{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LEK5HMXNWMMINOIIJVWWSTOMRP","short_pith_number":"pith:LEK5HMXN","schema_version":"1.0","canonical_sha256":"5915d3b2edb31886b9084d6d694dcc8bd040cc2407d403dce31871c32e83660e","source":{"kind":"arxiv","id":"2411.18019","version":1},"attestation_state":"computed","paper":{"title":"A Real-World Benchmark for Evaluating Fine-Grained Issue Solving Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bo Jiang, Chao Peng, Cuiyun Gao, Jingyi Ren, Pengfei Gao, Qinyun Wu, Ruida Hu, Xiangxin Meng, Xinchen Wang","submitted_at":"2024-11-27T03:25:44Z","abstract_excerpt":"Automatically resolving software issues is crucial for software development in practice, impacting the software quality and user experience. The process of resolving real-world issues encompasses tasks such as question-answering (QA), fault localization, and code editing. Existing benchmarks such as HumanEval fall short in their ability to assess LLMs' proficiency in solving issues within a codebase. Although benchmarks like SWE-Bench are designed to evaluate the LLMs' capability to handle real-world GitHub issues, the end-to-end evaluation method cannot provide granular insights on the perfor"},"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":"2411.18019","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-27T03:25:44Z","cross_cats_sorted":[],"title_canon_sha256":"590b21b77ec4d974350561b22a6d698e9997e2d14e685e601814ab7d73fed038","abstract_canon_sha256":"0c10cdb179d49f831043fca9406faedd87723d20923a00511dfb07d548b07d17"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:10.488816Z","signature_b64":"6lBVqPlb2nF5tQVkniup5h4B7bABr2G7wkf7MUGP9SIbJ0N6oMqz69hD4dhbuGlgZ3shBjYJ2yDXn9gGeK73Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5915d3b2edb31886b9084d6d694dcc8bd040cc2407d403dce31871c32e83660e","last_reissued_at":"2026-07-05T09:41:10.488332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:10.488332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Real-World Benchmark for Evaluating Fine-Grained Issue Solving Capabilities of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Bo Jiang, Chao Peng, Cuiyun Gao, Jingyi Ren, Pengfei Gao, Qinyun Wu, Ruida Hu, Xiangxin Meng, Xinchen Wang","submitted_at":"2024-11-27T03:25:44Z","abstract_excerpt":"Automatically resolving software issues is crucial for software development in practice, impacting the software quality and user experience. The process of resolving real-world issues encompasses tasks such as question-answering (QA), fault localization, and code editing. Existing benchmarks such as HumanEval fall short in their ability to assess LLMs' proficiency in solving issues within a codebase. Although benchmarks like SWE-Bench are designed to evaluate the LLMs' capability to handle real-world GitHub issues, the end-to-end evaluation method cannot provide granular insights on the perfor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18019","kind":"arxiv","version":1},"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/2411.18019/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":"2411.18019","created_at":"2026-07-05T09:41:10.488390+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18019v1","created_at":"2026-07-05T09:41:10.488390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18019","created_at":"2026-07-05T09:41:10.488390+00:00"},{"alias_kind":"pith_short_12","alias_value":"LEK5HMXNWMMI","created_at":"2026-07-05T09:41:10.488390+00:00"},{"alias_kind":"pith_short_16","alias_value":"LEK5HMXNWMMINOII","created_at":"2026-07-05T09:41:10.488390+00:00"},{"alias_kind":"pith_short_8","alias_value":"LEK5HMXN","created_at":"2026-07-05T09:41:10.488390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.11270","citing_title":"Evaluating LLM Agents on Automated Software Analysis Tasks","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP","json":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP.json","graph_json":"https://pith.science/api/pith-number/LEK5HMXNWMMINOIIJVWWSTOMRP/graph.json","events_json":"https://pith.science/api/pith-number/LEK5HMXNWMMINOIIJVWWSTOMRP/events.json","paper":"https://pith.science/paper/LEK5HMXN"},"agent_actions":{"view_html":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP","download_json":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP.json","view_paper":"https://pith.science/paper/LEK5HMXN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18019&json=true","fetch_graph":"https://pith.science/api/pith-number/LEK5HMXNWMMINOIIJVWWSTOMRP/graph.json","fetch_events":"https://pith.science/api/pith-number/LEK5HMXNWMMINOIIJVWWSTOMRP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP/action/storage_attestation","attest_author":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP/action/author_attestation","sign_citation":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP/action/citation_signature","submit_replication":"https://pith.science/pith/LEK5HMXNWMMINOIIJVWWSTOMRP/action/replication_record"}},"created_at":"2026-07-05T09:41:10.488390+00:00","updated_at":"2026-07-05T09:41:10.488390+00:00"}