{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VZGGVIVK36KRGDOXXNEW3FURVU","short_pith_number":"pith:VZGGVIVK","schema_version":"1.0","canonical_sha256":"ae4c6aa2aadf95130dd7bb496d9691ad0840c6797efb22cae12ea25e44ef48af","source":{"kind":"arxiv","id":"2503.03656","version":2},"attestation_state":"computed","paper":{"title":"Robust Learning of Diverse Code Edits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Abhijeet Awasthi, Aditya Kanade, Nagarajan Natarajan, Swayam Singh, Tushar Aggarwal","submitted_at":"2025-03-05T16:39:04Z","abstract_excerpt":"Software engineering activities frequently involve edits to existing code. However, contemporary code language models (LMs) lack the ability to handle diverse types of code-edit requirements. In this work, we attempt to overcome this shortcoming through (1) a novel synthetic data generation pipeline and (2) a robust model adaptation algorithm. Starting with seed code examples and diverse editing criteria, our pipeline generates high-quality samples comprising original and modified code, along with natural language instructions in different styles and verbosity. Today's code LMs come bundled wi"},"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":"2503.03656","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2025-03-05T16:39:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e89f4b8d21a37caf4b5137d3e4ba75e15a6c13fd443616294ab1497b1c4153cc","abstract_canon_sha256":"57500d390bd7b54904db28d38832f9b689aafc629ad40366ed4021d02bf2d1a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:03.679847Z","signature_b64":"G7wNSNUnwyoLmX+7445d1WinSFS4HuS+7smLoYr9A9U0l3aykLky/K1jXW47yL/8DKKR0OAfTcxtd1f7P7hUCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae4c6aa2aadf95130dd7bb496d9691ad0840c6797efb22cae12ea25e44ef48af","last_reissued_at":"2026-07-05T11:01:03.679352Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:03.679352Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robust Learning of Diverse Code Edits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Abhijeet Awasthi, Aditya Kanade, Nagarajan Natarajan, Swayam Singh, Tushar Aggarwal","submitted_at":"2025-03-05T16:39:04Z","abstract_excerpt":"Software engineering activities frequently involve edits to existing code. However, contemporary code language models (LMs) lack the ability to handle diverse types of code-edit requirements. In this work, we attempt to overcome this shortcoming through (1) a novel synthetic data generation pipeline and (2) a robust model adaptation algorithm. Starting with seed code examples and diverse editing criteria, our pipeline generates high-quality samples comprising original and modified code, along with natural language instructions in different styles and verbosity. Today's code LMs come bundled wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03656","kind":"arxiv","version":2},"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/2503.03656/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":"2503.03656","created_at":"2026-07-05T11:01:03.679413+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03656v2","created_at":"2026-07-05T11:01:03.679413+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03656","created_at":"2026-07-05T11:01:03.679413+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZGGVIVK36KR","created_at":"2026-07-05T11:01:03.679413+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZGGVIVK36KRGDOX","created_at":"2026-07-05T11:01:03.679413+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZGGVIVK","created_at":"2026-07-05T11:01:03.679413+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.17329","citing_title":"A Pilot Study on Detecting Software Design Patterns with Large Language Models: An Empirical Evaluation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU","json":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU.json","graph_json":"https://pith.science/api/pith-number/VZGGVIVK36KRGDOXXNEW3FURVU/graph.json","events_json":"https://pith.science/api/pith-number/VZGGVIVK36KRGDOXXNEW3FURVU/events.json","paper":"https://pith.science/paper/VZGGVIVK"},"agent_actions":{"view_html":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU","download_json":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU.json","view_paper":"https://pith.science/paper/VZGGVIVK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03656&json=true","fetch_graph":"https://pith.science/api/pith-number/VZGGVIVK36KRGDOXXNEW3FURVU/graph.json","fetch_events":"https://pith.science/api/pith-number/VZGGVIVK36KRGDOXXNEW3FURVU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU/action/storage_attestation","attest_author":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU/action/author_attestation","sign_citation":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU/action/citation_signature","submit_replication":"https://pith.science/pith/VZGGVIVK36KRGDOXXNEW3FURVU/action/replication_record"}},"created_at":"2026-07-05T11:01:03.679413+00:00","updated_at":"2026-07-05T11:01:03.679413+00:00"}