{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZECONFKJY4B5RWFJ4ONCJ266YW","short_pith_number":"pith:ZECONFKJ","schema_version":"1.0","canonical_sha256":"c904e69549c703d8d8a9e39a24ebdec5963c436bc4610c6c3112c68f95c4086d","source":{"kind":"arxiv","id":"2307.13883","version":2},"attestation_state":"computed","paper":{"title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Charles Sutton, Joey Hong, Kensen Shi, Manzil Zaheer, Pengcheng Yin, Yinlin Deng","submitted_at":"2023-07-26T01:07:52Z","abstract_excerpt":"When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, we can measure whether they compositionally generalize, that is, whether a model that has been trained on the simpler subtasks is subsequently able to solve more complex tasks. In this paper, we characterize several different forms of compositional generalization that are desirable in program synthesis, forming a meta-benchmark which we use to create generalizat"},"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":"2307.13883","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-07-26T01:07:52Z","cross_cats_sorted":["cs.PL"],"title_canon_sha256":"cb6decd91bfad91238fdc462a79e94fcd84c5f8272f9557fd16ea22acdcbc215","abstract_canon_sha256":"21f29d3618064b6859415cc836f98e68e3cf7b7d8af60f84b6e21768f925e471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:15:38.404254Z","signature_b64":"eWUA08nGs1z0gJT5sJDTvF2SVV9q503oB+Pt+YbYZJ4tw6kN4sgJ09e92JxLhhRC3iM+0lJn9NSJY70GudE3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c904e69549c703d8d8a9e39a24ebdec5963c436bc4610c6c3112c68f95c4086d","last_reissued_at":"2026-07-05T08:15:38.403775Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:15:38.403775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PL"],"primary_cat":"cs.LG","authors_text":"Charles Sutton, Joey Hong, Kensen Shi, Manzil Zaheer, Pengcheng Yin, Yinlin Deng","submitted_at":"2023-07-26T01:07:52Z","abstract_excerpt":"When writing programs, people have the ability to tackle a new complex task by decomposing it into smaller and more familiar subtasks. While it is difficult to measure whether neural program synthesis methods have similar capabilities, we can measure whether they compositionally generalize, that is, whether a model that has been trained on the simpler subtasks is subsequently able to solve more complex tasks. In this paper, we characterize several different forms of compositional generalization that are desirable in program synthesis, forming a meta-benchmark which we use to create generalizat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.13883","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/2307.13883/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":"2307.13883","created_at":"2026-07-05T08:15:38.403836+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.13883v2","created_at":"2026-07-05T08:15:38.403836+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.13883","created_at":"2026-07-05T08:15:38.403836+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZECONFKJY4B5","created_at":"2026-07-05T08:15:38.403836+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZECONFKJY4B5RWFJ","created_at":"2026-07-05T08:15:38.403836+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZECONFKJ","created_at":"2026-07-05T08:15:38.403836+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.18907","citing_title":"Gradient-Based Program Synthesis with Neurally Interpreted Languages","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW","json":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW.json","graph_json":"https://pith.science/api/pith-number/ZECONFKJY4B5RWFJ4ONCJ266YW/graph.json","events_json":"https://pith.science/api/pith-number/ZECONFKJY4B5RWFJ4ONCJ266YW/events.json","paper":"https://pith.science/paper/ZECONFKJ"},"agent_actions":{"view_html":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW","download_json":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW.json","view_paper":"https://pith.science/paper/ZECONFKJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.13883&json=true","fetch_graph":"https://pith.science/api/pith-number/ZECONFKJY4B5RWFJ4ONCJ266YW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZECONFKJY4B5RWFJ4ONCJ266YW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW/action/storage_attestation","attest_author":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW/action/author_attestation","sign_citation":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW/action/citation_signature","submit_replication":"https://pith.science/pith/ZECONFKJY4B5RWFJ4ONCJ266YW/action/replication_record"}},"created_at":"2026-07-05T08:15:38.403836+00:00","updated_at":"2026-07-05T08:15:38.403836+00:00"}