{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:7ZSDLCUA5SELLPF3CERAGBZ4SZ","short_pith_number":"pith:7ZSDLCUA","schema_version":"1.0","canonical_sha256":"fe64358a80ec88b5bcbb112203073c965ae9e80d406cbefb7e806593ad0de6b0","source":{"kind":"arxiv","id":"2001.00059","version":3},"attestation_state":"computed","paper":{"title":"Learning and Evaluating Contextual Embedding of Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Aditya Kanade, Gogul Balakrishnan, Kensen Shi, Petros Maniatis","submitted_at":"2019-12-21T05:05:22Z","abstract_excerpt":"Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come with the development of pre-trained contextual embeddings, such as BERT, which can be fine-tuned for downstream tasks with less labeled data and training budget, while achieving better accuracies. However, there is no attempt yet to obtain a high-quality contextual embedding of source code, and to evaluate it on multiple program-understanding tasks simultaneo"},"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":"2001.00059","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2019-12-21T05:05:22Z","cross_cats_sorted":["cs.CL","cs.LG","cs.PL"],"title_canon_sha256":"6595ffc7b213aa0bc966baa358bc67eb9e853a3c8ce7fdca056c9391a03fd655","abstract_canon_sha256":"830ce02fd3626dbf997648b6e2f846ab5f391b7115fb380b484c6256bf7a1cf1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:27:44.380534Z","signature_b64":"XBL0EKiww+QlvPfcaXSowMs8643k1sLGlrs6wTD9KY/wQlr3/yS7RcvqOSJdVuLI74bxCPGYSfzO9yWTRV6nAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe64358a80ec88b5bcbb112203073c965ae9e80d406cbefb7e806593ad0de6b0","last_reissued_at":"2026-07-05T01:27:44.379566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:27:44.379566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning and Evaluating Contextual Embedding of Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.PL"],"primary_cat":"cs.SE","authors_text":"Aditya Kanade, Gogul Balakrishnan, Kensen Shi, Petros Maniatis","submitted_at":"2019-12-21T05:05:22Z","abstract_excerpt":"Recent research has achieved impressive results on understanding and improving source code by building up on machine-learning techniques developed for natural languages. A significant advancement in natural-language understanding has come with the development of pre-trained contextual embeddings, such as BERT, which can be fine-tuned for downstream tasks with less labeled data and training budget, while achieving better accuracies. However, there is no attempt yet to obtain a high-quality contextual embedding of source code, and to evaluate it on multiple program-understanding tasks simultaneo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.00059","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/2001.00059/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":"2001.00059","created_at":"2026-07-05T01:27:44.379640+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.00059v3","created_at":"2026-07-05T01:27:44.379640+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.00059","created_at":"2026-07-05T01:27:44.379640+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ZSDLCUA5SEL","created_at":"2026-07-05T01:27:44.379640+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ZSDLCUA5SELLPF3","created_at":"2026-07-05T01:27:44.379640+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ZSDLCUA","created_at":"2026-07-05T01:27:44.379640+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2009.08366","citing_title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2009.10297","citing_title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2002.08155","citing_title":"CodeBERT: A Pre-Trained Model for Programming and Natural Languages","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ","json":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ.json","graph_json":"https://pith.science/api/pith-number/7ZSDLCUA5SELLPF3CERAGBZ4SZ/graph.json","events_json":"https://pith.science/api/pith-number/7ZSDLCUA5SELLPF3CERAGBZ4SZ/events.json","paper":"https://pith.science/paper/7ZSDLCUA"},"agent_actions":{"view_html":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ","download_json":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ.json","view_paper":"https://pith.science/paper/7ZSDLCUA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.00059&json=true","fetch_graph":"https://pith.science/api/pith-number/7ZSDLCUA5SELLPF3CERAGBZ4SZ/graph.json","fetch_events":"https://pith.science/api/pith-number/7ZSDLCUA5SELLPF3CERAGBZ4SZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ/action/storage_attestation","attest_author":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ/action/author_attestation","sign_citation":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ/action/citation_signature","submit_replication":"https://pith.science/pith/7ZSDLCUA5SELLPF3CERAGBZ4SZ/action/replication_record"}},"created_at":"2026-07-05T01:27:44.379640+00:00","updated_at":"2026-07-05T01:27:44.379640+00:00"}