{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CBMDEUAEUHHJWLSTSLMBFKD5ZX","short_pith_number":"pith:CBMDEUAE","schema_version":"1.0","canonical_sha256":"1058325004a1ce9b2e5392d812a87dcdf94b6b5b1043f4b6da40d9e3315df73e","source":{"kind":"arxiv","id":"2202.06689","version":1},"attestation_state":"computed","paper":{"title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Georgios Gousios, Maliheh Izadi, Roberta Gismondi","submitted_at":"2022-02-14T13:26:54Z","abstract_excerpt":"Code completion is an essential feature of IDEs, yet current autocompleters are restricted to either grammar-based or NLP-based single token completions. Both approaches have significant drawbacks: grammar-based autocompletion is restricted in dynamically-typed language environments, whereas NLP-based autocompleters struggle to understand the semantics of the programming language and the developer's code context.\n  In this work, we present CodeFill, a language model for autocompletion that combines learned structure and naming information. Using a parallel Transformer architecture and multi-ta"},"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":"2202.06689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.SE","submitted_at":"2022-02-14T13:26:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"97d57523c410086f3e3e7af14e4292c4aed66a9d37fec0afff6ea1aa6e471fbf","abstract_canon_sha256":"2274e40ab44aed40cb7262b0474df8494f17c25c99f6f788367e11623438cab0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:41.025194Z","signature_b64":"ndIw0jTH/dpfVKrS7KQcnxP2vgBpDMF+lqfQfcJK1sbKy5Q5NGTn3ILRM/lhVu+z44nkxJQO3jQ9sKSGp4e/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1058325004a1ce9b2e5392d812a87dcdf94b6b5b1043f4b6da40d9e3315df73e","last_reissued_at":"2026-07-05T03:56:41.024766Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:41.024766Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CodeFill: Multi-token Code Completion by Jointly Learning from Structure and Naming Sequences","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SE","authors_text":"Georgios Gousios, Maliheh Izadi, Roberta Gismondi","submitted_at":"2022-02-14T13:26:54Z","abstract_excerpt":"Code completion is an essential feature of IDEs, yet current autocompleters are restricted to either grammar-based or NLP-based single token completions. Both approaches have significant drawbacks: grammar-based autocompletion is restricted in dynamically-typed language environments, whereas NLP-based autocompleters struggle to understand the semantics of the programming language and the developer's code context.\n  In this work, we present CodeFill, a language model for autocompletion that combines learned structure and naming information. Using a parallel Transformer architecture and multi-ta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.06689","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/2202.06689/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":"2202.06689","created_at":"2026-07-05T03:56:41.024820+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.06689v1","created_at":"2026-07-05T03:56:41.024820+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.06689","created_at":"2026-07-05T03:56:41.024820+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBMDEUAEUHHJ","created_at":"2026-07-05T03:56:41.024820+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBMDEUAEUHHJWLST","created_at":"2026-07-05T03:56:41.024820+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBMDEUAE","created_at":"2026-07-05T03:56:41.024820+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.05051","citing_title":"On the Generalizability of Transformer Models to Code Completions of Different Lengths","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX","json":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX.json","graph_json":"https://pith.science/api/pith-number/CBMDEUAEUHHJWLSTSLMBFKD5ZX/graph.json","events_json":"https://pith.science/api/pith-number/CBMDEUAEUHHJWLSTSLMBFKD5ZX/events.json","paper":"https://pith.science/paper/CBMDEUAE"},"agent_actions":{"view_html":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX","download_json":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX.json","view_paper":"https://pith.science/paper/CBMDEUAE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.06689&json=true","fetch_graph":"https://pith.science/api/pith-number/CBMDEUAEUHHJWLSTSLMBFKD5ZX/graph.json","fetch_events":"https://pith.science/api/pith-number/CBMDEUAEUHHJWLSTSLMBFKD5ZX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX/action/storage_attestation","attest_author":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX/action/author_attestation","sign_citation":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX/action/citation_signature","submit_replication":"https://pith.science/pith/CBMDEUAEUHHJWLSTSLMBFKD5ZX/action/replication_record"}},"created_at":"2026-07-05T03:56:41.024820+00:00","updated_at":"2026-07-05T03:56:41.024820+00:00"}