{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:36V5RF6QNQDJQEN2CNJRDLD7BD","short_pith_number":"pith:36V5RF6Q","schema_version":"1.0","canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","source":{"kind":"arxiv","id":"1904.03061","version":1},"attestation_state":"computed","paper":{"title":"A Literature Study of Embeddings on Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Monperrus, Zimin Chen","submitted_at":"2019-04-05T13:37:42Z","abstract_excerpt":"Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The articles in this survey have been collected by asking authors of related work and with an extensive search on Google Scholar. Each article is categorized into five categories: 1. embedding of tokens 2. embedding of functions or methods 3. embedding of sequences or sets of method c"},"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":"1904.03061","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-04-05T13:37:42Z","cross_cats_sorted":["cs.PL","cs.SE","stat.ML"],"title_canon_sha256":"613065e98e7b35f64dcf555f292a21f9875e26214249e47a2406d98e9e94e880","abstract_canon_sha256":"47fa342cf604ec6275339df888ff33dd5d13fc65b642589011ea5d72f308fd1e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:18.729633Z","signature_b64":"MdeHfCq8BgJaEtRwo17d5g/37RBbMfo+xlB/KmrLTDCy1MDqv0XjL884YmQFRzZCMKLXq+Z6wFVPjjAxLsmoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfabd897d06c069811ba135311ac7f08f6eadbd49147bb462664a397f1ae7104","last_reissued_at":"2026-05-17T23:49:18.729091Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:18.729091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Literature Study of Embeddings on Source Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","cs.SE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Martin Monperrus, Zimin Chen","submitted_at":"2019-04-05T13:37:42Z","abstract_excerpt":"Natural language processing has improved tremendously after the success of word embedding techniques such as word2vec. Recently, the same idea has been applied on source code with encouraging results. In this survey, we aim to collect and discuss the usage of word embedding techniques on programs and source code. The articles in this survey have been collected by asking authors of related work and with an extensive search on Google Scholar. Each article is categorized into five categories: 1. embedding of tokens 2. embedding of functions or methods 3. embedding of sequences or sets of method c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03061","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":"1904.03061","created_at":"2026-05-17T23:49:18.729182+00:00"},{"alias_kind":"arxiv_version","alias_value":"1904.03061v1","created_at":"2026-05-17T23:49:18.729182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03061","created_at":"2026-05-17T23:49:18.729182+00:00"},{"alias_kind":"pith_short_12","alias_value":"36V5RF6QNQDJ","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_16","alias_value":"36V5RF6QNQDJQEN2","created_at":"2026-05-18T12:33:07.085635+00:00"},{"alias_kind":"pith_short_8","alias_value":"36V5RF6Q","created_at":"2026-05-18T12:33:07.085635+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.15412","citing_title":"Social Life of Code: Modeling Evolution through Code Embedding and Opinion Dynamics","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD","json":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD.json","graph_json":"https://pith.science/api/pith-number/36V5RF6QNQDJQEN2CNJRDLD7BD/graph.json","events_json":"https://pith.science/api/pith-number/36V5RF6QNQDJQEN2CNJRDLD7BD/events.json","paper":"https://pith.science/paper/36V5RF6Q"},"agent_actions":{"view_html":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD","download_json":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD.json","view_paper":"https://pith.science/paper/36V5RF6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1904.03061&json=true","fetch_graph":"https://pith.science/api/pith-number/36V5RF6QNQDJQEN2CNJRDLD7BD/graph.json","fetch_events":"https://pith.science/api/pith-number/36V5RF6QNQDJQEN2CNJRDLD7BD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/action/storage_attestation","attest_author":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/action/author_attestation","sign_citation":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/action/citation_signature","submit_replication":"https://pith.science/pith/36V5RF6QNQDJQEN2CNJRDLD7BD/action/replication_record"}},"created_at":"2026-05-17T23:49:18.729182+00:00","updated_at":"2026-05-17T23:49:18.729182+00:00"}