{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JUASKGXRELM4N6XN64WEYBC3W2","short_pith_number":"pith:JUASKGXR","schema_version":"1.0","canonical_sha256":"4d01251af122d9c6faedf72c4c045bb6be753e9cecf415e263d04591d9fac174","source":{"kind":"arxiv","id":"2306.14898","version":3},"attestation_state":"computed","paper":{"title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Akshara Prabhakar, John Yang, Karthik Narasimhan, Shunyu Yao","submitted_at":"2023-06-26T17:59:50Z","abstract_excerpt":"Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding benchmarks mostly consider a static instruction-to-code sequence transduction process, which has the potential for error propagation and a disconnect between the generated code and its final execution environment. To address this gap, we introduce InterCode, a lightweight, flexible, and easy-to-use framework of interactive coding as a standard reinforcement le"},"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":"2306.14898","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-26T17:59:50Z","cross_cats_sorted":["cs.LG","cs.SE"],"title_canon_sha256":"2d2ec5328690c9328fa8c7500594f91fde3b12306f78da8642a73a26f3110378","abstract_canon_sha256":"f2dd7ba975d870b154f5962fd97cf70e03d02fae2e0df03047217e6773c3f65a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:30.791253Z","signature_b64":"WaFf1oDTKP6l0OLu/n/lAljNEZB2ge1Lx320oDX4/+W2ahaIIZpjg8EDRYhRhQZt57986tfgJKYTP8Fw3baRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d01251af122d9c6faedf72c4c045bb6be753e9cecf415e263d04591d9fac174","last_reissued_at":"2026-07-05T07:06:30.790745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:30.790745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SE"],"primary_cat":"cs.CL","authors_text":"Akshara Prabhakar, John Yang, Karthik Narasimhan, Shunyu Yao","submitted_at":"2023-06-26T17:59:50Z","abstract_excerpt":"Humans write code in a fundamentally interactive manner and rely on constant execution feedback to correct errors, resolve ambiguities, and decompose tasks. While LLMs have recently exhibited promising coding capabilities, current coding benchmarks mostly consider a static instruction-to-code sequence transduction process, which has the potential for error propagation and a disconnect between the generated code and its final execution environment. To address this gap, we introduce InterCode, a lightweight, flexible, and easy-to-use framework of interactive coding as a standard reinforcement le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.14898","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/2306.14898/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":"2306.14898","created_at":"2026-07-05T07:06:30.790807+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.14898v3","created_at":"2026-07-05T07:06:30.790807+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.14898","created_at":"2026-07-05T07:06:30.790807+00:00"},{"alias_kind":"pith_short_12","alias_value":"JUASKGXRELM4","created_at":"2026-07-05T07:06:30.790807+00:00"},{"alias_kind":"pith_short_16","alias_value":"JUASKGXRELM4N6XN","created_at":"2026-07-05T07:06:30.790807+00:00"},{"alias_kind":"pith_short_8","alias_value":"JUASKGXR","created_at":"2026-07-05T07:06:30.790807+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29115","citing_title":"unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18073","citing_title":"A-ProS: Towards Reliable Autonomous Programming Through Multi-Model Feedback","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2507.06261","citing_title":"Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2507.14201","citing_title":"ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2409.12917","citing_title":"Training Language Models to Self-Correct via Reinforcement Learning","ref_index":147,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07972","citing_title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10597","citing_title":"CrackMeBench: Binary Reverse Engineering for Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08904","citing_title":"OPT-BENCH: Evaluating the Iterative Self-Optimization of LLM Agents in Large-Scale Search Spaces","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25727","citing_title":"Toward Scalable Terminal Task Synthesis via Skill Graphs","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18718","citing_title":"Towards Optimal Agentic Architectures for Offensive Security Tasks","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2408.00118","citing_title":"Gemma 2: Improving Open Language Models at a Practical Size","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15136","citing_title":"Feedback-Driven Execution for LLM-Based Binary Analysis","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20148","citing_title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","ref_index":52,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2","json":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2.json","graph_json":"https://pith.science/api/pith-number/JUASKGXRELM4N6XN64WEYBC3W2/graph.json","events_json":"https://pith.science/api/pith-number/JUASKGXRELM4N6XN64WEYBC3W2/events.json","paper":"https://pith.science/paper/JUASKGXR"},"agent_actions":{"view_html":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2","download_json":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2.json","view_paper":"https://pith.science/paper/JUASKGXR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.14898&json=true","fetch_graph":"https://pith.science/api/pith-number/JUASKGXRELM4N6XN64WEYBC3W2/graph.json","fetch_events":"https://pith.science/api/pith-number/JUASKGXRELM4N6XN64WEYBC3W2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2/action/storage_attestation","attest_author":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2/action/author_attestation","sign_citation":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2/action/citation_signature","submit_replication":"https://pith.science/pith/JUASKGXRELM4N6XN64WEYBC3W2/action/replication_record"}},"created_at":"2026-07-05T07:06:30.790807+00:00","updated_at":"2026-07-05T07:06:30.790807+00:00"}