{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:M5PIZSXKFMF533J7KBP3U6RQJV","short_pith_number":"pith:M5PIZSXK","schema_version":"1.0","canonical_sha256":"675e8ccaea2b0bdded3f505fba7a304d6e3cb9c31700bb5619a1f1dfb43abc34","source":{"kind":"arxiv","id":"1707.06209","version":1},"attestation_state":"computed","paper":{"title":"Crowdsourcing Multiple Choice Science Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.HC","authors_text":"Johannes Welbl, Matt Gardner, Nelson F. Liu","submitted_at":"2017-07-19T17:28:46Z","abstract_excerpt":"We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality, relevance or diversity in the answer options. Our method addresses these problems by leveraging a large corpus of domain-specific text and a small set of existing questions. It produces model suggestions for document selection and answer distractor choice which aid the human question generation process. With this method we have assembled SciQ, a dataset of 13.7K multiple choice science exam questions (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":"1707.06209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.HC","submitted_at":"2017-07-19T17:28:46Z","cross_cats_sorted":["cs.AI","cs.CL","stat.ML"],"title_canon_sha256":"889c31c8c6874c18f276bb679118b521633a6eccfaa38f8aad270c1c47d83dc6","abstract_canon_sha256":"bdc2efe5c858864ce8087af8fca0508f3562d047e29a838417a21228291c17dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:39:57.274601Z","signature_b64":"LsICs7ulQWelmtCd98/6kqo1yYz0mdSaPzpjwCNseC0ONjxW1nyWLlQWZ1bWWo9rIAF+CWlJ7DFRI+ep3fxrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"675e8ccaea2b0bdded3f505fba7a304d6e3cb9c31700bb5619a1f1dfb43abc34","last_reissued_at":"2026-05-18T00:39:57.274072Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:39:57.274072Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crowdsourcing Multiple Choice Science Questions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","stat.ML"],"primary_cat":"cs.HC","authors_text":"Johannes Welbl, Matt Gardner, Nelson F. Liu","submitted_at":"2017-07-19T17:28:46Z","abstract_excerpt":"We present a novel method for obtaining high-quality, domain-targeted multiple choice questions from crowd workers. Generating these questions can be difficult without trading away originality, relevance or diversity in the answer options. Our method addresses these problems by leveraging a large corpus of domain-specific text and a small set of existing questions. It produces model suggestions for document selection and answer distractor choice which aid the human question generation process. With this method we have assembled SciQ, a dataset of 13.7K multiple choice science exam questions (D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06209","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":""},"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":"1707.06209","created_at":"2026-05-18T00:39:57.274168+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.06209v1","created_at":"2026-05-18T00:39:57.274168+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06209","created_at":"2026-05-18T00:39:57.274168+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5PIZSXKFMF5","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5PIZSXKFMF533J7","created_at":"2026-05-18T12:31:28.150371+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5PIZSXK","created_at":"2026-05-18T12:31:28.150371+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":14,"sample":[{"citing_arxiv_id":"2502.04416","citing_title":"Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2505.15323","citing_title":"Improving LLM First-Token Predictions in Multiple-Choice Question Answering via Output Prefilling","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2506.12119","citing_title":"Mixture-of-Experts Can Surpass Dense LLMs Under Strictly Equal Resource","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17653","citing_title":"LLMForge: Multi-Backend Hardware-Aware Neural Architecture Search with Infinite-Head Attention for Edge Language Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2507.15640","citing_title":"Data Mixing Agent: Learning to Re-weight Domains for Continual Pre-training","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2510.18245","citing_title":"Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":128,"is_internal_anchor":true},{"citing_arxiv_id":"2601.00417","citing_title":"Deep Delta Learning","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2601.21349","citing_title":"L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2603.14360","citing_title":"M$^2$RNN: Non-Linear RNNs with Matrix-Valued States for Scalable Language Modeling","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12715","citing_title":"Scaling Laws for Mixture Pretraining Under Data Constraints","ref_index":57,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12529","citing_title":"BackFlush: Knowledge-Free Backdoor Detection and Elimination with Watermark Preservation in Large Language Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13595","citing_title":"Inducing Artificial Uncertainty in Language Models","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2110.08207","citing_title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2211.09085","citing_title":"Galactica: A Large Language Model for Science","ref_index":250,"is_internal_anchor":false},{"citing_arxiv_id":"2406.04093","citing_title":"Scaling and evaluating sparse autoencoders","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00539","citing_title":"AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00539","citing_title":"AGoQ: Activation and Gradient Quantization for Memory-Efficient Distributed Training of LLMs","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19015","citing_title":"FedProxy: Federated Fine-Tuning of LLMs via Proxy SLMs and Heterogeneity-Aware Fusion","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07963","citing_title":"Rethinking Data Mixing from the Perspective of Large Language Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17051","citing_title":"Efficient Task Adaptation in Large Language Models via Selective Parameter Optimization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17621","citing_title":"KnowledgeBerg: Evaluating Systematic Knowledge Coverage and Compositional Reasoning in Large Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19444","citing_title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","ref_index":197,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV","json":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV.json","graph_json":"https://pith.science/api/pith-number/M5PIZSXKFMF533J7KBP3U6RQJV/graph.json","events_json":"https://pith.science/api/pith-number/M5PIZSXKFMF533J7KBP3U6RQJV/events.json","paper":"https://pith.science/paper/M5PIZSXK"},"agent_actions":{"view_html":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV","download_json":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV.json","view_paper":"https://pith.science/paper/M5PIZSXK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.06209&json=true","fetch_graph":"https://pith.science/api/pith-number/M5PIZSXKFMF533J7KBP3U6RQJV/graph.json","fetch_events":"https://pith.science/api/pith-number/M5PIZSXKFMF533J7KBP3U6RQJV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV/action/storage_attestation","attest_author":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV/action/author_attestation","sign_citation":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV/action/citation_signature","submit_replication":"https://pith.science/pith/M5PIZSXKFMF533J7KBP3U6RQJV/action/replication_record"}},"created_at":"2026-05-18T00:39:57.274168+00:00","updated_at":"2026-05-18T00:39:57.274168+00:00"}