{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPKDJ6D2XV3FCA2EN57OCOLCHJ","short_pith_number":"pith:XPKDJ6D2","schema_version":"1.0","canonical_sha256":"bbd434f87abd765103446f7ee139623a7a7910eb660b76eafe372e5484a8a771","source":{"kind":"arxiv","id":"2501.15587","version":2},"attestation_state":"computed","paper":{"title":"SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chao Qu, Dakuan Lu, Rui Xu, Tianchu Yao, Wei Chu, Xiaoyu Tan, Yinghui Xu, Yuan Qi","submitted_at":"2025-01-26T16:26:38Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) exemplified by the impressive mathematical and scientific reasoning capabilities of the o1 model have spotlighted the critical importance of high-quality training data in advancing LLM performance across STEM disciplines. While the mathematics community has benefited from a growing body of curated datasets, the scientific domain at the higher education level has long suffered from a scarcity of comparable resources. To address this gap, we present SCP-116K, a new large-scale dataset of 116,756 high-quality problem-solution pairs, automatical"},"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":"2501.15587","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-26T16:26:38Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"f84d091ae11186f490ea69e3dcacf198c8e5b94099c9f593cddfd7cd0373c956","abstract_canon_sha256":"bcb89427f0424e393d142cd455e6bb748794512cb4fb818698f6e897bc8be11e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:24.207553Z","signature_b64":"WG5rWIopAdtCOIu9BmByREQsqOhD4oi1+tBLQ1l37t3MtQyf08a+jDrU7Ni8XlM344zarnKmF8lqcBgMwlk9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbd434f87abd765103446f7ee139623a7a7910eb660b76eafe372e5484a8a771","last_reissued_at":"2026-07-05T11:58:24.207084Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:24.207084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Chao Qu, Dakuan Lu, Rui Xu, Tianchu Yao, Wei Chu, Xiaoyu Tan, Yinghui Xu, Yuan Qi","submitted_at":"2025-01-26T16:26:38Z","abstract_excerpt":"Recent breakthroughs in large language models (LLMs) exemplified by the impressive mathematical and scientific reasoning capabilities of the o1 model have spotlighted the critical importance of high-quality training data in advancing LLM performance across STEM disciplines. While the mathematics community has benefited from a growing body of curated datasets, the scientific domain at the higher education level has long suffered from a scarcity of comparable resources. To address this gap, we present SCP-116K, a new large-scale dataset of 116,756 high-quality problem-solution pairs, automatical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15587","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/2501.15587/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":"2501.15587","created_at":"2026-07-05T11:58:24.207141+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15587v2","created_at":"2026-07-05T11:58:24.207141+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15587","created_at":"2026-07-05T11:58:24.207141+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPKDJ6D2XV3F","created_at":"2026-07-05T11:58:24.207141+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPKDJ6D2XV3FCA2E","created_at":"2026-07-05T11:58:24.207141+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPKDJ6D2","created_at":"2026-07-05T11:58:24.207141+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.14184","citing_title":"Deeper Thought, Weaker Aim: Understanding and Mitigating Perceptual Impairment during Reasoning in Multimodal Large Language Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2507.17746","citing_title":"Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domains","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ","json":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ.json","graph_json":"https://pith.science/api/pith-number/XPKDJ6D2XV3FCA2EN57OCOLCHJ/graph.json","events_json":"https://pith.science/api/pith-number/XPKDJ6D2XV3FCA2EN57OCOLCHJ/events.json","paper":"https://pith.science/paper/XPKDJ6D2"},"agent_actions":{"view_html":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ","download_json":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ.json","view_paper":"https://pith.science/paper/XPKDJ6D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15587&json=true","fetch_graph":"https://pith.science/api/pith-number/XPKDJ6D2XV3FCA2EN57OCOLCHJ/graph.json","fetch_events":"https://pith.science/api/pith-number/XPKDJ6D2XV3FCA2EN57OCOLCHJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ/action/storage_attestation","attest_author":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ/action/author_attestation","sign_citation":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ/action/citation_signature","submit_replication":"https://pith.science/pith/XPKDJ6D2XV3FCA2EN57OCOLCHJ/action/replication_record"}},"created_at":"2026-07-05T11:58:24.207141+00:00","updated_at":"2026-07-05T11:58:24.207141+00:00"}