{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WS2VLVQ26QRAOOSA37AJ72MWRD","short_pith_number":"pith:WS2VLVQ2","schema_version":"1.0","canonical_sha256":"b4b555d61af422073a40dfc09fe99688d78493fe2d53a63f356fde173b92c2b4","source":{"kind":"arxiv","id":"2303.06808","version":2},"attestation_state":"computed","paper":{"title":"Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jianjun Zhao, Maxime Cordy, Mike Papadakis, Qiang Hu, Yuejun Guo, Yves Le Traon, Zeming Dong, Zhenya Zhang","submitted_at":"2023-03-13T01:47:05Z","abstract_excerpt":"Recent studies have demonstrated remarkable advancements in source code learning, which applies deep neural networks (DNNs) to tackle various software engineering tasks. Similar to other DNN-based domains, source code learning also requires massive high-quality training data to achieve the success of these applications. Data augmentation, a technique used to produce additional training data, is widely adopted in other domains (e.g. computer vision). However, the existing practice of data augmentation in source code learning is limited to simple syntax-preserved methods, such as code refactorin"},"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":"2303.06808","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2023-03-13T01:47:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0cb5fe12568bd3cc22e0d9d97c50d79fcbd1d0ee9bfd42f32d81d5d1d9c9a1d4","abstract_canon_sha256":"983e659fdf75c1754cfb49c8e059c9a9ddf16ef3f5bb8b6e8c8f1baa0b5a6988"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:21.345124Z","signature_b64":"0TuGOak8+3i8gxmzVmou+4BsTiZafXnUIMrZxJhVnbQmAWFSSvqetlO4HgJ6lMFx6bW0sBKSFvWmhuW3aQ3YDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4b555d61af422073a40dfc09fe99688d78493fe2d53a63f356fde173b92c2b4","last_reissued_at":"2026-07-05T10:10:21.344646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:21.344646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting Source Code Learning with Text-Oriented Data Augmentation: An Empirical Study","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Jianjun Zhao, Maxime Cordy, Mike Papadakis, Qiang Hu, Yuejun Guo, Yves Le Traon, Zeming Dong, Zhenya Zhang","submitted_at":"2023-03-13T01:47:05Z","abstract_excerpt":"Recent studies have demonstrated remarkable advancements in source code learning, which applies deep neural networks (DNNs) to tackle various software engineering tasks. Similar to other DNN-based domains, source code learning also requires massive high-quality training data to achieve the success of these applications. Data augmentation, a technique used to produce additional training data, is widely adopted in other domains (e.g. computer vision). However, the existing practice of data augmentation in source code learning is limited to simple syntax-preserved methods, such as code refactorin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.06808","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/2303.06808/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":"2303.06808","created_at":"2026-07-05T10:10:21.344703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.06808v2","created_at":"2026-07-05T10:10:21.344703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.06808","created_at":"2026-07-05T10:10:21.344703+00:00"},{"alias_kind":"pith_short_12","alias_value":"WS2VLVQ26QRA","created_at":"2026-07-05T10:10:21.344703+00:00"},{"alias_kind":"pith_short_16","alias_value":"WS2VLVQ26QRAOOSA","created_at":"2026-07-05T10:10:21.344703+00:00"},{"alias_kind":"pith_short_8","alias_value":"WS2VLVQ2","created_at":"2026-07-05T10:10:21.344703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00413","citing_title":"ClozeMaster: Fuzzing Rust Compiler by Harnessing LLMs for Infilling Masked Real Programs","ref_index":54,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD","json":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD.json","graph_json":"https://pith.science/api/pith-number/WS2VLVQ26QRAOOSA37AJ72MWRD/graph.json","events_json":"https://pith.science/api/pith-number/WS2VLVQ26QRAOOSA37AJ72MWRD/events.json","paper":"https://pith.science/paper/WS2VLVQ2"},"agent_actions":{"view_html":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD","download_json":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD.json","view_paper":"https://pith.science/paper/WS2VLVQ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.06808&json=true","fetch_graph":"https://pith.science/api/pith-number/WS2VLVQ26QRAOOSA37AJ72MWRD/graph.json","fetch_events":"https://pith.science/api/pith-number/WS2VLVQ26QRAOOSA37AJ72MWRD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD/action/storage_attestation","attest_author":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD/action/author_attestation","sign_citation":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD/action/citation_signature","submit_replication":"https://pith.science/pith/WS2VLVQ26QRAOOSA37AJ72MWRD/action/replication_record"}},"created_at":"2026-07-05T10:10:21.344703+00:00","updated_at":"2026-07-05T10:10:21.344703+00:00"}