{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ASHNUPN7KN3KNWFVS2R32A6QDK","short_pith_number":"pith:ASHNUPN7","schema_version":"1.0","canonical_sha256":"048eda3dbf5376a6d8b596a3bd03d01aa88f0d76806364521db42092d6c1058b","source":{"kind":"arxiv","id":"2310.15539","version":2},"attestation_state":"computed","paper":{"title":"SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adrien Sad\\'e, Eric Soriano, Guillem Sole, Jialing Pan, Jin Kim, Sylvain Flamant","submitted_at":"2023-10-24T06:04:28Z","abstract_excerpt":"With the recent focus on Large Language Models (LLMs), both StarCoder (Li et al., 2023) and Code Llama (Rozi\\`ere et al., 2023) have demonstrated remarkable performance in code generation. However, there is still a need for improvement in code translation functionality with efficient training techniques. In response to this, we introduce SteloCoder, a decoder-only StarCoder-based LLM designed specifically for multi-programming language-to-Python code translation. In particular, SteloCoder achieves C++, C#, JavaScript, Java, or PHP-to-Python code translation without specifying the input program"},"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":"2310.15539","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-24T06:04:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"93a02d4097f907ba2319c2a6d2b0f7607c5343766ee2a5fc9edd783eeb6a8217","abstract_canon_sha256":"072cd58da77872f565da4a6fd6419f33ee31bb0dfe7f584d76a6fcb0a862f601"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:24:21.060686Z","signature_b64":"OzFYC/g/IPNafqya+6uxlsKAa1H377SCDjmTzVl6QNUEUF0/YqPxD0QVyx2Cc6PAmVkF1SwMxS2TJvlpZG9eBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"048eda3dbf5376a6d8b596a3bd03d01aa88f0d76806364521db42092d6c1058b","last_reissued_at":"2026-07-05T07:24:21.060262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:24:21.060262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Adrien Sad\\'e, Eric Soriano, Guillem Sole, Jialing Pan, Jin Kim, Sylvain Flamant","submitted_at":"2023-10-24T06:04:28Z","abstract_excerpt":"With the recent focus on Large Language Models (LLMs), both StarCoder (Li et al., 2023) and Code Llama (Rozi\\`ere et al., 2023) have demonstrated remarkable performance in code generation. However, there is still a need for improvement in code translation functionality with efficient training techniques. In response to this, we introduce SteloCoder, a decoder-only StarCoder-based LLM designed specifically for multi-programming language-to-Python code translation. In particular, SteloCoder achieves C++, C#, JavaScript, Java, or PHP-to-Python code translation without specifying the input program"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15539","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/2310.15539/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":"2310.15539","created_at":"2026-07-05T07:24:21.060337+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.15539v2","created_at":"2026-07-05T07:24:21.060337+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15539","created_at":"2026-07-05T07:24:21.060337+00:00"},{"alias_kind":"pith_short_12","alias_value":"ASHNUPN7KN3K","created_at":"2026-07-05T07:24:21.060337+00:00"},{"alias_kind":"pith_short_16","alias_value":"ASHNUPN7KN3KNWFV","created_at":"2026-07-05T07:24:21.060337+00:00"},{"alias_kind":"pith_short_8","alias_value":"ASHNUPN7","created_at":"2026-07-05T07:24:21.060337+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10285","citing_title":"OpenRTLSet: A Fully Open-Source Dataset for Large Language Model-based Verilog Module Design","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07085","citing_title":"Porting Declarative UI to HarmonyOS: A Heuristic-guided LLM Approach","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27487","citing_title":"Low Rank Adaptation for Adversarial Perturbation","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09894","citing_title":"Deterministic vs. LLM-Controlled Orchestration for COBOL-to-Python Modernization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02195","citing_title":"Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02195","citing_title":"Beyond Translation Accuracy: Addressing False Failures in LLM-Based Code Translation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK","json":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK.json","graph_json":"https://pith.science/api/pith-number/ASHNUPN7KN3KNWFVS2R32A6QDK/graph.json","events_json":"https://pith.science/api/pith-number/ASHNUPN7KN3KNWFVS2R32A6QDK/events.json","paper":"https://pith.science/paper/ASHNUPN7"},"agent_actions":{"view_html":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK","download_json":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK.json","view_paper":"https://pith.science/paper/ASHNUPN7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.15539&json=true","fetch_graph":"https://pith.science/api/pith-number/ASHNUPN7KN3KNWFVS2R32A6QDK/graph.json","fetch_events":"https://pith.science/api/pith-number/ASHNUPN7KN3KNWFVS2R32A6QDK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK/action/storage_attestation","attest_author":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK/action/author_attestation","sign_citation":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK/action/citation_signature","submit_replication":"https://pith.science/pith/ASHNUPN7KN3KNWFVS2R32A6QDK/action/replication_record"}},"created_at":"2026-07-05T07:24:21.060337+00:00","updated_at":"2026-07-05T07:24:21.060337+00:00"}