{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5O7YTUYJE3GP6CJHRRDRMLWWRN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"eb600b8e303aa56ff35958812820648ba1108d6442b4336e22f75779f8c39052","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-03-17T19:48:41Z","title_canon_sha256":"6aed1ccdd542a01d85d8394490f9db18a28111fd5c872accb767bd169769cfa6"},"schema_version":"1.0","source":{"id":"2003.07914","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.07914","created_at":"2026-07-05T00:49:02Z"},{"alias_kind":"arxiv_version","alias_value":"2003.07914v1","created_at":"2026-07-05T00:49:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.07914","created_at":"2026-07-05T00:49:02Z"},{"alias_kind":"pith_short_12","alias_value":"5O7YTUYJE3GP","created_at":"2026-07-05T00:49:02Z"},{"alias_kind":"pith_short_16","alias_value":"5O7YTUYJE3GP6CJH","created_at":"2026-07-05T00:49:02Z"},{"alias_kind":"pith_short_8","alias_value":"5O7YTUYJ","created_at":"2026-07-05T00:49:02Z"}],"graph_snapshots":[{"event_id":"sha256:d601550b8fa95f95f4164929d4a0b4ecf39af3cd7dc11e27c4d14094c07fbd65","target":"graph","created_at":"2026-07-05T00:49:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2003.07914/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Andrea Janes, Charles Sutton, Hlib Babii, Rafael-Michael Karampatsis, Romain Robbes","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-03-17T19:48:41Z","title":"Big Code != Big Vocabulary: Open-Vocabulary Models for Source Code"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.07914","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:74ca9a9035e3784ac0fcab7aaa20174a9f1fd1bc4406e92f172d8f2edaabfea6","target":"record","created_at":"2026-07-05T00:49:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"eb600b8e303aa56ff35958812820648ba1108d6442b4336e22f75779f8c39052","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2020-03-17T19:48:41Z","title_canon_sha256":"6aed1ccdd542a01d85d8394490f9db18a28111fd5c872accb767bd169769cfa6"},"schema_version":"1.0","source":{"id":"2003.07914","kind":"arxiv","version":1}},"canonical_sha256":"ebbf89d30926ccff09278c47162ed68b6d732f17ed64266f8b51637836f389f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebbf89d30926ccff09278c47162ed68b6d732f17ed64266f8b51637836f389f9","first_computed_at":"2026-07-05T00:49:02.629611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:49:02.629611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eyK7caSyHvDKCv8jqJz5M6i79Z6rafd0GMDNn/kaGpl8I7GxMrNRdeYUtjmrNI2EtyRCyFJ1UQhr85R8ZIZrBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:49:02.630091Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.07914","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:74ca9a9035e3784ac0fcab7aaa20174a9f1fd1bc4406e92f172d8f2edaabfea6","sha256:d601550b8fa95f95f4164929d4a0b4ecf39af3cd7dc11e27c4d14094c07fbd65"],"state_sha256":"fd46623cf7a62caa6c6fbc4c8aa5381b748dab3195f8ac92586242e69d0a66b0"}