{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TKPFUNDF4WGTORPAI6INWPUXWO","short_pith_number":"pith:TKPFUNDF","schema_version":"1.0","canonical_sha256":"9a9e5a3465e58d3745e04790db3e97b393e39602bec2c3e70ce5f6669450fd3e","source":{"kind":"arxiv","id":"2402.14658","version":3},"attestation_state":"computed","paper":{"title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bill Yuchen Lin, Ge Zhang, Jie Fu, Tianhao Shen, Tianyu Zheng, Wenhu Chen, Xiang Yue, Xueling Liu","submitted_at":"2024-02-22T16:06:23Z","abstract_excerpt":"The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpret"},"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":"2402.14658","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-02-22T16:06:23Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"0cf32cfdce7f4b405fea00113bed9058d03b6cc72b30e3040564403749a2f402","abstract_canon_sha256":"ac823f2e0afd39606c4c4ea0fc7ffd35a32148b3530c9b558b3f08e75196c939"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:39.853019Z","signature_b64":"7P1jYovAxBXpK+WBtBIVaZM9lQ9IM1M9lm8Iyu1KAGVufbRbmUQEIoCw4hgyLoVeQaPUY/WHDyuIOeR7wCNTAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a9e5a3465e58d3745e04790db3e97b393e39602bec2c3e70ce5f6669450fd3e","last_reissued_at":"2026-07-05T09:57:39.852527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:39.852527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.SE","authors_text":"Bill Yuchen Lin, Ge Zhang, Jie Fu, Tianhao Shen, Tianyu Zheng, Wenhu Chen, Xiang Yue, Xueling Liu","submitted_at":"2024-02-22T16:06:23Z","abstract_excerpt":"The introduction of large language models has significantly advanced code generation. However, open-source models often lack the execution capabilities and iterative refinement of advanced systems like the GPT-4 Code Interpreter. To address this, we introduce OpenCodeInterpreter, a family of open-source code systems designed for generating, executing, and iteratively refining code. Supported by Code-Feedback, a dataset featuring 68K multi-turn interactions, OpenCodeInterpreter integrates execution and human feedback for dynamic code refinement. Our comprehensive evaluation of OpenCodeInterpret"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14658","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/2402.14658/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":"2402.14658","created_at":"2026-07-05T09:57:39.852584+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14658v3","created_at":"2026-07-05T09:57:39.852584+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14658","created_at":"2026-07-05T09:57:39.852584+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKPFUNDF4WGT","created_at":"2026-07-05T09:57:39.852584+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKPFUNDF4WGTORPA","created_at":"2026-07-05T09:57:39.852584+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKPFUNDF","created_at":"2026-07-05T09:57:39.852584+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":15,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19364","citing_title":"Closing the Social-Semantic Gap: SPSD for Edge-Based Prompt Compression in Cloud LLM Inference","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27295","citing_title":"Gemini Embedding 2: A Native Multimodal Embedding Model from Gemini","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27365","citing_title":"LocateAnything: Fast and High-Quality Vision-Language Grounding with Parallel Box Decoding","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29460","citing_title":"FedSmoothLoRA: Toward Smoother and Faster Convergence in Federated Low-Rank Adaptation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27747","citing_title":"UNICS: Multilingual Code Search via Unified Pseudocode and Contrastive Transfer Learning","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16470","citing_title":"Strategic Over-Parameterization for Generalizable Low-Rank Adaptation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2406.11794","citing_title":"DataComp-LM: In search of the next generation of training sets for language models","ref_index":218,"is_internal_anchor":false},{"citing_arxiv_id":"2412.14164","citing_title":"MetaMorph: Multimodal Understanding and Generation via Instruction Tuning","ref_index":180,"is_internal_anchor":false},{"citing_arxiv_id":"2406.16860","citing_title":"Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2601.00376","citing_title":"In Line with Context: Repository-Level Code Generation via Context Inlining","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2409.02060","citing_title":"OLMoE: Open Mixture-of-Experts Language Models","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2603.23964","citing_title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","ref_index":151,"is_internal_anchor":false},{"citing_arxiv_id":"2502.01456","citing_title":"Process Reinforcement through Implicit Rewards","ref_index":148,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":227,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18124","citing_title":"TLoRA: Task-aware Low Rank Adaptation of Large Language Models","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO","json":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO.json","graph_json":"https://pith.science/api/pith-number/TKPFUNDF4WGTORPAI6INWPUXWO/graph.json","events_json":"https://pith.science/api/pith-number/TKPFUNDF4WGTORPAI6INWPUXWO/events.json","paper":"https://pith.science/paper/TKPFUNDF"},"agent_actions":{"view_html":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO","download_json":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO.json","view_paper":"https://pith.science/paper/TKPFUNDF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14658&json=true","fetch_graph":"https://pith.science/api/pith-number/TKPFUNDF4WGTORPAI6INWPUXWO/graph.json","fetch_events":"https://pith.science/api/pith-number/TKPFUNDF4WGTORPAI6INWPUXWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO/action/storage_attestation","attest_author":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO/action/author_attestation","sign_citation":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO/action/citation_signature","submit_replication":"https://pith.science/pith/TKPFUNDF4WGTORPAI6INWPUXWO/action/replication_record"}},"created_at":"2026-07-05T09:57:39.852584+00:00","updated_at":"2026-07-05T09:57:39.852584+00:00"}