{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T2YJUGSAJ5F26VY6YH2T6JTHL6","short_pith_number":"pith:T2YJUGSA","schema_version":"1.0","canonical_sha256":"9eb09a1a404f4baf571ec1f53f26675fb683ff62c05768e65274df3fd36c3bc7","source":{"kind":"arxiv","id":"2401.07950","version":3},"attestation_state":"computed","paper":{"title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Zhang, Jie Tang, Kaiyu Yang, Sining Zhoubian, Yisong Yue, Yuxiao Dong, Zhengxiao Du, Zihan Wang, Ziniu Hu","submitted_at":"2024-01-15T20:22:21Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise in assisting scientific discovery. However, such applications are currently limited by LLMs' deficiencies in understanding intricate scientific concepts, deriving symbolic equations, and solving advanced numerical calculations. To bridge these gaps, we introduce SciInstruct, a suite of scientific instructions for training scientific language models capable of college-level scientific reasoning. Central to our approach is a novel self-reflective instruction annotation framework to address the data scarcity challenge in the science domain. This fra"},"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":"2401.07950","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-15T20:22:21Z","cross_cats_sorted":[],"title_canon_sha256":"540e7ac159dfafe7fa7ad09a521b5817d75949a175285dcbd8d336aed51941b6","abstract_canon_sha256":"b80ff457b87a8819e739e27b194363639af6b5dc0f67495755bf51ed325e81f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:36:38.034704Z","signature_b64":"C8h1ugCwyF2oIb0MlUmi8xeNbUyekzky4Y9d6H66j8Jzn/rrh83tdFJAN4Awa+3kqG+TLNoDV5ljJgEMdd3QAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9eb09a1a404f4baf571ec1f53f26675fb683ff62c05768e65274df3fd36c3bc7","last_reissued_at":"2026-07-05T09:36:38.032889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:36:38.032889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dan Zhang, Jie Tang, Kaiyu Yang, Sining Zhoubian, Yisong Yue, Yuxiao Dong, Zhengxiao Du, Zihan Wang, Ziniu Hu","submitted_at":"2024-01-15T20:22:21Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise in assisting scientific discovery. However, such applications are currently limited by LLMs' deficiencies in understanding intricate scientific concepts, deriving symbolic equations, and solving advanced numerical calculations. To bridge these gaps, we introduce SciInstruct, a suite of scientific instructions for training scientific language models capable of college-level scientific reasoning. Central to our approach is a novel self-reflective instruction annotation framework to address the data scarcity challenge in the science domain. This fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.07950","kind":"arxiv","version":3},"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/2401.07950/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":"2401.07950","created_at":"2026-07-05T09:36:38.034226+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.07950v3","created_at":"2026-07-05T09:36:38.034226+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.07950","created_at":"2026-07-05T09:36:38.034226+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2YJUGSAJ5F2","created_at":"2026-07-05T09:36:38.034226+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2YJUGSAJ5F26VY6","created_at":"2026-07-05T09:36:38.034226+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2YJUGSA","created_at":"2026-07-05T09:36:38.034226+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07712","citing_title":"MatMind: A Structure-Activity Knowledge-Driven Generative Foundation Model for Materials Science","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27351","citing_title":"Heterogeneous Scientific Foundation Model Collaboration","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6","json":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6.json","graph_json":"https://pith.science/api/pith-number/T2YJUGSAJ5F26VY6YH2T6JTHL6/graph.json","events_json":"https://pith.science/api/pith-number/T2YJUGSAJ5F26VY6YH2T6JTHL6/events.json","paper":"https://pith.science/paper/T2YJUGSA"},"agent_actions":{"view_html":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6","download_json":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6.json","view_paper":"https://pith.science/paper/T2YJUGSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.07950&json=true","fetch_graph":"https://pith.science/api/pith-number/T2YJUGSAJ5F26VY6YH2T6JTHL6/graph.json","fetch_events":"https://pith.science/api/pith-number/T2YJUGSAJ5F26VY6YH2T6JTHL6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6/action/storage_attestation","attest_author":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6/action/author_attestation","sign_citation":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6/action/citation_signature","submit_replication":"https://pith.science/pith/T2YJUGSAJ5F26VY6YH2T6JTHL6/action/replication_record"}},"created_at":"2026-07-05T09:36:38.034226+00:00","updated_at":"2026-07-05T09:36:38.034226+00:00"}