{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:5O7YTUYJE3GP6CJHRRDRMLWWRN","short_pith_number":"pith:5O7YTUYJ","schema_version":"1.0","canonical_sha256":"ebbf89d30926ccff09278c47162ed68b6d732f17ed64266f8b51637836f389f9","source":{"kind":"arxiv","id":"2003.07914","version":1},"attestation_state":"computed","paper":{"title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Andrea Janes, Charles Sutton, Hlib Babii, Rafael-Michael Karampatsis, Romain Robbes","submitted_at":"2020-03-17T19:48:41Z","abstract_excerpt":"Statistical language modeling techniques have successfully been applied to large source code corpora, yielding a variety of new software development tools, such as tools for code suggestion, improving readability, and API migration. A major issue with these techniques is that code introduces new vocabulary at a far higher rate than natural language, as new identifier names proliferate. Both large vocabularies and out-of-vocabulary issues severely affect Neural Language Models (NLMs) of source code, degrading their performance and rendering them unable to scale.\n  In this paper, we address this"},"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":"2003.07914","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-03-17T19:48:41Z","cross_cats_sorted":[],"title_canon_sha256":"6aed1ccdd542a01d85d8394490f9db18a28111fd5c872accb767bd169769cfa6","abstract_canon_sha256":"eb600b8e303aa56ff35958812820648ba1108d6442b4336e22f75779f8c39052"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:49:02.630091Z","signature_b64":"eyK7caSyHvDKCv8jqJz5M6i79Z6rafd0GMDNn/kaGpl8I7GxMrNRdeYUtjmrNI2EtyRCyFJ1UQhr85R8ZIZrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebbf89d30926ccff09278c47162ed68b6d732f17ed64266f8b51637836f389f9","last_reissued_at":"2026-07-05T00:49:02.629611Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:49:02.629611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Andrea Janes, Charles Sutton, Hlib Babii, Rafael-Michael Karampatsis, Romain Robbes","submitted_at":"2020-03-17T19:48:41Z","abstract_excerpt":"Statistical language modeling techniques have successfully been applied to large source code corpora, yielding a variety of new software development tools, such as tools for code suggestion, improving readability, and API migration. A major issue with these techniques is that code introduces new vocabulary at a far higher rate than natural language, as new identifier names proliferate. Both large vocabularies and out-of-vocabulary issues severely affect Neural Language Models (NLMs) of source code, degrading their performance and rendering them unable to scale.\n  In this paper, we address this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07914","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/2003.07914/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":"2003.07914","created_at":"2026-07-05T00:49:02.629684+00:00"},{"alias_kind":"arxiv_version","alias_value":"2003.07914v1","created_at":"2026-07-05T00:49:02.629684+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07914","created_at":"2026-07-05T00:49:02.629684+00:00"},{"alias_kind":"pith_short_12","alias_value":"5O7YTUYJE3GP","created_at":"2026-07-05T00:49:02.629684+00:00"},{"alias_kind":"pith_short_16","alias_value":"5O7YTUYJE3GP6CJH","created_at":"2026-07-05T00:49:02.629684+00:00"},{"alias_kind":"pith_short_8","alias_value":"5O7YTUYJ","created_at":"2026-07-05T00:49:02.629684+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"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":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN","json":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN.json","graph_json":"https://pith.science/api/pith-number/5O7YTUYJE3GP6CJHRRDRMLWWRN/graph.json","events_json":"https://pith.science/api/pith-number/5O7YTUYJE3GP6CJHRRDRMLWWRN/events.json","paper":"https://pith.science/paper/5O7YTUYJ"},"agent_actions":{"view_html":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN","download_json":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN.json","view_paper":"https://pith.science/paper/5O7YTUYJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2003.07914&json=true","fetch_graph":"https://pith.science/api/pith-number/5O7YTUYJE3GP6CJHRRDRMLWWRN/graph.json","fetch_events":"https://pith.science/api/pith-number/5O7YTUYJE3GP6CJHRRDRMLWWRN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN/action/storage_attestation","attest_author":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN/action/author_attestation","sign_citation":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN/action/citation_signature","submit_replication":"https://pith.science/pith/5O7YTUYJE3GP6CJHRRDRMLWWRN/action/replication_record"}},"created_at":"2026-07-05T00:49:02.629684+00:00","updated_at":"2026-07-05T00:49:02.629684+00:00"}