{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2DSGSZYMTUCTDOJ66MFRMBI2ZQ","short_pith_number":"pith:2DSGSZYM","schema_version":"1.0","canonical_sha256":"d0e469670c9d0531b93ef30b16051acc24fab6146fc529c0a32657a76a9644d1","source":{"kind":"arxiv","id":"2403.03894","version":3},"attestation_state":"computed","paper":{"title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.AI","authors_text":"Goran Glava\\v{s}, Indraneil Paul, Iryna Gurevych","submitted_at":"2024-03-06T17:52:08Z","abstract_excerpt":"Code understanding and generation have fast become some of the most popular applications of language models (LMs). Nonetheless, research on multilingual aspects of Code-LMs (i.e., LMs for code generation) such as cross-lingual transfer between different programming languages, language-specific data augmentation, and post-hoc LM adaptation, alongside exploitation of data sources other than the original textual content, has been much sparser than for their natural language counterparts. In particular, most mainstream Code-LMs have been pre-trained on source code files alone. In this work, we inv"},"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":"2403.03894","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-03-06T17:52:08Z","cross_cats_sorted":["cs.CL","cs.PL"],"title_canon_sha256":"4b5196ebda71353351548dc1893c0b4f24e3f259dd378df2421b85d920d37cdb","abstract_canon_sha256":"8bb7719dd8e030c2bddab919bdf83175cd3befb6527536eb35a3dbfa05fa952e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:02.240787Z","signature_b64":"A+BZE/2xfJRB0VPgn8Jd+LOZcf4MYWXXbhwpilxLbsjRESfANB7a4fPVBaSJofsCr3hF+Y2d034hfgS/3yQhBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0e469670c9d0531b93ef30b16051acc24fab6146fc529c0a32657a76a9644d1","last_reissued_at":"2026-07-05T08:08:02.240325Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:02.240325Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL","cs.PL"],"primary_cat":"cs.AI","authors_text":"Goran Glava\\v{s}, Indraneil Paul, Iryna Gurevych","submitted_at":"2024-03-06T17:52:08Z","abstract_excerpt":"Code understanding and generation have fast become some of the most popular applications of language models (LMs). Nonetheless, research on multilingual aspects of Code-LMs (i.e., LMs for code generation) such as cross-lingual transfer between different programming languages, language-specific data augmentation, and post-hoc LM adaptation, alongside exploitation of data sources other than the original textual content, has been much sparser than for their natural language counterparts. In particular, most mainstream Code-LMs have been pre-trained on source code files alone. In this work, we inv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03894","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/2403.03894/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":"2403.03894","created_at":"2026-07-05T08:08:02.240380+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03894v3","created_at":"2026-07-05T08:08:02.240380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03894","created_at":"2026-07-05T08:08:02.240380+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DSGSZYMTUCT","created_at":"2026-07-05T08:08:02.240380+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DSGSZYMTUCTDOJ6","created_at":"2026-07-05T08:08:02.240380+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DSGSZYM","created_at":"2026-07-05T08:08:02.240380+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07925","citing_title":"ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2412.04590","citing_title":"Specification-Driven Code Translation Powered by Large Language Models: How Far Are We?","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":212,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08247","citing_title":"LLM Translation of Compiler Intermediate Representation","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25960","citing_title":"Large Language Models for Multilingual Code Intelligence: A Survey","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ","json":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ.json","graph_json":"https://pith.science/api/pith-number/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/graph.json","events_json":"https://pith.science/api/pith-number/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/events.json","paper":"https://pith.science/paper/2DSGSZYM"},"agent_actions":{"view_html":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ","download_json":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ.json","view_paper":"https://pith.science/paper/2DSGSZYM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03894&json=true","fetch_graph":"https://pith.science/api/pith-number/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/action/storage_attestation","attest_author":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/action/author_attestation","sign_citation":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/action/citation_signature","submit_replication":"https://pith.science/pith/2DSGSZYMTUCTDOJ66MFRMBI2ZQ/action/replication_record"}},"created_at":"2026-07-05T08:08:02.240380+00:00","updated_at":"2026-07-05T08:08:02.240380+00:00"}