{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:F6OZSZV4USXUQPIS23L7JJX42W","short_pith_number":"pith:F6OZSZV4","schema_version":"1.0","canonical_sha256":"2f9d9966bca4af483d12d6d7f4a6fcd5beb2ff3d55bf765fb09dfbee7473d6e2","source":{"kind":"arxiv","id":"2305.14318","version":3},"attestation_state":"computed","paper":{"title":"CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Qian, Chi Han, Heng Ji, Yi R. Fung, Yujia Qin, Zhiyuan Liu","submitted_at":"2023-05-23T17:51:52Z","abstract_excerpt":"Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math compet"},"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":"2305.14318","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T17:51:52Z","cross_cats_sorted":[],"title_canon_sha256":"35a2216a5c8eac060d966a50e5ef206198f14154b946a1869fde5ecdda0220d6","abstract_canon_sha256":"aeb9370f1cb7d81a22f7626c8da8744c402c78c1cb4f778cdb1aa67d3b6b7605"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:54.835123Z","signature_b64":"eVxwbZWmEeoYEfKo8/pRFgIbWIA+RyVyostIBETHvKX7hQKQbFYduy8YpKgVGSmHy/wJAmBdcTvWUp5QEoD3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f9d9966bca4af483d12d6d7f4a6fcd5beb2ff3d55bf765fb09dfbee7473d6e2","last_reissued_at":"2026-07-05T08:34:54.834689Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:54.834689Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CREATOR: Tool Creation for Disentangling Abstract and Concrete Reasoning of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Qian, Chi Han, Heng Ji, Yi R. Fung, Yujia Qin, Zhiyuan Liu","submitted_at":"2023-05-23T17:51:52Z","abstract_excerpt":"Large Language Models (LLMs) have made significant progress in utilizing tools, but their ability is limited by API availability and the instability of implicit reasoning, particularly when both planning and execution are involved. To overcome these limitations, we propose CREATOR, a novel framework that enables LLMs to create their own tools using documentation and code realization. CREATOR disentangles abstract tool creation and concrete decision execution, resulting in improved performance. We evaluate CREATOR on MATH and TabMWP benchmarks, respectively consisting of challenging math compet"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14318","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/2305.14318/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":"2305.14318","created_at":"2026-07-05T08:34:54.834748+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14318v3","created_at":"2026-07-05T08:34:54.834748+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14318","created_at":"2026-07-05T08:34:54.834748+00:00"},{"alias_kind":"pith_short_12","alias_value":"F6OZSZV4USXU","created_at":"2026-07-05T08:34:54.834748+00:00"},{"alias_kind":"pith_short_16","alias_value":"F6OZSZV4USXUQPIS","created_at":"2026-07-05T08:34:54.834748+00:00"},{"alias_kind":"pith_short_8","alias_value":"F6OZSZV4","created_at":"2026-07-05T08:34:54.834748+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08010","citing_title":"Tool-Making and Self-Evolving LLM Agents in Low-Latency Systems","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26669","citing_title":"SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00384","citing_title":"VESTA: Visual Exploration with Statistical Tool Agents","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19793","citing_title":"Prompt Injection Attack to Tool Selection in LLM Agents","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2309.16797","citing_title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","ref_index":264,"is_internal_anchor":false},{"citing_arxiv_id":"2304.08244","citing_title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03057","citing_title":"Querying Structured Data Through Natural Language Using Language Models","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10774","citing_title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12015","citing_title":"SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces","ref_index":43,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W","json":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W.json","graph_json":"https://pith.science/api/pith-number/F6OZSZV4USXUQPIS23L7JJX42W/graph.json","events_json":"https://pith.science/api/pith-number/F6OZSZV4USXUQPIS23L7JJX42W/events.json","paper":"https://pith.science/paper/F6OZSZV4"},"agent_actions":{"view_html":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W","download_json":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W.json","view_paper":"https://pith.science/paper/F6OZSZV4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14318&json=true","fetch_graph":"https://pith.science/api/pith-number/F6OZSZV4USXUQPIS23L7JJX42W/graph.json","fetch_events":"https://pith.science/api/pith-number/F6OZSZV4USXUQPIS23L7JJX42W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W/action/storage_attestation","attest_author":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W/action/author_attestation","sign_citation":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W/action/citation_signature","submit_replication":"https://pith.science/pith/F6OZSZV4USXUQPIS23L7JJX42W/action/replication_record"}},"created_at":"2026-07-05T08:34:54.834748+00:00","updated_at":"2026-07-05T08:34:54.834748+00:00"}