{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:F5QPJXQRBVVU2FWO73XG6FWKGE","short_pith_number":"pith:F5QPJXQR","schema_version":"1.0","canonical_sha256":"2f60f4de110d6b4d16cefeee6f16ca311d0281ef5e850a9ec45dd2c0cb169242","source":{"kind":"arxiv","id":"2411.14121","version":1},"attestation_state":"computed","paper":{"title":"Learning from \"Silly\" Questions Improves Large Language Models, But Only Slightly","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Han Yu, Jindong Wang, Shudong Liu, Takahiro Shinozaki, Tingyuan Zhu, Yidong Wang","submitted_at":"2024-11-21T13:45:40Z","abstract_excerpt":"Constructing high-quality Supervised Fine-Tuning (SFT) datasets is critical for the training of large language models (LLMs). Recent studies have shown that using data from a specific source, Ruozhiba, a Chinese website where users ask \"silly\" questions to better understand certain topics, can lead to better fine-tuning performance. This paper aims to explore some hidden factors: the potential interpretations of its success and a large-scale evaluation of the performance. First, we leverage GPT-4 to analyze the successful cases of Ruozhiba questions from the perspective of education, psycholog"},"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":"2411.14121","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T13:45:40Z","cross_cats_sorted":[],"title_canon_sha256":"3ceea373f5ca5404c4e0fc12560ad12b8a37f1014343fd258d06f7ebdff10951","abstract_canon_sha256":"b979d4ba93aee2d2117340770bbaeeafe1a3f04f8d763ae62f65c738104e0f94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:41.965408Z","signature_b64":"ZCZv4vy/Nxa4wVUpgVKak2f5n7i/UkRkTC7Bk/DzQ63OHKz7W0BlqbcpFWaLTbS/HE7hMWIh/AjSDSOSRJUXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f60f4de110d6b4d16cefeee6f16ca311d0281ef5e850a9ec45dd2c0cb169242","last_reissued_at":"2026-07-05T09:38:41.964887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:41.964887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning from \"Silly\" Questions Improves Large Language Models, But Only Slightly","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Derek F. Wong, Han Yu, Jindong Wang, Shudong Liu, Takahiro Shinozaki, Tingyuan Zhu, Yidong Wang","submitted_at":"2024-11-21T13:45:40Z","abstract_excerpt":"Constructing high-quality Supervised Fine-Tuning (SFT) datasets is critical for the training of large language models (LLMs). Recent studies have shown that using data from a specific source, Ruozhiba, a Chinese website where users ask \"silly\" questions to better understand certain topics, can lead to better fine-tuning performance. This paper aims to explore some hidden factors: the potential interpretations of its success and a large-scale evaluation of the performance. First, we leverage GPT-4 to analyze the successful cases of Ruozhiba questions from the perspective of education, psycholog"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14121","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/2411.14121/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":"2411.14121","created_at":"2026-07-05T09:38:41.964948+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.14121v1","created_at":"2026-07-05T09:38:41.964948+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14121","created_at":"2026-07-05T09:38:41.964948+00:00"},{"alias_kind":"pith_short_12","alias_value":"F5QPJXQRBVVU","created_at":"2026-07-05T09:38:41.964948+00:00"},{"alias_kind":"pith_short_16","alias_value":"F5QPJXQRBVVU2FWO","created_at":"2026-07-05T09:38:41.964948+00:00"},{"alias_kind":"pith_short_8","alias_value":"F5QPJXQR","created_at":"2026-07-05T09:38:41.964948+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/F5QPJXQRBVVU2FWO73XG6FWKGE","json":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE.json","graph_json":"https://pith.science/api/pith-number/F5QPJXQRBVVU2FWO73XG6FWKGE/graph.json","events_json":"https://pith.science/api/pith-number/F5QPJXQRBVVU2FWO73XG6FWKGE/events.json","paper":"https://pith.science/paper/F5QPJXQR"},"agent_actions":{"view_html":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE","download_json":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE.json","view_paper":"https://pith.science/paper/F5QPJXQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.14121&json=true","fetch_graph":"https://pith.science/api/pith-number/F5QPJXQRBVVU2FWO73XG6FWKGE/graph.json","fetch_events":"https://pith.science/api/pith-number/F5QPJXQRBVVU2FWO73XG6FWKGE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE/action/storage_attestation","attest_author":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE/action/author_attestation","sign_citation":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE/action/citation_signature","submit_replication":"https://pith.science/pith/F5QPJXQRBVVU2FWO73XG6FWKGE/action/replication_record"}},"created_at":"2026-07-05T09:38:41.964948+00:00","updated_at":"2026-07-05T09:38:41.964948+00:00"}