{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FJXGFQ2E4YXG5U3DLEJRXRCLPZ","short_pith_number":"pith:FJXGFQ2E","schema_version":"1.0","canonical_sha256":"2a6e62c344e62e6ed36359131bc44b7e69bc8b8e8e83e7e1a247211f91357d64","source":{"kind":"arxiv","id":"2202.13972","version":2},"attestation_state":"computed","paper":{"title":"The impact of lexical and grammatical processing on generating code from natural language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beno\\^it Crabb\\'e, Nathana\\\"el Beau","submitted_at":"2022-02-28T17:23:30Z","abstract_excerpt":"Considering the seq2seq architecture of TranX for natural language to code translation, we identify four key components of importance: grammatical constraints, lexical preprocessing, input representations, and copy mechanisms. To study the impact of these components, we use a state-of-the-art architecture that relies on BERT encoder and a grammar-based decoder for which a formalization is provided. The paper highlights the importance of the lexical substitution component in the current natural language to code systems."},"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":"2202.13972","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-28T17:23:30Z","cross_cats_sorted":[],"title_canon_sha256":"7a2f0b2f74bf6e6789bce2e883ace43759d058fc781d310151cd0c474fa13830","abstract_canon_sha256":"8d5f6db45475303e2dcac97066fd70da0a3a4b438e0fa72cb9e7ce9ddf92a1af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:38.878118Z","signature_b64":"mns+ynLygAWNWRSqYMnxpnI+JpY4Vh6+RTbk0ALs671R0Ew+2tvwtX5WHgJp4G3BMFiCIVLeka4IRb5GiOHgBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a6e62c344e62e6ed36359131bc44b7e69bc8b8e8e83e7e1a247211f91357d64","last_reissued_at":"2026-07-05T04:05:38.877681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:38.877681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The impact of lexical and grammatical processing on generating code from natural language","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Beno\\^it Crabb\\'e, Nathana\\\"el Beau","submitted_at":"2022-02-28T17:23:30Z","abstract_excerpt":"Considering the seq2seq architecture of TranX for natural language to code translation, we identify four key components of importance: grammatical constraints, lexical preprocessing, input representations, and copy mechanisms. To study the impact of these components, we use a state-of-the-art architecture that relies on BERT encoder and a grammar-based decoder for which a formalization is provided. The paper highlights the importance of the lexical substitution component in the current natural language to code systems."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.13972","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/2202.13972/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":"2202.13972","created_at":"2026-07-05T04:05:38.877738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.13972v2","created_at":"2026-07-05T04:05:38.877738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.13972","created_at":"2026-07-05T04:05:38.877738+00:00"},{"alias_kind":"pith_short_12","alias_value":"FJXGFQ2E4YXG","created_at":"2026-07-05T04:05:38.877738+00:00"},{"alias_kind":"pith_short_16","alias_value":"FJXGFQ2E4YXG5U3D","created_at":"2026-07-05T04:05:38.877738+00:00"},{"alias_kind":"pith_short_8","alias_value":"FJXGFQ2E","created_at":"2026-07-05T04:05:38.877738+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/FJXGFQ2E4YXG5U3DLEJRXRCLPZ","json":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ.json","graph_json":"https://pith.science/api/pith-number/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/graph.json","events_json":"https://pith.science/api/pith-number/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/events.json","paper":"https://pith.science/paper/FJXGFQ2E"},"agent_actions":{"view_html":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ","download_json":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ.json","view_paper":"https://pith.science/paper/FJXGFQ2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.13972&json=true","fetch_graph":"https://pith.science/api/pith-number/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/graph.json","fetch_events":"https://pith.science/api/pith-number/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/action/storage_attestation","attest_author":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/action/author_attestation","sign_citation":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/action/citation_signature","submit_replication":"https://pith.science/pith/FJXGFQ2E4YXG5U3DLEJRXRCLPZ/action/replication_record"}},"created_at":"2026-07-05T04:05:38.877738+00:00","updated_at":"2026-07-05T04:05:38.877738+00:00"}