{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H7BCIN4IR3QFRQC6BFK75AVZIZ","short_pith_number":"pith:H7BCIN4I","schema_version":"1.0","canonical_sha256":"3fc22437888ee058c05e0955fe82b9464b373117a48df4a472a3d8536e8ebbb5","source":{"kind":"arxiv","id":"2404.05520","version":3},"attestation_state":"computed","paper":{"title":"The Fact Selection Problem in LLM-Based Program Repair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Abriele Qudsi, Boyu Yang, Damian Ziaber, Earl Barr, Huijie Yan, Nikhil Parasaram, Sergey Mechtaev, Zineb Flahy","submitted_at":"2024-04-08T13:41:32Z","abstract_excerpt":"Recent research has shown that incorporating bug-related facts, such as stack traces and GitHub issues, into prompts enhances the bug-fixing capabilities of large language models (LLMs). Considering the ever-increasing context window of these models, a critical question arises: what and how many facts should be included in prompts to maximise the chance of correctly fixing bugs? To answer this question, we conducted a large-scale study, employing over 19K prompts featuring various combinations of seven diverse facts to rectify 314 bugs from open-source Python projects within the BugsInPy bench"},"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":"2404.05520","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-04-08T13:41:32Z","cross_cats_sorted":[],"title_canon_sha256":"5a995306ed4614f61c5508e309b5759379e05677bcb03a936df1f76dd808a62d","abstract_canon_sha256":"ca1c663bd8af38de4c81c966475d6d02afdce9535ddcac911a0326be3148cbe2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:27.166063Z","signature_b64":"zcbVMnXMbrqsY3Dg1wzADukeZlZVDRnZ3xiCZ/vhy+nuB32U6A3iARsXTnZM5M6EhuI/gMvecHwEuxUX1OnlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fc22437888ee058c05e0955fe82b9464b373117a48df4a472a3d8536e8ebbb5","last_reissued_at":"2026-07-05T08:59:27.165566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:27.165566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Fact Selection Problem in LLM-Based Program Repair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Abriele Qudsi, Boyu Yang, Damian Ziaber, Earl Barr, Huijie Yan, Nikhil Parasaram, Sergey Mechtaev, Zineb Flahy","submitted_at":"2024-04-08T13:41:32Z","abstract_excerpt":"Recent research has shown that incorporating bug-related facts, such as stack traces and GitHub issues, into prompts enhances the bug-fixing capabilities of large language models (LLMs). Considering the ever-increasing context window of these models, a critical question arises: what and how many facts should be included in prompts to maximise the chance of correctly fixing bugs? To answer this question, we conducted a large-scale study, employing over 19K prompts featuring various combinations of seven diverse facts to rectify 314 bugs from open-source Python projects within the BugsInPy bench"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05520","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/2404.05520/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":"2404.05520","created_at":"2026-07-05T08:59:27.165626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05520v3","created_at":"2026-07-05T08:59:27.165626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05520","created_at":"2026-07-05T08:59:27.165626+00:00"},{"alias_kind":"pith_short_12","alias_value":"H7BCIN4IR3QF","created_at":"2026-07-05T08:59:27.165626+00:00"},{"alias_kind":"pith_short_16","alias_value":"H7BCIN4IR3QFRQC6","created_at":"2026-07-05T08:59:27.165626+00:00"},{"alias_kind":"pith_short_8","alias_value":"H7BCIN4I","created_at":"2026-07-05T08:59:27.165626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":209,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ","json":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ.json","graph_json":"https://pith.science/api/pith-number/H7BCIN4IR3QFRQC6BFK75AVZIZ/graph.json","events_json":"https://pith.science/api/pith-number/H7BCIN4IR3QFRQC6BFK75AVZIZ/events.json","paper":"https://pith.science/paper/H7BCIN4I"},"agent_actions":{"view_html":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ","download_json":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ.json","view_paper":"https://pith.science/paper/H7BCIN4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05520&json=true","fetch_graph":"https://pith.science/api/pith-number/H7BCIN4IR3QFRQC6BFK75AVZIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/H7BCIN4IR3QFRQC6BFK75AVZIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ/action/storage_attestation","attest_author":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ/action/author_attestation","sign_citation":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ/action/citation_signature","submit_replication":"https://pith.science/pith/H7BCIN4IR3QFRQC6BFK75AVZIZ/action/replication_record"}},"created_at":"2026-07-05T08:59:27.165626+00:00","updated_at":"2026-07-05T08:59:27.165626+00:00"}