{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DQO53UGG4GBSIIKLR7HE4RCLEC","short_pith_number":"pith:DQO53UGG","schema_version":"1.0","canonical_sha256":"1c1dddd0c6e18324214b8fce4e444b20a080d449df9591813d3ec9eac913b5a9","source":{"kind":"arxiv","id":"2410.18693","version":2},"attestation_state":"computed","paper":{"title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Juntao Li, Min Zhang, Qiaoming Zhu, Xiaobo Liang, Xinyu Shi, Yuyang Ding, Zhaopeng Tu","submitted_at":"2024-10-24T12:42:04Z","abstract_excerpt":"Improving the mathematical reasoning capabilities of Large Language Models (LLMs) is critical for advancing artificial intelligence. However, access to extensive, diverse, and high-quality reasoning datasets remains a significant challenge, particularly for the open-source community. In this paper, we propose ScaleQuest, a novel, scalable, and cost-effective data synthesis method that enables the generation of large-scale mathematical reasoning datasets using lightweight 7B-scale models. ScaleQuest introduces a two-stage question-tuning process comprising Question Fine-Tuning (QFT) and Questio"},"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":"2410.18693","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-24T12:42:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13c80f376e9ffd5fad763a83df55ff80863ef1f59039f33f63f28ac9f8d19953","abstract_canon_sha256":"34569fc5dc0535c3a5f7ef12b98cc52b5535aedb81dbffdcaa89de9df80bdf62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:01.952410Z","signature_b64":"QR8XAJ5Pq6ZWPhoAQoFATdEk8Bvniwk48yTM0lI5g8QEVJUvc4JxlQxa7bF63bIndWsUuFLQzVYQzl3Ft3ikDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c1dddd0c6e18324214b8fce4e444b20a080d449df9591813d3ec9eac913b5a9","last_reissued_at":"2026-07-05T11:10:01.951915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:01.951915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unleashing LLM Reasoning Capability via Scalable Question Synthesis from Scratch","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Juntao Li, Min Zhang, Qiaoming Zhu, Xiaobo Liang, Xinyu Shi, Yuyang Ding, Zhaopeng Tu","submitted_at":"2024-10-24T12:42:04Z","abstract_excerpt":"Improving the mathematical reasoning capabilities of Large Language Models (LLMs) is critical for advancing artificial intelligence. However, access to extensive, diverse, and high-quality reasoning datasets remains a significant challenge, particularly for the open-source community. In this paper, we propose ScaleQuest, a novel, scalable, and cost-effective data synthesis method that enables the generation of large-scale mathematical reasoning datasets using lightweight 7B-scale models. ScaleQuest introduces a two-stage question-tuning process comprising Question Fine-Tuning (QFT) and Questio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18693","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.18693/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":"2410.18693","created_at":"2026-07-05T11:10:01.951975+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18693v2","created_at":"2026-07-05T11:10:01.951975+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18693","created_at":"2026-07-05T11:10:01.951975+00:00"},{"alias_kind":"pith_short_12","alias_value":"DQO53UGG4GBS","created_at":"2026-07-05T11:10:01.951975+00:00"},{"alias_kind":"pith_short_16","alias_value":"DQO53UGG4GBSIIKL","created_at":"2026-07-05T11:10:01.951975+00:00"},{"alias_kind":"pith_short_8","alias_value":"DQO53UGG","created_at":"2026-07-05T11:10:01.951975+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC","json":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC.json","graph_json":"https://pith.science/api/pith-number/DQO53UGG4GBSIIKLR7HE4RCLEC/graph.json","events_json":"https://pith.science/api/pith-number/DQO53UGG4GBSIIKLR7HE4RCLEC/events.json","paper":"https://pith.science/paper/DQO53UGG"},"agent_actions":{"view_html":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC","download_json":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC.json","view_paper":"https://pith.science/paper/DQO53UGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18693&json=true","fetch_graph":"https://pith.science/api/pith-number/DQO53UGG4GBSIIKLR7HE4RCLEC/graph.json","fetch_events":"https://pith.science/api/pith-number/DQO53UGG4GBSIIKLR7HE4RCLEC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC/action/storage_attestation","attest_author":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC/action/author_attestation","sign_citation":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC/action/citation_signature","submit_replication":"https://pith.science/pith/DQO53UGG4GBSIIKLR7HE4RCLEC/action/replication_record"}},"created_at":"2026-07-05T11:10:01.951975+00:00","updated_at":"2026-07-05T11:10:01.951975+00:00"}