{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F5QPJXQRBVVU2FWO73XG6FWKGE","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b979d4ba93aee2d2117340770bbaeeafe1a3f04f8d763ae62f65c738104e0f94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T13:45:40Z","title_canon_sha256":"3ceea373f5ca5404c4e0fc12560ad12b8a37f1014343fd258d06f7ebdff10951"},"schema_version":"1.0","source":{"id":"2411.14121","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14121","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14121v1","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14121","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_12","alias_value":"F5QPJXQRBVVU","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_16","alias_value":"F5QPJXQRBVVU2FWO","created_at":"2026-07-05T09:38:41Z"},{"alias_kind":"pith_short_8","alias_value":"F5QPJXQR","created_at":"2026-07-05T09:38:41Z"}],"graph_snapshots":[{"event_id":"sha256:18bff309c63387ed4ed62514a03aa868e3404e8658f6da5a008905a18f43f77c","target":"graph","created_at":"2026-07-05T09:38:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2411.14121/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Derek F. Wong, Han Yu, Jindong Wang, Shudong Liu, Takahiro Shinozaki, Tingyuan Zhu, Yidong Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T13:45:40Z","title":"Learning from \"Silly\" Questions Improves Large Language Models, But Only Slightly"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14121","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6cc48b29567c43037278677d376bea3ce26a048b37d19981a94c992c43d77c33","target":"record","created_at":"2026-07-05T09:38:41Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b979d4ba93aee2d2117340770bbaeeafe1a3f04f8d763ae62f65c738104e0f94","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-21T13:45:40Z","title_canon_sha256":"3ceea373f5ca5404c4e0fc12560ad12b8a37f1014343fd258d06f7ebdff10951"},"schema_version":"1.0","source":{"id":"2411.14121","kind":"arxiv","version":1}},"canonical_sha256":"2f60f4de110d6b4d16cefeee6f16ca311d0281ef5e850a9ec45dd2c0cb169242","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f60f4de110d6b4d16cefeee6f16ca311d0281ef5e850a9ec45dd2c0cb169242","first_computed_at":"2026-07-05T09:38:41.964887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:41.964887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZCZv4vy/Nxa4wVUpgVKak2f5n7i/UkRkTC7Bk/DzQ63OHKz7W0BlqbcpFWaLTbS/HE7hMWIh/AjSDSOSRJUXBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:41.965408Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14121","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cc48b29567c43037278677d376bea3ce26a048b37d19981a94c992c43d77c33","sha256:18bff309c63387ed4ed62514a03aa868e3404e8658f6da5a008905a18f43f77c"],"state_sha256":"f024f28e4e9f9f7a49ab045d60630ffdf4018920491fec000dc5f7af5a364be1"}