{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7JXR4WNXT2ZMIKGU56EFRRX5SS","short_pith_number":"pith:7JXR4WNX","schema_version":"1.0","canonical_sha256":"fa6f1e59b79eb2c428d4ef8858c6fd948f906e6de02f4985e9a5963ecdc45cba","source":{"kind":"arxiv","id":"2502.19166","version":3},"attestation_state":"computed","paper":{"title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Donglin Di, Hongcheng Guo, Kaiwen Yan, Shaosheng Cao, Xuanqing Shi, Zhoujun Li","submitted_at":"2025-02-26T14:19:49Z","abstract_excerpt":"With the rapid advancement of Large Language Models (LLMs), the demand for robust instruction-following capabilities in code generation tasks has grown significantly. Code generation not only facilitates faster prototyping and automated testing, but also augments developer efficiency through improved maintainability and reusability of code. In this paper, we introduce CodeIF, the first benchmark specifically designed to assess the abilities of LLMs to adhere to task-oriented instructions within diverse code generation scenarios. CodeIF encompasses a broad range of tasks, including function syn"},"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":"2502.19166","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-02-26T14:19:49Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"eb1d42429002e749db733708630df8b96f78781548045bad58ed3d2baedb5da5","abstract_canon_sha256":"48d29d9998d2a94bf0d8fbe668666c3647bda14dbee90f73f4b111370212d264"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:48:01.361746Z","signature_b64":"GXTOoZlX29JoUD1dbQvvJY+5gRAuY60PUxz2aR9A193RVYplkISN2zbOpkLPMc81C+FxHBvVBWgP9pfDS0/ECg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fa6f1e59b79eb2c428d4ef8858c6fd948f906e6de02f4985e9a5963ecdc45cba","last_reissued_at":"2026-07-05T11:48:01.361179Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:48:01.361179Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeIF: Benchmarking the Instruction-Following Capabilities of Large Language Models for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Donglin Di, Hongcheng Guo, Kaiwen Yan, Shaosheng Cao, Xuanqing Shi, Zhoujun Li","submitted_at":"2025-02-26T14:19:49Z","abstract_excerpt":"With the rapid advancement of Large Language Models (LLMs), the demand for robust instruction-following capabilities in code generation tasks has grown significantly. Code generation not only facilitates faster prototyping and automated testing, but also augments developer efficiency through improved maintainability and reusability of code. In this paper, we introduce CodeIF, the first benchmark specifically designed to assess the abilities of LLMs to adhere to task-oriented instructions within diverse code generation scenarios. CodeIF encompasses a broad range of tasks, including function syn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.19166","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/2502.19166/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":"2502.19166","created_at":"2026-07-05T11:48:01.361254+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.19166v3","created_at":"2026-07-05T11:48:01.361254+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.19166","created_at":"2026-07-05T11:48:01.361254+00:00"},{"alias_kind":"pith_short_12","alias_value":"7JXR4WNXT2ZM","created_at":"2026-07-05T11:48:01.361254+00:00"},{"alias_kind":"pith_short_16","alias_value":"7JXR4WNXT2ZMIKGU","created_at":"2026-07-05T11:48:01.361254+00:00"},{"alias_kind":"pith_short_8","alias_value":"7JXR4WNX","created_at":"2026-07-05T11:48:01.361254+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16322","citing_title":"Steerable Instruction Following Coding Data Synthesis with Actor-Parametric Schema Co-Evolution","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09866","citing_title":"Automating Structural Analysis Across Multiple Software Platforms Using Large Language Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09443","citing_title":"Many-Tier Instruction Hierarchy in LLM Agents","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS","json":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS.json","graph_json":"https://pith.science/api/pith-number/7JXR4WNXT2ZMIKGU56EFRRX5SS/graph.json","events_json":"https://pith.science/api/pith-number/7JXR4WNXT2ZMIKGU56EFRRX5SS/events.json","paper":"https://pith.science/paper/7JXR4WNX"},"agent_actions":{"view_html":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS","download_json":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS.json","view_paper":"https://pith.science/paper/7JXR4WNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.19166&json=true","fetch_graph":"https://pith.science/api/pith-number/7JXR4WNXT2ZMIKGU56EFRRX5SS/graph.json","fetch_events":"https://pith.science/api/pith-number/7JXR4WNXT2ZMIKGU56EFRRX5SS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS/action/storage_attestation","attest_author":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS/action/author_attestation","sign_citation":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS/action/citation_signature","submit_replication":"https://pith.science/pith/7JXR4WNXT2ZMIKGU56EFRRX5SS/action/replication_record"}},"created_at":"2026-07-05T11:48:01.361254+00:00","updated_at":"2026-07-05T11:48:01.361254+00:00"}