{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PNKVIL5F2WGATBI4LZT7L2ZFWG","short_pith_number":"pith:PNKVIL5F","schema_version":"1.0","canonical_sha256":"7b55542fa5d58c09851c5e67f5eb25b1b8dc212d0c315fa458cc292f514260fe","source":{"kind":"arxiv","id":"1910.05865","version":1},"attestation_state":"computed","paper":{"title":"Neural Program Synthesis By Self-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Kening Zhang, Lu Dai, Udaikaran Singh, Yifan Xu, Zhuowen Tu","submitted_at":"2019-10-13T23:44:37Z","abstract_excerpt":"Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssemblet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effect"},"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":"1910.05865","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-13T23:44:37Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"875b0ab67edff738e1450b61c9f939454aeb73d0d6250d61900ddda688c72237","abstract_canon_sha256":"d2dec1daec9721fe8d5d8fb5d22592a5bfc1f9a02dfa00b982c717f2a8c0aa60"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:42.277230Z","signature_b64":"nwXj5mASJrUZWiOhADczr2+FYE8JgEg6+A3qMuPUSOGVguaiecde6hQlG/SFxpzYboUeWUl+ni/CZPFeRQTeCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b55542fa5d58c09851c5e67f5eb25b1b8dc212d0c315fa458cc292f514260fe","last_reissued_at":"2026-07-05T00:11:42.276736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:42.276736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Program Synthesis By Self-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.LG","authors_text":"Kening Zhang, Lu Dai, Udaikaran Singh, Yifan Xu, Zhuowen Tu","submitted_at":"2019-10-13T23:44:37Z","abstract_excerpt":"Neural inductive program synthesis is a task generating instructions that can produce desired outputs from given inputs. In this paper, we focus on the generation of a chunk of assembly code that can be executed to match a state change inside the CPU and RAM. We develop a neural program synthesis algorithm, AutoAssemblet, learned via self-learning reinforcement learning that explores the large code space efficiently. Policy networks and value networks are learned to reduce the breadth and depth of the Monte Carlo Tree Search, resulting in better synthesis performance. We also propose an effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.05865","kind":"arxiv","version":1},"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/1910.05865/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":"1910.05865","created_at":"2026-07-05T00:11:42.276803+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.05865v1","created_at":"2026-07-05T00:11:42.276803+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.05865","created_at":"2026-07-05T00:11:42.276803+00:00"},{"alias_kind":"pith_short_12","alias_value":"PNKVIL5F2WGA","created_at":"2026-07-05T00:11:42.276803+00:00"},{"alias_kind":"pith_short_16","alias_value":"PNKVIL5F2WGATBI4","created_at":"2026-07-05T00:11:42.276803+00:00"},{"alias_kind":"pith_short_8","alias_value":"PNKVIL5F","created_at":"2026-07-05T00:11:42.276803+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/PNKVIL5F2WGATBI4LZT7L2ZFWG","json":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG.json","graph_json":"https://pith.science/api/pith-number/PNKVIL5F2WGATBI4LZT7L2ZFWG/graph.json","events_json":"https://pith.science/api/pith-number/PNKVIL5F2WGATBI4LZT7L2ZFWG/events.json","paper":"https://pith.science/paper/PNKVIL5F"},"agent_actions":{"view_html":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG","download_json":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG.json","view_paper":"https://pith.science/paper/PNKVIL5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.05865&json=true","fetch_graph":"https://pith.science/api/pith-number/PNKVIL5F2WGATBI4LZT7L2ZFWG/graph.json","fetch_events":"https://pith.science/api/pith-number/PNKVIL5F2WGATBI4LZT7L2ZFWG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG/action/storage_attestation","attest_author":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG/action/author_attestation","sign_citation":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG/action/citation_signature","submit_replication":"https://pith.science/pith/PNKVIL5F2WGATBI4LZT7L2ZFWG/action/replication_record"}},"created_at":"2026-07-05T00:11:42.276803+00:00","updated_at":"2026-07-05T00:11:42.276803+00:00"}