{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MHMB5WGHVF3VAYZS6GCAM3BVAO","short_pith_number":"pith:MHMB5WGH","schema_version":"1.0","canonical_sha256":"61d81ed8c7a977506332f184066c3503a2d4ddff13ed3b02640e4a17cfe9a250","source":{"kind":"arxiv","id":"2412.19031","version":1},"attestation_state":"computed","paper":{"title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bing Xie, Shengnan An, Yanzhen Zou, Zeqi Lin, Zexiong Ma","submitted_at":"2024-12-26T03:01:32Z","abstract_excerpt":"Language models have been applied to various software development tasks, but the performance varies according to the scale of the models. Large Language Models (LLMs) outperform Small Language Models (SLMs) in complex tasks like repository-level issue resolving, but raise concerns about privacy and cost. In contrast, SLMs are more accessible but under-perform in complex tasks. In this paper, we introduce ReSAT (Repository Structure-Aware Training), construct training data based on a large number of issues and corresponding pull requests from open-source communities to enhance the model's under"},"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":"2412.19031","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-26T03:01:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d21674cf3747fc7be3ab3efb0ed5341a6d66d697f2752b88af2b848437ac349d","abstract_canon_sha256":"01ce42fc58bb669bdb462bc6b302c06bee88bff79f58a417cc97bb1a18cd5b7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:15.139458Z","signature_b64":"0Kl0EHookL45z85AiUrIzTxekKJTklgt+deChx0pqixKd9+pEO/kXy2Yh94om0FM01gSRyg75ksioKXI1bGaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61d81ed8c7a977506332f184066c3503a2d4ddff13ed3b02640e4a17cfe9a250","last_reissued_at":"2026-07-05T09:54:15.138963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:15.138963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Repository Structure-Aware Training Makes SLMs Better Issue Resolver","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Bing Xie, Shengnan An, Yanzhen Zou, Zeqi Lin, Zexiong Ma","submitted_at":"2024-12-26T03:01:32Z","abstract_excerpt":"Language models have been applied to various software development tasks, but the performance varies according to the scale of the models. Large Language Models (LLMs) outperform Small Language Models (SLMs) in complex tasks like repository-level issue resolving, but raise concerns about privacy and cost. In contrast, SLMs are more accessible but under-perform in complex tasks. In this paper, we introduce ReSAT (Repository Structure-Aware Training), construct training data based on a large number of issues and corresponding pull requests from open-source communities to enhance the model's under"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.19031","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/2412.19031/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":"2412.19031","created_at":"2026-07-05T09:54:15.139022+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.19031v1","created_at":"2026-07-05T09:54:15.139022+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.19031","created_at":"2026-07-05T09:54:15.139022+00:00"},{"alias_kind":"pith_short_12","alias_value":"MHMB5WGHVF3V","created_at":"2026-07-05T09:54:15.139022+00:00"},{"alias_kind":"pith_short_16","alias_value":"MHMB5WGHVF3VAYZS","created_at":"2026-07-05T09:54:15.139022+00:00"},{"alias_kind":"pith_short_8","alias_value":"MHMB5WGH","created_at":"2026-07-05T09:54:15.139022+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.12728","citing_title":"MCTS-Refined CoT: High-Quality Fine-Tuning Data for LLM-Based Repository Issue Resolution","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO","json":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO.json","graph_json":"https://pith.science/api/pith-number/MHMB5WGHVF3VAYZS6GCAM3BVAO/graph.json","events_json":"https://pith.science/api/pith-number/MHMB5WGHVF3VAYZS6GCAM3BVAO/events.json","paper":"https://pith.science/paper/MHMB5WGH"},"agent_actions":{"view_html":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO","download_json":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO.json","view_paper":"https://pith.science/paper/MHMB5WGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.19031&json=true","fetch_graph":"https://pith.science/api/pith-number/MHMB5WGHVF3VAYZS6GCAM3BVAO/graph.json","fetch_events":"https://pith.science/api/pith-number/MHMB5WGHVF3VAYZS6GCAM3BVAO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO/action/storage_attestation","attest_author":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO/action/author_attestation","sign_citation":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO/action/citation_signature","submit_replication":"https://pith.science/pith/MHMB5WGHVF3VAYZS6GCAM3BVAO/action/replication_record"}},"created_at":"2026-07-05T09:54:15.139022+00:00","updated_at":"2026-07-05T09:54:15.139022+00:00"}