{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:KD4QAO7TM4EDAAZ4YLRYRKNZGD","short_pith_number":"pith:KD4QAO7T","schema_version":"1.0","canonical_sha256":"50f9003bf3670830033cc2e388a9b930eaec0d29e7e5c3bfed363f89d53b228e","source":{"kind":"arxiv","id":"1902.11049","version":2},"attestation_state":"computed","paper":{"title":"Evaluating Rewards for Question Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sebastian Riedel, Tom Hosking","submitted_at":"2019-02-28T12:33:17Z","abstract_excerpt":"Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at test time, the model is asked to generate a whole sequence, causing errors to propagate through the generation process (exposure bias). A number of authors have proposed countering this bias by optimising for a reward that is less tightly coupled to the training data, using reinforcement learning. We optimise directly for quality metrics, including a novel appr"},"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":"1902.11049","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-02-28T12:33:17Z","cross_cats_sorted":[],"title_canon_sha256":"d2acd3e29a55aa217dcdd2294b05a3115e1b22539f87b3e2882d9235088d60db","abstract_canon_sha256":"d5d1f09a10d5c3f040ad2ca55989fb027a874e68f16a4fc12c967bf3ece59230"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:29.237816Z","signature_b64":"Y320axj0GQsSw3Vpqmy4GJ9055BgWzYxtJN3kd3vFJCetM19aUOrtVTsA3xSRzpv502fRw1NmFt9Shu9l9djDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50f9003bf3670830033cc2e388a9b930eaec0d29e7e5c3bfed363f89d53b228e","last_reissued_at":"2026-05-17T23:44:29.237308Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:29.237308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Rewards for Question Generation Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sebastian Riedel, Tom Hosking","submitted_at":"2019-02-28T12:33:17Z","abstract_excerpt":"Recent approaches to question generation have used modifications to a Seq2Seq architecture inspired by advances in machine translation. Models are trained using teacher forcing to optimise only the one-step-ahead prediction. However, at test time, the model is asked to generate a whole sequence, causing errors to propagate through the generation process (exposure bias). A number of authors have proposed countering this bias by optimising for a reward that is less tightly coupled to the training data, using reinforcement learning. We optimise directly for quality metrics, including a novel appr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.11049","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":""},"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":"1902.11049","created_at":"2026-05-17T23:44:29.237410+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.11049v2","created_at":"2026-05-17T23:44:29.237410+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.11049","created_at":"2026-05-17T23:44:29.237410+00:00"},{"alias_kind":"pith_short_12","alias_value":"KD4QAO7TM4ED","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"KD4QAO7TM4EDAAZ4","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"KD4QAO7T","created_at":"2026-05-18T12:33:21.387695+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/KD4QAO7TM4EDAAZ4YLRYRKNZGD","json":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD.json","graph_json":"https://pith.science/api/pith-number/KD4QAO7TM4EDAAZ4YLRYRKNZGD/graph.json","events_json":"https://pith.science/api/pith-number/KD4QAO7TM4EDAAZ4YLRYRKNZGD/events.json","paper":"https://pith.science/paper/KD4QAO7T"},"agent_actions":{"view_html":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD","download_json":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD.json","view_paper":"https://pith.science/paper/KD4QAO7T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.11049&json=true","fetch_graph":"https://pith.science/api/pith-number/KD4QAO7TM4EDAAZ4YLRYRKNZGD/graph.json","fetch_events":"https://pith.science/api/pith-number/KD4QAO7TM4EDAAZ4YLRYRKNZGD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD/action/storage_attestation","attest_author":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD/action/author_attestation","sign_citation":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD/action/citation_signature","submit_replication":"https://pith.science/pith/KD4QAO7TM4EDAAZ4YLRYRKNZGD/action/replication_record"}},"created_at":"2026-05-17T23:44:29.237410+00:00","updated_at":"2026-05-17T23:44:29.237410+00:00"}