{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:DPTVKY2IYJ7WMOJCOZUAAZBGFJ","short_pith_number":"pith:DPTVKY2I","schema_version":"1.0","canonical_sha256":"1be7556348c27f66392276680064262a65a68138732eea4afcb1947b174da5c7","source":{"kind":"arxiv","id":"1808.01400","version":6},"attestation_state":"computed","paper":{"title":"code2seq: Generating Sequences from Structured Representations of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eran Yahav, Omer Levy, Shaked Brody, Uri Alon","submitted_at":"2018-08-04T01:26:07Z","abstract_excerpt":"The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine translation (NMT), have achieved state-of-the-art performance on these tasks by treating source code as a sequence of tokens. We present ${\\rm {\\scriptsize CODE2SEQ}}$: an alternative approach that leverages the syntactic structure of programming languages to better encode source code. Our model represents a code snippet as the set of compositional paths in its abst"},"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":"1808.01400","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-04T01:26:07Z","cross_cats_sorted":["cs.PL","stat.ML"],"title_canon_sha256":"0bc637bfa0073ae4664c6a09d75fe04e9ffa9b3ee6bde366de758025a9c234a4","abstract_canon_sha256":"6ae24cdb0da93608ed6a58ed4cecc90f50029f26a388b332cc9554f9934a8b01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:53:02.763355Z","signature_b64":"eSCau+l0D5o4x4nvdey/JmRMDvk6delAKjdfbchqcCrzmI3ru4iH+fhb3WQtQXZoUI1a8/XPuj4abG/keAXKAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1be7556348c27f66392276680064262a65a68138732eea4afcb1947b174da5c7","last_reissued_at":"2026-05-17T23:53:02.762784Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:53:02.762784Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"code2seq: Generating Sequences from Structured Representations of Code","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Eran Yahav, Omer Levy, Shaked Brody, Uri Alon","submitted_at":"2018-08-04T01:26:07Z","abstract_excerpt":"The ability to generate natural language sequences from source code snippets has a variety of applications such as code summarization, documentation, and retrieval. Sequence-to-sequence (seq2seq) models, adopted from neural machine translation (NMT), have achieved state-of-the-art performance on these tasks by treating source code as a sequence of tokens. We present ${\\rm {\\scriptsize CODE2SEQ}}$: an alternative approach that leverages the syntactic structure of programming languages to better encode source code. Our model represents a code snippet as the set of compositional paths in its abst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.01400","kind":"arxiv","version":6},"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":"1808.01400","created_at":"2026-05-17T23:53:02.762889+00:00"},{"alias_kind":"arxiv_version","alias_value":"1808.01400v6","created_at":"2026-05-17T23:53:02.762889+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.01400","created_at":"2026-05-17T23:53:02.762889+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPTVKY2IYJ7W","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPTVKY2IYJ7WMOJC","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPTVKY2I","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":5,"sample":[{"citing_arxiv_id":"1907.02136","citing_title":"Learning Blended, Precise Semantic Program Embeddings","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2304.09655","citing_title":"How Secure is Code Generated by ChatGPT?","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2602.15412","citing_title":"Social Life of Code: Modeling Evolution through Code Embedding and Opinion Dynamics","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2009.08366","citing_title":"GraphCodeBERT: Pre-training Code Representations with Data Flow","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2009.10297","citing_title":"CodeBLEU: a Method for Automatic Evaluation of Code Synthesis","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"1909.09436","citing_title":"CodeSearchNet Challenge: Evaluating the State of Semantic Code Search","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07974","citing_title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","ref_index":241,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ","json":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ.json","graph_json":"https://pith.science/api/pith-number/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/graph.json","events_json":"https://pith.science/api/pith-number/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/events.json","paper":"https://pith.science/paper/DPTVKY2I"},"agent_actions":{"view_html":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ","download_json":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ.json","view_paper":"https://pith.science/paper/DPTVKY2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1808.01400&json=true","fetch_graph":"https://pith.science/api/pith-number/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/action/storage_attestation","attest_author":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/action/author_attestation","sign_citation":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/action/citation_signature","submit_replication":"https://pith.science/pith/DPTVKY2IYJ7WMOJCOZUAAZBGFJ/action/replication_record"}},"created_at":"2026-05-17T23:53:02.762889+00:00","updated_at":"2026-05-17T23:53:02.762889+00:00"}