{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:75IMWTBBR6SZEJYSIA2OSJX7Y4","short_pith_number":"pith:75IMWTBB","schema_version":"1.0","canonical_sha256":"ff50cb4c218fa59227124034e926ffc7302c0dce2e98aebd955826bb5be0609f","source":{"kind":"arxiv","id":"1606.03622","version":1},"attestation_state":"computed","paper":{"title":"Data Recombination for Neural Semantic Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Percy Liang, Robin Jia","submitted_at":"2016-06-11T20:34:09Z","abstract_excerpt":"Modeling crisp logical regularities is crucial in semantic parsing, making it difficult for neural models with no task-specific prior knowledge to achieve good results. In this paper, we introduce data recombination, a novel framework for injecting such prior knowledge into a model. From the training data, we induce a high-precision synchronous context-free grammar, which captures important conditional independence properties commonly found in semantic parsing. We then train a sequence-to-sequence recurrent network (RNN) model with a novel attention-based copying mechanism on datapoints sample"},"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":"1606.03622","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-11T20:34:09Z","cross_cats_sorted":[],"title_canon_sha256":"c1dd1d615cb1a01d30e6e4afe4b972dacb3e6741babd2bec68f4f2c0c9778b75","abstract_canon_sha256":"100aeb1960562d1ce743069c00552fc8c769dec5341c9b9f2d3fc7d24cd8d8f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:12:33.498405Z","signature_b64":"r2mDDRYyZFyjGrJmbs3zXxwBm9VYV2oo6B5anOhu70L6SrHGtK+q0wDz/HiAgD5OtjaZPatgMNvv5KWV0YO3AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff50cb4c218fa59227124034e926ffc7302c0dce2e98aebd955826bb5be0609f","last_reissued_at":"2026-05-18T01:12:33.497788Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:12:33.497788Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Recombination for Neural Semantic Parsing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Percy Liang, Robin Jia","submitted_at":"2016-06-11T20:34:09Z","abstract_excerpt":"Modeling crisp logical regularities is crucial in semantic parsing, making it difficult for neural models with no task-specific prior knowledge to achieve good results. In this paper, we introduce data recombination, a novel framework for injecting such prior knowledge into a model. From the training data, we induce a high-precision synchronous context-free grammar, which captures important conditional independence properties commonly found in semantic parsing. We then train a sequence-to-sequence recurrent network (RNN) model with a novel attention-based copying mechanism on datapoints sample"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.03622","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":""},"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":"1606.03622","created_at":"2026-05-18T01:12:33.497884+00:00"},{"alias_kind":"arxiv_version","alias_value":"1606.03622v1","created_at":"2026-05-18T01:12:33.497884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.03622","created_at":"2026-05-18T01:12:33.497884+00:00"},{"alias_kind":"pith_short_12","alias_value":"75IMWTBBR6SZ","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"75IMWTBBR6SZEJYS","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"75IMWTBB","created_at":"2026-05-18T12:30:04.600751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"1907.08584","citing_title":"CraftAssist: A Framework for Dialogue-enabled Interactive Agents","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4","json":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4.json","graph_json":"https://pith.science/api/pith-number/75IMWTBBR6SZEJYSIA2OSJX7Y4/graph.json","events_json":"https://pith.science/api/pith-number/75IMWTBBR6SZEJYSIA2OSJX7Y4/events.json","paper":"https://pith.science/paper/75IMWTBB"},"agent_actions":{"view_html":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4","download_json":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4.json","view_paper":"https://pith.science/paper/75IMWTBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1606.03622&json=true","fetch_graph":"https://pith.science/api/pith-number/75IMWTBBR6SZEJYSIA2OSJX7Y4/graph.json","fetch_events":"https://pith.science/api/pith-number/75IMWTBBR6SZEJYSIA2OSJX7Y4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4/action/storage_attestation","attest_author":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4/action/author_attestation","sign_citation":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4/action/citation_signature","submit_replication":"https://pith.science/pith/75IMWTBBR6SZEJYSIA2OSJX7Y4/action/replication_record"}},"created_at":"2026-05-18T01:12:33.497884+00:00","updated_at":"2026-05-18T01:12:33.497884+00:00"}