{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:F2FITEMQHQUVHQ32NHSEJZQ44Z","short_pith_number":"pith:F2FITEMQ","schema_version":"1.0","canonical_sha256":"2e8a8991903c2953c37a69e444e61ce679077c813abb018711b020b24cefb7c6","source":{"kind":"arxiv","id":"2203.03850","version":1},"attestation_state":"computed","paper":{"title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.CL","authors_text":"Daya Guo, Jian Yin, Ming Zhou, Nan Duan, Shuai Lu, Yanlin Wang","submitted_at":"2022-03-08T04:48:07Z","abstract_excerpt":"Pre-trained models for programming languages have recently demonstrated great success on code intelligence. To support both code-related understanding and generation tasks, recent works attempt to pre-train unified encoder-decoder models. However, such encoder-decoder framework is sub-optimal for auto-regressive tasks, especially code completion that requires a decoder-only manner for efficient inference. In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language. The model utilizes mask attention matrices with prefix adapters to control the behavior "},"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":"2203.03850","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-08T04:48:07Z","cross_cats_sorted":["cs.PL","cs.SE"],"title_canon_sha256":"91da9e08b902fa5703a4c1491c699ae42ed398cb6d3fe63989f74cf897bced25","abstract_canon_sha256":"ab9a8b249474d7673c0bff51f279031520326c2bcb8f0f2d82ccf42dc038054c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T02:44:30.780712Z","signature_b64":"T8kzKJ3PyE7oH0hTmLsCcA4n2+URB4Cvu9Nyu6ZZ/Ui1FNFQcFKquP1b16NjT/aEEo2z/I+rqGO9RRaxP+QQAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e8a8991903c2953c37a69e444e61ce679077c813abb018711b020b24cefb7c6","last_reissued_at":"2026-05-19T02:44:30.777825Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T02:44:30.777825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniXcoder: Unified Cross-Modal Pre-training for Code Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE"],"primary_cat":"cs.CL","authors_text":"Daya Guo, Jian Yin, Ming Zhou, Nan Duan, Shuai Lu, Yanlin Wang","submitted_at":"2022-03-08T04:48:07Z","abstract_excerpt":"Pre-trained models for programming languages have recently demonstrated great success on code intelligence. To support both code-related understanding and generation tasks, recent works attempt to pre-train unified encoder-decoder models. However, such encoder-decoder framework is sub-optimal for auto-regressive tasks, especially code completion that requires a decoder-only manner for efficient inference. In this paper, we present UniXcoder, a unified cross-modal pre-trained model for programming language. The model utilizes mask attention matrices with prefix adapters to control the behavior "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03850","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":""},"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":"2203.03850","created_at":"2026-05-19T02:44:30.777956+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.03850v1","created_at":"2026-05-19T02:44:30.777956+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03850","created_at":"2026-05-19T02:44:30.777956+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2FITEMQHQUV","created_at":"2026-05-19T02:44:30.777956+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2FITEMQHQUVHQ32","created_at":"2026-05-19T02:44:30.777956+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2FITEMQ","created_at":"2026-05-19T02:44:30.777956+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2402.01411","citing_title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2410.22240","citing_title":"Are Decoder-Only Large Language Models the Silver Bullet for Code Search?","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2509.20881","citing_title":"PseudoBridge: Pseudo Code as the Bridge for Better Semantic and Logic Alignment in Code Retrieval","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16046","citing_title":"XSearch: Explainable Code Search via Concept-to-Code Alignment","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15315","citing_title":"Context Pruning for Coding Agents via Multi-Rubric Latent Reasoning","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21954","citing_title":"Fine-Tuning Code Language Models to Detect Cross-Language Bugs","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2509.09192","citing_title":"ReDef: Do Code Language Models Truly Understand Code Changes for Just-in-Time Software Defect Prediction?","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2510.04166","citing_title":"Multi Language Models for On-the-Fly Syntax Highlighting","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2602.01785","citing_title":"CodeOCR: On the Effectiveness of Vision Language Models in Code Understanding","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16377","citing_title":"GoCoMA: Hyperbolic Multimodal Representation Fusion for Large Language Model-Generated Code Attribution","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02702","citing_title":"TypePro: Boosting LLM-Based Type Inference via Inter-Procedural Slicing","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27647","citing_title":"Tail-aware N-version Machine Learning Models for Reliable API Recommendation","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26313","citing_title":"VulStyle: A Multi-Modal Pre-Training for Code Stylometry-Augmented Vulnerability Detection","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25599","citing_title":"PLMGH: What Matters in PLM-GNN Hybrids for Code Classification and Vulnerability Detection","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22432","citing_title":"R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21051","citing_title":"Residual Risk Analysis in Benign Code: How Far Are We? A Multi-Model Semantic and Structural Similarity Approach","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18162","citing_title":"VerilogCL: A Contrastive Learning Framework for Robust LLM-Based Verilog Generation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18607","citing_title":"TurboEvolve: Towards Fast and Robust LLM-Driven Program Evolution","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2506.18088","citing_title":"RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07957","citing_title":"Similar Pattern Annotation via Retrieval Knowledge for LLM-Based Test Code Fault Localization","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07891","citing_title":"AFGNN: API Misuse Detection using Graph Neural Networks and Clustering","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13725","citing_title":"On the Effectiveness of Context Compression for Repository-Level Tasks: An Empirical Investigation","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2504.15564","citing_title":"OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z","json":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z.json","graph_json":"https://pith.science/api/pith-number/F2FITEMQHQUVHQ32NHSEJZQ44Z/graph.json","events_json":"https://pith.science/api/pith-number/F2FITEMQHQUVHQ32NHSEJZQ44Z/events.json","paper":"https://pith.science/paper/F2FITEMQ"},"agent_actions":{"view_html":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z","download_json":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z.json","view_paper":"https://pith.science/paper/F2FITEMQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.03850&json=true","fetch_graph":"https://pith.science/api/pith-number/F2FITEMQHQUVHQ32NHSEJZQ44Z/graph.json","fetch_events":"https://pith.science/api/pith-number/F2FITEMQHQUVHQ32NHSEJZQ44Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z/action/storage_attestation","attest_author":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z/action/author_attestation","sign_citation":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z/action/citation_signature","submit_replication":"https://pith.science/pith/F2FITEMQHQUVHQ32NHSEJZQ44Z/action/replication_record"}},"created_at":"2026-05-19T02:44:30.777956+00:00","updated_at":"2026-05-19T02:44:30.777956+00:00"}