{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:IHSPCXKB5AIZTMCMYXUHMJBZGL","short_pith_number":"pith:IHSPCXKB","schema_version":"1.0","canonical_sha256":"41e4f15d41e81199b04cc5e876243932c8017ebf2d9faa5f6f96121209dbc0c9","source":{"kind":"arxiv","id":"1803.09473","version":5},"attestation_state":"computed","paper":{"title":"code2vec: Learning Distributed Representations of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eran Yahav, Meital Zilberstein, Omer Levy, Uri Alon","submitted_at":"2018-03-26T09:05:30Z","abstract_excerpt":"We present a neural model for representing snippets of code as continuous distributed vectors (\"code embeddings\"). The main idea is to represent a code snippet as a single fixed-length $\\textit{code vector}$, which can be used to predict semantic properties of the snippet. This is performed by decomposing code to a collection of paths in its abstract syntax tree, and learning the atomic representation of each path $\\textit{simultaneously}$ with learning how to aggregate a set of them. We demonstrate the effectiveness of our approach by using it to predict a method's name from the vector repres"},"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":"1803.09473","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-03-26T09:05:30Z","cross_cats_sorted":["cs.AI","cs.PL","stat.ML"],"title_canon_sha256":"89a12c9704f3fd0bea2c135de1a1aa5364ca811724930e37d7f0a1c2f302ed2e","abstract_canon_sha256":"47bd634a508ccb5ac5307fa3053b8ebfdc1aa2923fdb3f2c768a92a030573dbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:01.429064Z","signature_b64":"ABuMcyVYQxVoFcv7nK6LTh0K2ZSS6SxmG55tIuY2H3OswRTSBhy/AS0xi8xm5gDLdvbmcb9z48OWT9khIZgwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41e4f15d41e81199b04cc5e876243932c8017ebf2d9faa5f6f96121209dbc0c9","last_reissued_at":"2026-05-18T00:02:01.428254Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:01.428254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"code2vec: Learning Distributed Representations of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eran Yahav, Meital Zilberstein, Omer Levy, Uri Alon","submitted_at":"2018-03-26T09:05:30Z","abstract_excerpt":"We present a neural model for representing snippets of code as continuous distributed vectors (\"code embeddings\"). The main idea is to represent a code snippet as a single fixed-length $\\textit{code vector}$, which can be used to predict semantic properties of the snippet. This is performed by decomposing code to a collection of paths in its abstract syntax tree, and learning the atomic representation of each path $\\textit{simultaneously}$ with learning how to aggregate a set of them. We demonstrate the effectiveness of our approach by using it to predict a method's name from the vector repres"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.09473","kind":"arxiv","version":5},"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":"1803.09473","created_at":"2026-05-18T00:02:01.428402+00:00"},{"alias_kind":"arxiv_version","alias_value":"1803.09473v5","created_at":"2026-05-18T00:02:01.428402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.09473","created_at":"2026-05-18T00:02:01.428402+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHSPCXKB5AIZ","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHSPCXKB5AIZTMCM","created_at":"2026-05-18T12:32:31.084164+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHSPCXKB","created_at":"2026-05-18T12:32:31.084164+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":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL","json":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL.json","graph_json":"https://pith.science/api/pith-number/IHSPCXKB5AIZTMCMYXUHMJBZGL/graph.json","events_json":"https://pith.science/api/pith-number/IHSPCXKB5AIZTMCMYXUHMJBZGL/events.json","paper":"https://pith.science/paper/IHSPCXKB"},"agent_actions":{"view_html":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL","download_json":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL.json","view_paper":"https://pith.science/paper/IHSPCXKB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1803.09473&json=true","fetch_graph":"https://pith.science/api/pith-number/IHSPCXKB5AIZTMCMYXUHMJBZGL/graph.json","fetch_events":"https://pith.science/api/pith-number/IHSPCXKB5AIZTMCMYXUHMJBZGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL/action/storage_attestation","attest_author":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL/action/author_attestation","sign_citation":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL/action/citation_signature","submit_replication":"https://pith.science/pith/IHSPCXKB5AIZTMCMYXUHMJBZGL/action/replication_record"}},"created_at":"2026-05-18T00:02:01.428402+00:00","updated_at":"2026-05-18T00:02:01.428402+00:00"}