{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:62TAP2JZCHZGC62TGLIW4I2QVS","short_pith_number":"pith:62TAP2JZ","schema_version":"1.0","canonical_sha256":"f6a607e93911f2617b5332d16e2350aca0e3d4725bbfd0ccbfd1e57671e3e686","source":{"kind":"arxiv","id":"2503.04625","version":2},"attestation_state":"computed","paper":{"title":"START: Self-taught Reasoner with Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beichen Zhang, Binyuan Hui, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jiaxi Yang, Junyang Lin, Mingfeng Xue, Xiang Wang, Zhenru Zhang","submitted_at":"2025-03-06T17:11:51Z","abstract_excerpt":"Large reasoning models (LRMs) like OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable capabilities in complex reasoning tasks through the utilization of long Chain-of-thought (CoT). However, these models often suffer from hallucinations and inefficiencies due to their reliance solely on internal reasoning processes. In this paper, we introduce START (Self-Taught Reasoner with Tools), a novel tool-integrated long CoT reasoning LLM that significantly enhances reasoning capabilities by leveraging external tools. Through code execution, START is capable of performing complex computations, self"},"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":"2503.04625","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-06T17:11:51Z","cross_cats_sorted":[],"title_canon_sha256":"9622c54c0d6b70569be56a5e6964c1ee48fb1be320a65e9619f3cf47fa746dca","abstract_canon_sha256":"e4b55435e76ac442dad971e5377563cc0dc4bc3f35377067834dd69d20fc07ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:17.059532Z","signature_b64":"TF9mocPcf4FX7sH3YhueMRS0B69A6PXaKletSkaqq4CFWeGUiXMwTEsMpjPxyD6hW2nYIbhUQm010lqkO8lXCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6a607e93911f2617b5332d16e2350aca0e3d4725bbfd0ccbfd1e57671e3e686","last_reissued_at":"2026-07-05T10:26:17.058936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:17.058936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"START: Self-taught Reasoner with Tools","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beichen Zhang, Binyuan Hui, Bowen Yu, Chengpeng Li, Dayiheng Liu, Jiaxi Yang, Junyang Lin, Mingfeng Xue, Xiang Wang, Zhenru Zhang","submitted_at":"2025-03-06T17:11:51Z","abstract_excerpt":"Large reasoning models (LRMs) like OpenAI-o1 and DeepSeek-R1 have demonstrated remarkable capabilities in complex reasoning tasks through the utilization of long Chain-of-thought (CoT). However, these models often suffer from hallucinations and inefficiencies due to their reliance solely on internal reasoning processes. In this paper, we introduce START (Self-Taught Reasoner with Tools), a novel tool-integrated long CoT reasoning LLM that significantly enhances reasoning capabilities by leveraging external tools. Through code execution, START is capable of performing complex computations, self"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04625","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/2503.04625/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":"2503.04625","created_at":"2026-07-05T10:26:17.059006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04625v2","created_at":"2026-07-05T10:26:17.059006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04625","created_at":"2026-07-05T10:26:17.059006+00:00"},{"alias_kind":"pith_short_12","alias_value":"62TAP2JZCHZG","created_at":"2026-07-05T10:26:17.059006+00:00"},{"alias_kind":"pith_short_16","alias_value":"62TAP2JZCHZGC62T","created_at":"2026-07-05T10:26:17.059006+00:00"},{"alias_kind":"pith_short_8","alias_value":"62TAP2JZ","created_at":"2026-07-05T10:26:17.059006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"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":133,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":206,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS","json":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS.json","graph_json":"https://pith.science/api/pith-number/62TAP2JZCHZGC62TGLIW4I2QVS/graph.json","events_json":"https://pith.science/api/pith-number/62TAP2JZCHZGC62TGLIW4I2QVS/events.json","paper":"https://pith.science/paper/62TAP2JZ"},"agent_actions":{"view_html":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS","download_json":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS.json","view_paper":"https://pith.science/paper/62TAP2JZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04625&json=true","fetch_graph":"https://pith.science/api/pith-number/62TAP2JZCHZGC62TGLIW4I2QVS/graph.json","fetch_events":"https://pith.science/api/pith-number/62TAP2JZCHZGC62TGLIW4I2QVS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS/action/storage_attestation","attest_author":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS/action/author_attestation","sign_citation":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS/action/citation_signature","submit_replication":"https://pith.science/pith/62TAP2JZCHZGC62TGLIW4I2QVS/action/replication_record"}},"created_at":"2026-07-05T10:26:17.059006+00:00","updated_at":"2026-07-05T10:26:17.059006+00:00"}