{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FIAV5MASQEPIYAQVX6HKNWZRXK","short_pith_number":"pith:FIAV5MAS","schema_version":"1.0","canonical_sha256":"2a015eb012811e8c0215bf8ea6db31baa98198699cd0174141961777c10bc82b","source":{"kind":"arxiv","id":"2403.19154","version":3},"attestation_state":"computed","paper":{"title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chinmaya Andukuri, Jan-Philipp Fr\\\"anken, Noah D. Goodman, Tobias Gerstenberg","submitted_at":"2024-03-28T05:35:22Z","abstract_excerpt":"When prompting language models to complete a task, users often leave important aspects unsaid. While asking questions could resolve this ambiguity (GATE; Li et al., 2023), models often struggle to ask good questions. We explore a language model's ability to self-improve (STaR; Zelikman et al., 2022) by rewarding the model for generating useful questions-a simple method we dub STaR-GATE. We generate a synthetic dataset of 25,500 unique persona-task prompts to simulate conversations between a pretrained language model-the Questioner-and a Roleplayer whose preferences are unknown to the Questione"},"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":"2403.19154","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-28T05:35:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a8a75bace478d6b3847ed6e857335c54d82baf89f319d89afa20a531b66139f1","abstract_canon_sha256":"8447891239e5868ee3d2089ff2a3832751f9aa2ce89c8b3c4b2be3a6a856663c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:21.196761Z","signature_b64":"3a33O997R46ig2wUxThuQFfdsBFRqzZEGadb3luIB/NlClVmFChedo1n4wBlVHRGVvC6jX9SqKh0eJnm2Du9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a015eb012811e8c0215bf8ea6db31baa98198699cd0174141961777c10bc82b","last_reissued_at":"2026-07-05T08:53:21.196280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:21.196280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STaR-GATE: Teaching Language Models to Ask Clarifying Questions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chinmaya Andukuri, Jan-Philipp Fr\\\"anken, Noah D. Goodman, Tobias Gerstenberg","submitted_at":"2024-03-28T05:35:22Z","abstract_excerpt":"When prompting language models to complete a task, users often leave important aspects unsaid. While asking questions could resolve this ambiguity (GATE; Li et al., 2023), models often struggle to ask good questions. We explore a language model's ability to self-improve (STaR; Zelikman et al., 2022) by rewarding the model for generating useful questions-a simple method we dub STaR-GATE. We generate a synthetic dataset of 25,500 unique persona-task prompts to simulate conversations between a pretrained language model-the Questioner-and a Roleplayer whose preferences are unknown to the Questione"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19154","kind":"arxiv","version":3},"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/2403.19154/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":"2403.19154","created_at":"2026-07-05T08:53:21.196341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19154v3","created_at":"2026-07-05T08:53:21.196341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19154","created_at":"2026-07-05T08:53:21.196341+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIAV5MASQEPI","created_at":"2026-07-05T08:53:21.196341+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIAV5MASQEPIYAQV","created_at":"2026-07-05T08:53:21.196341+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIAV5MAS","created_at":"2026-07-05T08:53:21.196341+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12587","citing_title":"Strategic Decision Support for AI Agents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03110","citing_title":"Coherence Maximization Improves Pluralistic Alignment","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01182","citing_title":"CA-BED: Conversation-Aware Bayesian Experimental Design","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06869","citing_title":"Evidence-Based Intelligent Diagnostic and Therapeutic Visualization System with Large Language Models: Multi-Turn Interaction and Multimodal Treatment Plan Generation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2409.00557","citing_title":"Learning to Ask: When LLM Agents Meet Unclear Instruction","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02315","citing_title":"Beyond the Assistant Turn: User Turn Generation as a Probe of Interaction Awareness in Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11240","citing_title":"When to Ask a Question: Understanding Communication Strategies in Generative AI Tools","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09808","citing_title":"Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09228","citing_title":"ProactBench: Beyond What The User Asked For","ref_index":94,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05386","citing_title":"BALAR : A Bayesian Agentic Loop for Active Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21827","citing_title":"Alignment has a Fantasia Problem","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK","json":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK.json","graph_json":"https://pith.science/api/pith-number/FIAV5MASQEPIYAQVX6HKNWZRXK/graph.json","events_json":"https://pith.science/api/pith-number/FIAV5MASQEPIYAQVX6HKNWZRXK/events.json","paper":"https://pith.science/paper/FIAV5MAS"},"agent_actions":{"view_html":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK","download_json":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK.json","view_paper":"https://pith.science/paper/FIAV5MAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19154&json=true","fetch_graph":"https://pith.science/api/pith-number/FIAV5MASQEPIYAQVX6HKNWZRXK/graph.json","fetch_events":"https://pith.science/api/pith-number/FIAV5MASQEPIYAQVX6HKNWZRXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK/action/storage_attestation","attest_author":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK/action/author_attestation","sign_citation":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK/action/citation_signature","submit_replication":"https://pith.science/pith/FIAV5MASQEPIYAQVX6HKNWZRXK/action/replication_record"}},"created_at":"2026-07-05T08:53:21.196341+00:00","updated_at":"2026-07-05T08:53:21.196341+00:00"}