{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPKDJ6D2XV3FCA2EN57OCOLCHJ","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":"bcb89427f0424e393d142cd455e6bb748794512cb4fb818698f6e897bc8be11e","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-26T16:26:38Z","title_canon_sha256":"f84d091ae11186f490ea69e3dcacf198c8e5b94099c9f593cddfd7cd0373c956"},"schema_version":"1.0","source":{"id":"2501.15587","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15587","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15587v2","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15587","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"pith_short_12","alias_value":"XPKDJ6D2XV3F","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"pith_short_16","alias_value":"XPKDJ6D2XV3FCA2E","created_at":"2026-07-05T11:58:24Z"},{"alias_kind":"pith_short_8","alias_value":"XPKDJ6D2","created_at":"2026-07-05T11:58:24Z"}],"graph_snapshots":[{"event_id":"sha256:b8ef9b37fea573ed3f2c727661cfa3b6d5576c32362fdbb68fcf8f2fabe7cbd2","target":"graph","created_at":"2026-07-05T11:58:24Z","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/2501.15587/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chao Qu, Dakuan Lu, Rui Xu, Tianchu Yao, Wei Chu, Xiaoyu Tan, Yinghui Xu, Yuan Qi","cross_cats":["cs.AI","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-26T16:26:38Z","title":"SCP-116K: A High-Quality Problem-Solution Dataset and a Generalized Pipeline for Automated Extraction in the Higher Education Science Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15587","kind":"arxiv","version":2},"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":"sha256:29f439af8e3938f48c21a7efe275da6401c9bd4e23f582b10e062f036cd7f0a3","target":"record","created_at":"2026-07-05T11:58:24Z","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":"bcb89427f0424e393d142cd455e6bb748794512cb4fb818698f6e897bc8be11e","cross_cats_sorted":["cs.AI","cs.IR"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-26T16:26:38Z","title_canon_sha256":"f84d091ae11186f490ea69e3dcacf198c8e5b94099c9f593cddfd7cd0373c956"},"schema_version":"1.0","source":{"id":"2501.15587","kind":"arxiv","version":2}},"canonical_sha256":"bbd434f87abd765103446f7ee139623a7a7910eb660b76eafe372e5484a8a771","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbd434f87abd765103446f7ee139623a7a7910eb660b76eafe372e5484a8a771","first_computed_at":"2026-07-05T11:58:24.207084Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:24.207084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WG5rWIopAdtCOIu9BmByREQsqOhD4oi1+tBLQ1l37t3MtQyf08a+jDrU7Ni8XlM344zarnKmF8lqcBgMwlk9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:24.207553Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15587","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29f439af8e3938f48c21a7efe275da6401c9bd4e23f582b10e062f036cd7f0a3","sha256:b8ef9b37fea573ed3f2c727661cfa3b6d5576c32362fdbb68fcf8f2fabe7cbd2"],"state_sha256":"4d281fbd7f5254a14d744feba1686751b2ecdda7d9d80f355af55736f5a9a948"}