{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:35IEUEANROOOJYXCILETQIQ7GX","short_pith_number":"pith:35IEUEAN","schema_version":"1.0","canonical_sha256":"df504a100d8b9ce4e2e242c938221f35e1ac715991270face53d22b649ab6b6c","source":{"kind":"arxiv","id":"1911.09983","version":2},"attestation_state":"computed","paper":{"title":"TreeGen: A Tree-Based Transformer Architecture for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Lili Mou, Lu Zhang, Qihao Zhu, Yican Sun, Yingfei Xiong, Zeyu Sun","submitted_at":"2019-11-22T11:45:26Z","abstract_excerpt":"A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems. One is the long dependency problem, where a code element often depends on another far-away code element. A variable reference, for example, depends on its definition, which may appear quite a few lines before. The other problem is structure modeling, as programs contain rich structural information. In this paper, we propose a novel tree-based neural architect"},"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":"1911.09983","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-11-22T11:45:26Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"4180394904c0e444394da28f9179f6f3e5e237996a6c46773dd03891747fd409","abstract_canon_sha256":"ebb4a9912bcfbaaeab2fe8fbde86e60a824761bef46ec2aca88c337e7a8e232c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:43.463745Z","signature_b64":"YZxQNZuKB1wtqAxc0aEJoAdph1PnZmaWD9pZOy3n6CHUctcfF6WLr5ZSPAQpLlGdaliyg1uHt3AjaMjV2Y0MBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df504a100d8b9ce4e2e242c938221f35e1ac715991270face53d22b649ab6b6c","last_reissued_at":"2026-07-05T00:22:43.463308Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:43.463308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TreeGen: A Tree-Based Transformer Architecture for Code Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.LG","authors_text":"Lili Mou, Lu Zhang, Qihao Zhu, Yican Sun, Yingfei Xiong, Zeyu Sun","submitted_at":"2019-11-22T11:45:26Z","abstract_excerpt":"A code generation system generates programming language code based on an input natural language description. State-of-the-art approaches rely on neural networks for code generation. However, these code generators suffer from two problems. One is the long dependency problem, where a code element often depends on another far-away code element. A variable reference, for example, depends on its definition, which may appear quite a few lines before. The other problem is structure modeling, as programs contain rich structural information. In this paper, we propose a novel tree-based neural architect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.09983","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1911.09983/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1911.09983","created_at":"2026-07-05T00:22:43.463390+00:00"},{"alias_kind":"arxiv_version","alias_value":"1911.09983v2","created_at":"2026-07-05T00:22:43.463390+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.09983","created_at":"2026-07-05T00:22:43.463390+00:00"},{"alias_kind":"pith_short_12","alias_value":"35IEUEANROOO","created_at":"2026-07-05T00:22:43.463390+00:00"},{"alias_kind":"pith_short_16","alias_value":"35IEUEANROOOJYXC","created_at":"2026-07-05T00:22:43.463390+00:00"},{"alias_kind":"pith_short_8","alias_value":"35IEUEAN","created_at":"2026-07-05T00:22:43.463390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04003","citing_title":"Seamlessly Integrating Tree-Based Positional Embeddings into Transformer Models for Source Code Representation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX","json":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX.json","graph_json":"https://pith.science/api/pith-number/35IEUEANROOOJYXCILETQIQ7GX/graph.json","events_json":"https://pith.science/api/pith-number/35IEUEANROOOJYXCILETQIQ7GX/events.json","paper":"https://pith.science/paper/35IEUEAN"},"agent_actions":{"view_html":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX","download_json":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX.json","view_paper":"https://pith.science/paper/35IEUEAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1911.09983&json=true","fetch_graph":"https://pith.science/api/pith-number/35IEUEANROOOJYXCILETQIQ7GX/graph.json","fetch_events":"https://pith.science/api/pith-number/35IEUEANROOOJYXCILETQIQ7GX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX/action/storage_attestation","attest_author":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX/action/author_attestation","sign_citation":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX/action/citation_signature","submit_replication":"https://pith.science/pith/35IEUEANROOOJYXCILETQIQ7GX/action/replication_record"}},"created_at":"2026-07-05T00:22:43.463390+00:00","updated_at":"2026-07-05T00:22:43.463390+00:00"}