG-specific objectives via reinforcement learning to improve question quality. We design three different rewards that target to improve the fluency, relevance, and answerability of generate"},"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":"2011.01102","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-02T16:37:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94a21824c242cd56598ba721418d1a30645f5d94b8d6a236c67cfa2b6ab313b0","abstract_canon_sha256":"8c1b362049218976f339b9ab2fe51d01161fc8bc4f180a3cd5246dd703975d3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:22.982676Z","signature_b64":"Wq9lgna2nDZ93ugsLubx9YeCJYRNHVJ5AxfizDpiUuRfkBulYIPJ04kuDcFBE7rMGhhshsUFBqskqq7X1cdhBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b74f6fb0250158bb733d60cdd7d2a7afdeac89a83011715a830ab55bc63b0cd7","last_reissued_at":"2026-07-05T01:48:22.982329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:22.982329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploring Question-Specific Rewards for Generating Deep Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dongzhe Wang, Liangming Pan, Min-Yen Kan, Yansong Feng, Yuxi Xie","submitted_at":"2020-11-02T16:37:30Z","abstract_excerpt":"Recent question generation (QG) approaches often utilize the sequence-to-sequence framework (Seq2Seq) to optimize the log-likelihood of ground-truth questions using teacher forcing. However, this training objective is inconsistent with actual question quality, which is often reflected by certain global properties such as whether the question can be answered by the document. As such, we directly optimize for QG-specific objectives via reinforcement learning to improve question quality. We design three different rewards that target to improve the fluency, relevance, and answerability of generate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01102","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/2011.01102/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":"2011.01102","created_at":"2026-07-05T01:48:22.982392+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.01102v1","created_at":"2026-07-05T01:48:22.982392+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01102","created_at":"2026-07-05T01:48:22.982392+00:00"},{"alias_kind":"pith_short_12","alias_value":"W5HW7MBFAFML","created_at":"2026-07-05T01:48:22.982392+00:00"},{"alias_kind":"pith_short_16","alias_value":"W5HW7MBFAFMLW4Z5","created_at":"2026-07-05T01:48:22.982392+00:00"},{"alias_kind":"pith_short_8","alias_value":"W5HW7MBF","created_at":"2026-07-05T01:48:22.982392+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/W5HW7MBFAFMLW4Z5MDG5PUVHV7","json":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7.json","graph_json":"https://pith.science/api/pith-number/W5HW7MBFAFMLW4Z5MDG5PUVHV7/graph.json","events_json":"https://pith.science/api/pith-number/W5HW7MBFAFMLW4Z5MDG5PUVHV7/events.json","paper":"https://pith.science/paper/W5HW7MBF"},"agent_actions":{"view_html":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7","download_json":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7.json","view_paper":"https://pith.science/paper/W5HW7MBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.01102&json=true","fetch_graph":"https://pith.science/api/pith-number/W5HW7MBFAFMLW4Z5MDG5PUVHV7/graph.json","fetch_events":"https://pith.science/api/pith-number/W5HW7MBFAFMLW4Z5MDG5PUVHV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7/action/storage_attestation","attest_author":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7/action/author_attestation","sign_citation":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7/action/citation_signature","submit_replication":"https://pith.science/pith/W5HW7MBFAFMLW4Z5MDG5PUVHV7/action/replication_record"}},"created_at":"2026-07-05T01:48:22.982392+00:00","updated_at":"2026-07-05T01:48:22.982392+00:00"}