{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V4AUPFAZFPEHNZLY4FVL6KMNNV","short_pith_number":"pith:V4AUPFAZ","schema_version":"1.0","canonical_sha256":"af014794192bc876e578e16abf298d6d719d316051c59e31675868c276497f04","source":{"kind":"arxiv","id":"2402.11451","version":2},"attestation_state":"computed","paper":{"title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Hany Awadalla, Junheng Hao, Liangming Pan, Ruochen Xu, Shuohang Wang, Weizhu Chen, Yixin Cao, Yubo Ma, Yujiu Yang, Zhibin Gou","submitted_at":"2024-02-18T04:19:44Z","abstract_excerpt":"Scientific reasoning poses an excessive challenge for even the most advanced Large Language Models (LLMs). To make this task more practical and solvable for LLMs, we introduce a new task setting named tool-augmented scientific reasoning. This setting supplements LLMs with scalable toolsets, and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user. To facilitate the research of such setting, we construct a tool-augmented training corpus named MathFunc which encompasses over 30,000 samples and roughly 6,000 tools. Building on MathFunc, we develop SciAgent to retr"},"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":"2402.11451","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-18T04:19:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"82d6c206ba2f9d1e0ae912467172e73d368eb3908a588d20e26172f67920eb36","abstract_canon_sha256":"d122960012a23771e2d38972c273d02c90f34019efaae74869787d3a949ed2b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:29.178212Z","signature_b64":"9ACYg0t9tfA+uhT8lRssv8HgBSyBf0GVgYaoNOPGEkJJshJBl/U8D4iWE2cn9gnz2unqdc4LfybTQWoPhEVOCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af014794192bc876e578e16abf298d6d719d316051c59e31675868c276497f04","last_reissued_at":"2026-07-05T07:47:29.177736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:29.177736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SciAgent: Tool-augmented Language Models for Scientific Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aixin Sun, Hany Awadalla, Junheng Hao, Liangming Pan, Ruochen Xu, Shuohang Wang, Weizhu Chen, Yixin Cao, Yubo Ma, Yujiu Yang, Zhibin Gou","submitted_at":"2024-02-18T04:19:44Z","abstract_excerpt":"Scientific reasoning poses an excessive challenge for even the most advanced Large Language Models (LLMs). To make this task more practical and solvable for LLMs, we introduce a new task setting named tool-augmented scientific reasoning. This setting supplements LLMs with scalable toolsets, and shifts the focus from pursuing an omniscient problem solver to a proficient tool-user. To facilitate the research of such setting, we construct a tool-augmented training corpus named MathFunc which encompasses over 30,000 samples and roughly 6,000 tools. Building on MathFunc, we develop SciAgent to retr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11451","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/2402.11451/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":"2402.11451","created_at":"2026-07-05T07:47:29.177791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11451v2","created_at":"2026-07-05T07:47:29.177791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11451","created_at":"2026-07-05T07:47:29.177791+00:00"},{"alias_kind":"pith_short_12","alias_value":"V4AUPFAZFPEH","created_at":"2026-07-05T07:47:29.177791+00:00"},{"alias_kind":"pith_short_16","alias_value":"V4AUPFAZFPEHNZLY","created_at":"2026-07-05T07:47:29.177791+00:00"},{"alias_kind":"pith_short_8","alias_value":"V4AUPFAZ","created_at":"2026-07-05T07:47:29.177791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07850","citing_title":"PDE-Agents: An LLM-Orchestrated Multi-Agent Framework for Automated Finite Element Simulations with Knowledge Graph-Augmented Reasoning","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17554","citing_title":"Evaluating Deep Research Agents on Expert Consulting Work: A Benchmark with Verifiers, Rubrics, and Cognitive Traps","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18630","citing_title":"SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26645","citing_title":"SciHorizon-DataEVA: An Agentic System for AI-Readiness Evaluation of Heterogeneous Scientific Data","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV","json":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV.json","graph_json":"https://pith.science/api/pith-number/V4AUPFAZFPEHNZLY4FVL6KMNNV/graph.json","events_json":"https://pith.science/api/pith-number/V4AUPFAZFPEHNZLY4FVL6KMNNV/events.json","paper":"https://pith.science/paper/V4AUPFAZ"},"agent_actions":{"view_html":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV","download_json":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV.json","view_paper":"https://pith.science/paper/V4AUPFAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11451&json=true","fetch_graph":"https://pith.science/api/pith-number/V4AUPFAZFPEHNZLY4FVL6KMNNV/graph.json","fetch_events":"https://pith.science/api/pith-number/V4AUPFAZFPEHNZLY4FVL6KMNNV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV/action/storage_attestation","attest_author":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV/action/author_attestation","sign_citation":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV/action/citation_signature","submit_replication":"https://pith.science/pith/V4AUPFAZFPEHNZLY4FVL6KMNNV/action/replication_record"}},"created_at":"2026-07-05T07:47:29.177791+00:00","updated_at":"2026-07-05T07:47:29.177791+00:00"}