{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YQILV4AUDBEYEA5HQED7APISEV","short_pith_number":"pith:YQILV4AU","schema_version":"1.0","canonical_sha256":"c410baf01418498203a78107f03d12257b5b81fadb9f3ace56ad8b8a66268508","source":{"kind":"arxiv","id":"1805.11651","version":2},"attestation_state":"computed","paper":{"title":"Splitting source code identifiers using Bidirectional LSTM Recurrent Neural Network","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Egor Bulychev, Gabor Markowski, Konstantin Slavnov, Romain Keramitas, Vadim Markovtsev, Waren Long","submitted_at":"2018-05-26T06:46:55Z","abstract_excerpt":"Programmers make rich use of natural language in the source code they write through identifiers and comments. Source code identifiers are selected from a pool of tokens which are strongly related to the meaning, naming conventions, and context. These tokens are often combined to produce more precise and obvious designations. Such multi-part identifiers count for 97% of all naming tokens in the Public Git Archive - the largest dataset of Git repositories to date. We introduce a bidirectional LSTM recurrent neural network to detect subtokens in source code identifiers. We trained that network on"},"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":"1805.11651","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2018-05-26T06:46:55Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"9487f65117d56cbdc0ad1579c3142ffc094e157bf801114b4971cc914e468df8","abstract_canon_sha256":"2aa15212486ee78b17aedbfdd47263d9d96971ce882e9dd298e94dfe63c2e864"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:21.682747Z","signature_b64":"ko6ZBe2JvSM+smRPVn+eK8AYTTiCEinOwJSHw6ovefqya6BdBAan8MM03VBYRV/8ZJsQ5lxPc9WWsBCRWVggDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c410baf01418498203a78107f03d12257b5b81fadb9f3ace56ad8b8a66268508","last_reissued_at":"2026-05-18T00:10:21.682045Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:21.682045Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Splitting source code identifiers using Bidirectional LSTM Recurrent Neural Network","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.CL","authors_text":"Egor Bulychev, Gabor Markowski, Konstantin Slavnov, Romain Keramitas, Vadim Markovtsev, Waren Long","submitted_at":"2018-05-26T06:46:55Z","abstract_excerpt":"Programmers make rich use of natural language in the source code they write through identifiers and comments. Source code identifiers are selected from a pool of tokens which are strongly related to the meaning, naming conventions, and context. These tokens are often combined to produce more precise and obvious designations. Such multi-part identifiers count for 97% of all naming tokens in the Public Git Archive - the largest dataset of Git repositories to date. We introduce a bidirectional LSTM recurrent neural network to detect subtokens in source code identifiers. We trained that network on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.11651","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":""},"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":"1805.11651","created_at":"2026-05-18T00:10:21.682151+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.11651v2","created_at":"2026-05-18T00:10:21.682151+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.11651","created_at":"2026-05-18T00:10:21.682151+00:00"},{"alias_kind":"pith_short_12","alias_value":"YQILV4AUDBEY","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YQILV4AUDBEYEA5H","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YQILV4AU","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV","json":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV.json","graph_json":"https://pith.science/api/pith-number/YQILV4AUDBEYEA5HQED7APISEV/graph.json","events_json":"https://pith.science/api/pith-number/YQILV4AUDBEYEA5HQED7APISEV/events.json","paper":"https://pith.science/paper/YQILV4AU"},"agent_actions":{"view_html":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV","download_json":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV.json","view_paper":"https://pith.science/paper/YQILV4AU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.11651&json=true","fetch_graph":"https://pith.science/api/pith-number/YQILV4AUDBEYEA5HQED7APISEV/graph.json","fetch_events":"https://pith.science/api/pith-number/YQILV4AUDBEYEA5HQED7APISEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV/action/storage_attestation","attest_author":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV/action/author_attestation","sign_citation":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV/action/citation_signature","submit_replication":"https://pith.science/pith/YQILV4AUDBEYEA5HQED7APISEV/action/replication_record"}},"created_at":"2026-05-18T00:10:21.682151+00:00","updated_at":"2026-05-18T00:10:21.682151+00:00"}