{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:2SORW7GSCOKGM7W37MYZOB3YV7","short_pith_number":"pith:2SORW7GS","schema_version":"1.0","canonical_sha256":"d49d1b7cd21394667edbfb31970778affce7a0487cb2e0eb8ca4c6646837485f","source":{"kind":"arxiv","id":"1805.04276","version":2},"attestation_state":"computed","paper":{"title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Devlin, Matthew Hausknecht, Pushmeet Kohli, Rishabh Singh, Rudy Bunel","submitted_at":"2018-05-11T08:45:24Z","abstract_excerpt":"Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are trained to maximize the likelihood of known reference programs. While achieving impressive results, this strategy has two key limitations. First, it ignores Program Aliasing: the fact that many different programs may satisfy a given specification (especially with incomplete speci"},"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":"1805.04276","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-05-11T08:45:24Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"0ddd14097f9cb4d78a50e7115c77e856b61a196d4f2e450acef00afe4cd92bc3","abstract_canon_sha256":"c73468eec9dfe727bbb948329364652e70dd39769d95dd80de5429de95936a3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:15:27.485419Z","signature_b64":"z5pnWxqftpSwBucuBxv20W75/aeyt54iLZlSECtPp3E8jOw2o46rAsok8CuulAS5MtnpaJxJMBUx6L0KJh6XBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d49d1b7cd21394667edbfb31970778affce7a0487cb2e0eb8ca4c6646837485f","last_reissued_at":"2026-05-18T00:15:27.484750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:15:27.484750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Grammar and Reinforcement Learning for Neural Program Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Devlin, Matthew Hausknecht, Pushmeet Kohli, Rishabh Singh, Rudy Bunel","submitted_at":"2018-05-11T08:45:24Z","abstract_excerpt":"Program synthesis is the task of automatically generating a program consistent with a specification. Recent years have seen proposal of a number of neural approaches for program synthesis, many of which adopt a sequence generation paradigm similar to neural machine translation, in which sequence-to-sequence models are trained to maximize the likelihood of known reference programs. While achieving impressive results, this strategy has two key limitations. First, it ignores Program Aliasing: the fact that many different programs may satisfy a given specification (especially with incomplete speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04276","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":""},"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":"1805.04276","created_at":"2026-05-18T00:15:27.484860+00:00"},{"alias_kind":"arxiv_version","alias_value":"1805.04276v2","created_at":"2026-05-18T00:15:27.484860+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04276","created_at":"2026-05-18T00:15:27.484860+00:00"},{"alias_kind":"pith_short_12","alias_value":"2SORW7GSCOKG","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_16","alias_value":"2SORW7GSCOKGM7W3","created_at":"2026-05-18T12:32:02.567920+00:00"},{"alias_kind":"pith_short_8","alias_value":"2SORW7GS","created_at":"2026-05-18T12:32:02.567920+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2304.10726","citing_title":"Usenix'23 Extended Version: Smart Learning to Find Dumb Contracts","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7","json":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7.json","graph_json":"https://pith.science/api/pith-number/2SORW7GSCOKGM7W37MYZOB3YV7/graph.json","events_json":"https://pith.science/api/pith-number/2SORW7GSCOKGM7W37MYZOB3YV7/events.json","paper":"https://pith.science/paper/2SORW7GS"},"agent_actions":{"view_html":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7","download_json":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7.json","view_paper":"https://pith.science/paper/2SORW7GS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1805.04276&json=true","fetch_graph":"https://pith.science/api/pith-number/2SORW7GSCOKGM7W37MYZOB3YV7/graph.json","fetch_events":"https://pith.science/api/pith-number/2SORW7GSCOKGM7W37MYZOB3YV7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7/action/storage_attestation","attest_author":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7/action/author_attestation","sign_citation":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7/action/citation_signature","submit_replication":"https://pith.science/pith/2SORW7GSCOKGM7W37MYZOB3YV7/action/replication_record"}},"created_at":"2026-05-18T00:15:27.484860+00:00","updated_at":"2026-05-18T00:15:27.484860+00:00"}