{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:2NEKVEI2CWOROWUZZVBCCGIMBX","short_pith_number":"pith:2NEKVEI2","schema_version":"1.0","canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","source":{"kind":"arxiv","id":"1904.11968","version":1},"attestation_state":"computed","paper":{"title":"Learning Semantic Vector Representations of Source Code via a Siamese Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Zhang, David Wehr, Eleanor Pence, Guilherme Ferreira, Halley Fede, John Walczyk, Joseph Hughes","submitted_at":"2019-04-26T17:52:06Z","abstract_excerpt":"The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create vectors which capture the semantics of code. We evaluate the quality of embeddings by identifying which problem from a programming competition the code solves. Our model significantly outperforms a bag-of-tokens embedding, providing promising results for improving code embeddings"},"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":"1904.11968","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-26T17:52:06Z","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"title_canon_sha256":"7b3c096edcae673e9a55f553ed92644f4d11810ef2d986e65f62e2b7f95ea562","abstract_canon_sha256":"38d64fe52b74943d2d147cdd00b222e709131fc1be47514e0e3c8056776a1965"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:40.501155Z","signature_b64":"Gw8ynr1aYrWz9Etwk5AKycm7WK7gSkg7gYg6nuFpr7dEF6s6fD5mvTWdypZ5deCNYEc344kdi851oef028aTAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d348aa911a159d175a99cd4221190c0df6b5f87eec41464792fb056fea0eb5ff","last_reissued_at":"2026-05-17T23:47:40.500609Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:40.500609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Semantic Vector Representations of Source Code via a Siamese Neural Network","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bo Zhang, David Wehr, Eleanor Pence, Guilherme Ferreira, Halley Fede, John Walczyk, Joseph Hughes","submitted_at":"2019-04-26T17:52:06Z","abstract_excerpt":"The abundance of open-source code, coupled with the success of recent advances in deep learning for natural language processing, has given rise to a promising new application of machine learning to source code. In this work, we explore the use of a Siamese recurrent neural network model on Python source code to create vectors which capture the semantics of code. We evaluate the quality of embeddings by identifying which problem from a programming competition the code solves. Our model significantly outperforms a bag-of-tokens embedding, providing promising results for improving code embeddings"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.11968","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":""},"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":"1904.11968","created_at":"2026-05-17T23:47:40.500676+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.11968v1","created_at":"2026-05-17T23:47:40.500676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.11968","created_at":"2026-05-17T23:47:40.500676+00:00"},{"alias_kind":"pith_short_12","alias_value":"2NEKVEI2CWOR","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"2NEKVEI2CWOROWUZ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"2NEKVEI2","created_at":"2026-05-18T12:33:07.085635+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/2NEKVEI2CWOROWUZZVBCCGIMBX","json":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX.json","graph_json":"https://pith.science/api/pith-number/2NEKVEI2CWOROWUZZVBCCGIMBX/graph.json","events_json":"https://pith.science/api/pith-number/2NEKVEI2CWOROWUZZVBCCGIMBX/events.json","paper":"https://pith.science/paper/2NEKVEI2"},"agent_actions":{"view_html":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX","download_json":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX.json","view_paper":"https://pith.science/paper/2NEKVEI2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.11968&json=true","fetch_graph":"https://pith.science/api/pith-number/2NEKVEI2CWOROWUZZVBCCGIMBX/graph.json","fetch_events":"https://pith.science/api/pith-number/2NEKVEI2CWOROWUZZVBCCGIMBX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/action/storage_attestation","attest_author":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/action/author_attestation","sign_citation":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/action/citation_signature","submit_replication":"https://pith.science/pith/2NEKVEI2CWOROWUZZVBCCGIMBX/action/replication_record"}},"created_at":"2026-05-17T23:47:40.500676+00:00","updated_at":"2026-05-17T23:47:40.500676+00:00"}