{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:VQLLHZSDEDL37Z7WSFLXDFNQNN","short_pith_number":"pith:VQLLHZSD","schema_version":"1.0","canonical_sha256":"ac16b3e64320d7bfe7f691577195b06b64c47c58c251f534e15cb32e3ce0d797","source":{"kind":"arxiv","id":"2108.11590","version":2},"attestation_state":"computed","paper":{"title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Kai-Wei Chang, Md Golam Rahman Tushar, Saikat Chakraborty, Wasi Uddin Ahmad","submitted_at":"2021-08-26T05:44:20Z","abstract_excerpt":"Program translation refers to migrating source code from one programming language to another. It has tremendous practical value in software development, as porting software across languages is time-consuming and costly. Automating program translation is of paramount importance in software migration, and recently researchers explored unsupervised approaches due to the unavailability of parallel corpora. However, the availability of pre-trained language models for programming languages enables supervised fine-tuning with a small number of labeled examples. Therefore, we present AVATAR, a collect"},"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":"2108.11590","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2021-08-26T05:44:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"3a16b77c1a56e546a7a20e4177cd64b66fba28350e358103f069d631c90d301d","abstract_canon_sha256":"99cc261cf22b2c9e80f5ef98e9330923e9915993dcdb1318b97d14dfd85a5ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:07:08.054752Z","signature_b64":"B2TGIqK89t8iCSdNt2aCBbEmlfk/ofxaM8M8w+XGivdNPthRiR3iJNl9exputNUEgKCd5Y1qum90qlWlhj5jAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac16b3e64320d7bfe7f691577195b06b64c47c58c251f534e15cb32e3ce0d797","last_reissued_at":"2026-07-05T06:07:08.054297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:07:08.054297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AVATAR: A Parallel Corpus for Java-Python Program Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Kai-Wei Chang, Md Golam Rahman Tushar, Saikat Chakraborty, Wasi Uddin Ahmad","submitted_at":"2021-08-26T05:44:20Z","abstract_excerpt":"Program translation refers to migrating source code from one programming language to another. It has tremendous practical value in software development, as porting software across languages is time-consuming and costly. Automating program translation is of paramount importance in software migration, and recently researchers explored unsupervised approaches due to the unavailability of parallel corpora. However, the availability of pre-trained language models for programming languages enables supervised fine-tuning with a small number of labeled examples. Therefore, we present AVATAR, a collect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11590","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/2108.11590/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":"2108.11590","created_at":"2026-07-05T06:07:08.054376+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.11590v2","created_at":"2026-07-05T06:07:08.054376+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11590","created_at":"2026-07-05T06:07:08.054376+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQLLHZSDEDL3","created_at":"2026-07-05T06:07:08.054376+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQLLHZSDEDL37Z7W","created_at":"2026-07-05T06:07:08.054376+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQLLHZSD","created_at":"2026-07-05T06:07:08.054376+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2402.09664","citing_title":"CodeMind: Evaluating Large Language Models for Code Reasoning","ref_index":18,"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":17,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14917","citing_title":"Evaluating Code Reasoning Abilities of Large Language Models Under Real-World Settings","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13896","citing_title":"Neural Code Translation of Legacy Code: APL to C#","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":64,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN","json":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN.json","graph_json":"https://pith.science/api/pith-number/VQLLHZSDEDL37Z7WSFLXDFNQNN/graph.json","events_json":"https://pith.science/api/pith-number/VQLLHZSDEDL37Z7WSFLXDFNQNN/events.json","paper":"https://pith.science/paper/VQLLHZSD"},"agent_actions":{"view_html":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN","download_json":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN.json","view_paper":"https://pith.science/paper/VQLLHZSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.11590&json=true","fetch_graph":"https://pith.science/api/pith-number/VQLLHZSDEDL37Z7WSFLXDFNQNN/graph.json","fetch_events":"https://pith.science/api/pith-number/VQLLHZSDEDL37Z7WSFLXDFNQNN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN/action/storage_attestation","attest_author":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN/action/author_attestation","sign_citation":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN/action/citation_signature","submit_replication":"https://pith.science/pith/VQLLHZSDEDL37Z7WSFLXDFNQNN/action/replication_record"}},"created_at":"2026-07-05T06:07:08.054376+00:00","updated_at":"2026-07-05T06:07:08.054376+00:00"}