{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SFF3BEEFYMACLXTRFTNRTSBA7S","short_pith_number":"pith:SFF3BEEF","schema_version":"1.0","canonical_sha256":"914bb09085c30025de712cdb19c820fcb27a7dcde8b5d63a11e88325208297f7","source":{"kind":"arxiv","id":"2005.08025","version":2},"attestation_state":"computed","paper":{"title":"IntelliCode Compose: Code Generation Using Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Alexey Svyatkovskiy, Neel Sundaresan, Shao Kun Deng, Shengyu Fu","submitted_at":"2020-05-16T15:47:53Z","abstract_excerpt":"In software development through integrated development environments (IDEs), code completion is one of the most widely used features. Nevertheless, majority of integrated development environments only support completion of methods and APIs, or arguments.\n  In this paper, we introduce IntelliCode Compose $-$ a general-purpose multilingual code completion tool which is capable of predicting sequences of code tokens of arbitrary types, generating up to entire lines of syntactically correct code. It leverages state-of-the-art generative transformer model trained on 1.2 billion lines of source code "},"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":"2005.08025","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-16T15:47:53Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"49ae01f05a080446e75c8b997ec5de4806cc58a6b4bee65fb7909a57431594ef","abstract_canon_sha256":"f7c06987fc8ab429914c50a5ffd4a232ad5d835719ee2452d5dc0670afe8c4ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:47:43.885517Z","signature_b64":"9KgGsfHr3WA0dPDaaxrQM5tiDHMBsoviNWe4gG2XvyCoHDiCR8zbux5KicQBG3lBMnnaQuYMzFN2GUD4bp3gBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"914bb09085c30025de712cdb19c820fcb27a7dcde8b5d63a11e88325208297f7","last_reissued_at":"2026-07-05T01:47:43.885107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:47:43.885107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IntelliCode Compose: Code Generation Using Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Alexey Svyatkovskiy, Neel Sundaresan, Shao Kun Deng, Shengyu Fu","submitted_at":"2020-05-16T15:47:53Z","abstract_excerpt":"In software development through integrated development environments (IDEs), code completion is one of the most widely used features. Nevertheless, majority of integrated development environments only support completion of methods and APIs, or arguments.\n  In this paper, we introduce IntelliCode Compose $-$ a general-purpose multilingual code completion tool which is capable of predicting sequences of code tokens of arbitrary types, generating up to entire lines of syntactically correct code. It leverages state-of-the-art generative transformer model trained on 1.2 billion lines of source code "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08025","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/2005.08025/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":"2005.08025","created_at":"2026-07-05T01:47:43.885163+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.08025v2","created_at":"2026-07-05T01:47:43.885163+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08025","created_at":"2026-07-05T01:47:43.885163+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFF3BEEFYMAC","created_at":"2026-07-05T01:47:43.885163+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFF3BEEFYMACLXTR","created_at":"2026-07-05T01:47:43.885163+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFF3BEEF","created_at":"2026-07-05T01:47:43.885163+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2102.04664","citing_title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2009.08366","citing_title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2009.10297","citing_title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18525","citing_title":"Towards Better Static Code Analysis Reports: Sentence Transformer-based Filtering of Non-Actionable Alerts","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S","json":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S.json","graph_json":"https://pith.science/api/pith-number/SFF3BEEFYMACLXTRFTNRTSBA7S/graph.json","events_json":"https://pith.science/api/pith-number/SFF3BEEFYMACLXTRFTNRTSBA7S/events.json","paper":"https://pith.science/paper/SFF3BEEF"},"agent_actions":{"view_html":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S","download_json":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S.json","view_paper":"https://pith.science/paper/SFF3BEEF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.08025&json=true","fetch_graph":"https://pith.science/api/pith-number/SFF3BEEFYMACLXTRFTNRTSBA7S/graph.json","fetch_events":"https://pith.science/api/pith-number/SFF3BEEFYMACLXTRFTNRTSBA7S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S/action/storage_attestation","attest_author":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S/action/author_attestation","sign_citation":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S/action/citation_signature","submit_replication":"https://pith.science/pith/SFF3BEEFYMACLXTRFTNRTSBA7S/action/replication_record"}},"created_at":"2026-07-05T01:47:43.885163+00:00","updated_at":"2026-07-05T01:47:43.885163+00:00"}