{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:32MQAIJAYWJP4WKTOK72WG5IYB","short_pith_number":"pith:32MQAIJA","schema_version":"1.0","canonical_sha256":"de99002120c592fe595372bfab1ba8c055d573c6d330352d11d545068afea8cf","source":{"kind":"arxiv","id":"2504.01523","version":1},"attestation_state":"computed","paper":{"title":"Adapting Knowledge Prompt Tuning for Enhanced Automated Program Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Lingxiao Jiang, Xuemeng Cai","submitted_at":"2025-04-02T09:10:02Z","abstract_excerpt":"Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as CodeT5, for APR. However, the effectiveness of fine-tuning becomes weakened in data scarcity scenarios, and data scarcity can be a common issue in practice, limiting fine-tuning performance. To alleviate this limitation, this paper adapts prompt tuning for enhanced APR and conducts a comprehensive study to evaluate its effectiveness in data scarcity scenarios, usi"},"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":"2504.01523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-04-02T09:10:02Z","cross_cats_sorted":[],"title_canon_sha256":"f934a6a1898486b96dce7132bf12e96d40adb240872b1f087982fe17237d7934","abstract_canon_sha256":"fc966f2d0962bd232feec0177c953bd525e7225f94f233955635d1302d773905"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:16.719440Z","signature_b64":"u4c79lK1YHnc2U4FCgeIbG9e5+sz00jQLaeUrPQpCc31kdSO4AqBGEDFf3FtDTaX7fueXX4yL8ZLJgDcA0OUCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de99002120c592fe595372bfab1ba8c055d573c6d330352d11d545068afea8cf","last_reissued_at":"2026-07-05T10:43:16.718914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:16.718914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adapting Knowledge Prompt Tuning for Enhanced Automated Program Repair","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Lingxiao Jiang, Xuemeng Cai","submitted_at":"2025-04-02T09:10:02Z","abstract_excerpt":"Automated Program Repair (APR) aims to enhance software reliability by automatically generating bug-fixing patches. Recent work has improved the state-of-the-art of APR by fine-tuning pre-trained large language models (LLMs), such as CodeT5, for APR. However, the effectiveness of fine-tuning becomes weakened in data scarcity scenarios, and data scarcity can be a common issue in practice, limiting fine-tuning performance. To alleviate this limitation, this paper adapts prompt tuning for enhanced APR and conducts a comprehensive study to evaluate its effectiveness in data scarcity scenarios, usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.01523","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/2504.01523/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":"2504.01523","created_at":"2026-07-05T10:43:16.718973+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.01523v1","created_at":"2026-07-05T10:43:16.718973+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.01523","created_at":"2026-07-05T10:43:16.718973+00:00"},{"alias_kind":"pith_short_12","alias_value":"32MQAIJAYWJP","created_at":"2026-07-05T10:43:16.718973+00:00"},{"alias_kind":"pith_short_16","alias_value":"32MQAIJAYWJP4WKT","created_at":"2026-07-05T10:43:16.718973+00:00"},{"alias_kind":"pith_short_8","alias_value":"32MQAIJA","created_at":"2026-07-05T10:43:16.718973+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.18831","citing_title":"Enhancing LLMs' Reasoning-Intensive Multimedia Search Capabilities through Fine-Tuning and Reinforcement Learning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB","json":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB.json","graph_json":"https://pith.science/api/pith-number/32MQAIJAYWJP4WKTOK72WG5IYB/graph.json","events_json":"https://pith.science/api/pith-number/32MQAIJAYWJP4WKTOK72WG5IYB/events.json","paper":"https://pith.science/paper/32MQAIJA"},"agent_actions":{"view_html":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB","download_json":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB.json","view_paper":"https://pith.science/paper/32MQAIJA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.01523&json=true","fetch_graph":"https://pith.science/api/pith-number/32MQAIJAYWJP4WKTOK72WG5IYB/graph.json","fetch_events":"https://pith.science/api/pith-number/32MQAIJAYWJP4WKTOK72WG5IYB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB/action/storage_attestation","attest_author":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB/action/author_attestation","sign_citation":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB/action/citation_signature","submit_replication":"https://pith.science/pith/32MQAIJAYWJP4WKTOK72WG5IYB/action/replication_record"}},"created_at":"2026-07-05T10:43:16.718973+00:00","updated_at":"2026-07-05T10:43:16.718973+00:00"}