{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WP5BIKODMUJFMNYNWX7OFATX2A","short_pith_number":"pith:WP5BIKOD","schema_version":"1.0","canonical_sha256":"b3fa1429c3651256370db5fee28277d0229fb6916999820c4ab31ef28aad7852","source":{"kind":"arxiv","id":"2503.04214","version":1},"attestation_state":"computed","paper":{"title":"Extracting Fix Ingredients using Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Julian Aron Prenner, Romain Robbes","submitted_at":"2025-03-06T08:48:52Z","abstract_excerpt":"Deep learning and language models are increasingly dominating automated program repair research. While previous generate-and-validate approaches were able to find and use fix ingredients on a file or even project level, neural language models are limited to the code that fits their input window. In this work we investigate how important identifier ingredients are in neural program repair and present ScanFix, an approach that leverages an additional scanner model to extract identifiers from a bug's file and potentially project-level context. We find that lack of knowledge of far-away identifier"},"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":"2503.04214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-03-06T08:48:52Z","cross_cats_sorted":[],"title_canon_sha256":"8d27fb6912cb4ddb349af2760cf8069046e0e1299add286f333a2cccf6753d34","abstract_canon_sha256":"9965fb81458d1bbc3b28de5d00ac57e961e4cd75e9055acaaf999f5c90ece778"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:32.366983Z","signature_b64":"2YndQhY1WeJXoymdJNeN4rxO28zMY6SLVL2Nz2hoTu1543YiZk1mgw1SV2Q4AYylJtscKvT/BonE4wMeYhMEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b3fa1429c3651256370db5fee28277d0229fb6916999820c4ab31ef28aad7852","last_reissued_at":"2026-07-05T10:25:32.366023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:32.366023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Extracting Fix Ingredients using Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Julian Aron Prenner, Romain Robbes","submitted_at":"2025-03-06T08:48:52Z","abstract_excerpt":"Deep learning and language models are increasingly dominating automated program repair research. While previous generate-and-validate approaches were able to find and use fix ingredients on a file or even project level, neural language models are limited to the code that fits their input window. In this work we investigate how important identifier ingredients are in neural program repair and present ScanFix, an approach that leverages an additional scanner model to extract identifiers from a bug's file and potentially project-level context. We find that lack of knowledge of far-away identifier"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04214","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/2503.04214/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":"2503.04214","created_at":"2026-07-05T10:25:32.366106+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04214v1","created_at":"2026-07-05T10:25:32.366106+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04214","created_at":"2026-07-05T10:25:32.366106+00:00"},{"alias_kind":"pith_short_12","alias_value":"WP5BIKODMUJF","created_at":"2026-07-05T10:25:32.366106+00:00"},{"alias_kind":"pith_short_16","alias_value":"WP5BIKODMUJFMNYN","created_at":"2026-07-05T10:25:32.366106+00:00"},{"alias_kind":"pith_short_8","alias_value":"WP5BIKOD","created_at":"2026-07-05T10:25:32.366106+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A","json":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A.json","graph_json":"https://pith.science/api/pith-number/WP5BIKODMUJFMNYNWX7OFATX2A/graph.json","events_json":"https://pith.science/api/pith-number/WP5BIKODMUJFMNYNWX7OFATX2A/events.json","paper":"https://pith.science/paper/WP5BIKOD"},"agent_actions":{"view_html":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A","download_json":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A.json","view_paper":"https://pith.science/paper/WP5BIKOD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04214&json=true","fetch_graph":"https://pith.science/api/pith-number/WP5BIKODMUJFMNYNWX7OFATX2A/graph.json","fetch_events":"https://pith.science/api/pith-number/WP5BIKODMUJFMNYNWX7OFATX2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A/action/storage_attestation","attest_author":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A/action/author_attestation","sign_citation":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A/action/citation_signature","submit_replication":"https://pith.science/pith/WP5BIKODMUJFMNYNWX7OFATX2A/action/replication_record"}},"created_at":"2026-07-05T10:25:32.366106+00:00","updated_at":"2026-07-05T10:25:32.366106+00:00"}