{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ENC5EIW5OFFUIGAHGWB7RRVKH3","short_pith_number":"pith:ENC5EIW5","schema_version":"1.0","canonical_sha256":"2345d222dd714b4418073583f8c6aa3efab2d49dd27a607ffc42f0d37976e058","source":{"kind":"arxiv","id":"2501.05040","version":3},"attestation_state":"computed","paper":{"title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Li, Chang Gao, Chengxing Xie, Difan Zou, He Du, Kai Chen, Wai Lam","submitted_at":"2025-01-09T07:54:24Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks. One significant application of LLMs is in tackling software engineering challenges, particularly in resolving real-world tasks on GitHub by fixing code based on the issues reported by the users. However, many current approaches rely on proprietary LLMs, which limits reproducibility, accessibility, and transparency. The critical components of LLMs for addressing software engineering issues and how their capabilities can be effectively enhanced remain unclear. To address these challenges, we "},"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":"2501.05040","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-09T07:54:24Z","cross_cats_sorted":[],"title_canon_sha256":"c4b87707f3258064fa30850f14e11aeb9ef2f658df6530d166ed2c9169b98fa6","abstract_canon_sha256":"f0f661bc981fd07f80f5bdac06a470bea98eb95b30ebf1f223c0a52e89cadff1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:26.735285Z","signature_b64":"ax3eHCLEr05Ca79UdAkM1SvBHMDzn4CO5Iajn4zsu1eNYjbTqDSr9RGS9i5WIdai+kTUmVa435fNpCR44zfWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2345d222dd714b4418073583f8c6aa3efab2d49dd27a607ffc42f0d37976e058","last_reissued_at":"2026-07-05T10:59:26.734778Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:26.734778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SWE-Fixer: Training Open-Source LLMs for Effective and Efficient GitHub Issue Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Li, Chang Gao, Chengxing Xie, Difan Zou, He Du, Kai Chen, Wai Lam","submitted_at":"2025-01-09T07:54:24Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable proficiency across a variety of complex tasks. One significant application of LLMs is in tackling software engineering challenges, particularly in resolving real-world tasks on GitHub by fixing code based on the issues reported by the users. However, many current approaches rely on proprietary LLMs, which limits reproducibility, accessibility, and transparency. The critical components of LLMs for addressing software engineering issues and how their capabilities can be effectively enhanced remain unclear. To address these challenges, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05040","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/2501.05040/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":"2501.05040","created_at":"2026-07-05T10:59:26.734838+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05040v3","created_at":"2026-07-05T10:59:26.734838+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05040","created_at":"2026-07-05T10:59:26.734838+00:00"},{"alias_kind":"pith_short_12","alias_value":"ENC5EIW5OFFU","created_at":"2026-07-05T10:59:26.734838+00:00"},{"alias_kind":"pith_short_16","alias_value":"ENC5EIW5OFFUIGAH","created_at":"2026-07-05T10:59:26.734838+00:00"},{"alias_kind":"pith_short_8","alias_value":"ENC5EIW5","created_at":"2026-07-05T10:59:26.734838+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19741","citing_title":"CityRAG: Stepping Into a City via Spatially-Grounded Video Generation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09659","citing_title":"End-to-End Context Compression at Scale","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03461","citing_title":"What Makes Interaction Trajectories Effective for Training Terminal Agents?","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00750","citing_title":"I-WebGenBench : Evaluating Interactivity in LLM-Generated Scientific Web Applications","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09134","citing_title":"BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09134","citing_title":"BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19742","citing_title":"PlayCoder: Making LLM-Generated GUI Code Playable","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3","json":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3.json","graph_json":"https://pith.science/api/pith-number/ENC5EIW5OFFUIGAHGWB7RRVKH3/graph.json","events_json":"https://pith.science/api/pith-number/ENC5EIW5OFFUIGAHGWB7RRVKH3/events.json","paper":"https://pith.science/paper/ENC5EIW5"},"agent_actions":{"view_html":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3","download_json":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3.json","view_paper":"https://pith.science/paper/ENC5EIW5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05040&json=true","fetch_graph":"https://pith.science/api/pith-number/ENC5EIW5OFFUIGAHGWB7RRVKH3/graph.json","fetch_events":"https://pith.science/api/pith-number/ENC5EIW5OFFUIGAHGWB7RRVKH3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3/action/storage_attestation","attest_author":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3/action/author_attestation","sign_citation":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3/action/citation_signature","submit_replication":"https://pith.science/pith/ENC5EIW5OFFUIGAHGWB7RRVKH3/action/replication_record"}},"created_at":"2026-07-05T10:59:26.734838+00:00","updated_at":"2026-07-05T10:59:26.734838+00:00"}