{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YYGFMGATBRAZCIF2ECVXLIWRBB","short_pith_number":"pith:YYGFMGAT","schema_version":"1.0","canonical_sha256":"c60c5618130c419120ba20ab75a2d1087d324d6984ec1da8598dd360d3864f6d","source":{"kind":"arxiv","id":"2402.01935","version":1},"attestation_state":"computed","paper":{"title":"Code Representation Learning At Scale","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Dan Roth, Dejiao Zhang, Hantian Ding, Ming Tan, Ramesh Nallapati, Wasi Ahmad, Xiaofei Ma","submitted_at":"2024-02-02T22:19:15Z","abstract_excerpt":"Recent studies have shown that code language models at scale demonstrate significant performance gains on downstream tasks, i.e., code generation. However, most of the existing works on code representation learning train models at a hundred million parameter scale using very limited pretraining corpora. In this work, we fuel code representation learning with a vast amount of code data via a two-stage pretraining scheme. We first train the encoders via a mix that leverages both randomness in masking language modeling and the structure aspect of programming language. We then enhance the represen"},"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":"2402.01935","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-02T22:19:15Z","cross_cats_sorted":[],"title_canon_sha256":"5d36babcd96c9b48e95ba73125b70077934b1b690671be284db59c5ca8cd41b2","abstract_canon_sha256":"c7beee13366e320eb7625a78efc3f2e1cbb0ffb0b77d319cf65b04917b9cf006"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:08.382660Z","signature_b64":"UXemiVKP+uvpJORZeaUxJsdLVU9+E35IT3TJhDXdQmQXx//N5N7XKo26i6/JbKm0dsRV+tr2bZzvGS0w9jsOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c60c5618130c419120ba20ab75a2d1087d324d6984ec1da8598dd360d3864f6d","last_reissued_at":"2026-07-05T07:41:08.382126Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:08.382126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Code Representation Learning At Scale","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Xiang, Dan Roth, Dejiao Zhang, Hantian Ding, Ming Tan, Ramesh Nallapati, Wasi Ahmad, Xiaofei Ma","submitted_at":"2024-02-02T22:19:15Z","abstract_excerpt":"Recent studies have shown that code language models at scale demonstrate significant performance gains on downstream tasks, i.e., code generation. However, most of the existing works on code representation learning train models at a hundred million parameter scale using very limited pretraining corpora. In this work, we fuel code representation learning with a vast amount of code data via a two-stage pretraining scheme. We first train the encoders via a mix that leverages both randomness in masking language modeling and the structure aspect of programming language. We then enhance the represen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01935","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.01935/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":"2402.01935","created_at":"2026-07-05T07:41:08.382183+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01935v1","created_at":"2026-07-05T07:41:08.382183+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01935","created_at":"2026-07-05T07:41:08.382183+00:00"},{"alias_kind":"pith_short_12","alias_value":"YYGFMGATBRAZ","created_at":"2026-07-05T07:41:08.382183+00:00"},{"alias_kind":"pith_short_16","alias_value":"YYGFMGATBRAZCIF2","created_at":"2026-07-05T07:41:08.382183+00:00"},{"alias_kind":"pith_short_8","alias_value":"YYGFMGAT","created_at":"2026-07-05T07:41:08.382183+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.22018","citing_title":"Do Papers Tell the Whole Story? A Benchmark and Framework for Uncovering Hidden Implementation Gaps in Bioinformatics","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16021","citing_title":"Neurosymbolic Repo-level Code Localization","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB","json":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB.json","graph_json":"https://pith.science/api/pith-number/YYGFMGATBRAZCIF2ECVXLIWRBB/graph.json","events_json":"https://pith.science/api/pith-number/YYGFMGATBRAZCIF2ECVXLIWRBB/events.json","paper":"https://pith.science/paper/YYGFMGAT"},"agent_actions":{"view_html":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB","download_json":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB.json","view_paper":"https://pith.science/paper/YYGFMGAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01935&json=true","fetch_graph":"https://pith.science/api/pith-number/YYGFMGATBRAZCIF2ECVXLIWRBB/graph.json","fetch_events":"https://pith.science/api/pith-number/YYGFMGATBRAZCIF2ECVXLIWRBB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB/action/storage_attestation","attest_author":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB/action/author_attestation","sign_citation":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB/action/citation_signature","submit_replication":"https://pith.science/pith/YYGFMGATBRAZCIF2ECVXLIWRBB/action/replication_record"}},"created_at":"2026-07-05T07:41:08.382183+00:00","updated_at":"2026-07-05T07:41:08.382183+00:00"}