{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:AE2FHABGTXCF55RVBUH7CO7H6D","short_pith_number":"pith:AE2FHABG","schema_version":"1.0","canonical_sha256":"01345380269dc45ef6350d0ff13be7f0c3f57e0da0ddd91c39034b471311f0c0","source":{"kind":"arxiv","id":"2004.13781","version":2},"attestation_state":"computed","paper":{"title":"Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Fangli Xu, Fengyuan Xu, Lingfei Wu, Sheng Zhong, Shiwei Feng, Shucheng Li","submitted_at":"2020-04-07T17:36:38Z","abstract_excerpt":"The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented grap"},"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":"2004.13781","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-07T17:36:38Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"d2af486d4fff8e8d1f2e95cb7cb3ea61b4775bb0549ccb40d7824b9c6d836813","abstract_canon_sha256":"322359b13a83e39eee12ac9085fcfca00b45c79e59f78c3f993bd1b2f759b2c1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:40:27.211207Z","signature_b64":"1M/vGoXXgy+mVc10LajqJQP1hyWbcbB2LljVjG/S+5vyLCkIfKT73zItTeeecnTM5thFERcgp/ku+GS3pTSjAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"01345380269dc45ef6350d0ff13be7f0c3f57e0da0ddd91c39034b471311f0c0","last_reissued_at":"2026-07-05T01:40:27.210786Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:40:27.210786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Fangli Xu, Fengyuan Xu, Lingfei Wu, Sheng Zhong, Shiwei Feng, Shucheng Li","submitted_at":"2020-04-07T17:36:38Z","abstract_excerpt":"The celebrated Seq2Seq technique and its numerous variants achieve excellent performance on many tasks such as neural machine translation, semantic parsing, and math word problem solving. However, these models either only consider input objects as sequences while ignoring the important structural information for encoding, or they simply treat output objects as sequence outputs instead of structural objects for decoding. In this paper, we present a novel Graph-to-Tree Neural Networks, namely Graph2Tree consisting of a graph encoder and a hierarchical tree decoder, that encodes an augmented grap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13781","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/2004.13781/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":"2004.13781","created_at":"2026-07-05T01:40:27.210837+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.13781v2","created_at":"2026-07-05T01:40:27.210837+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13781","created_at":"2026-07-05T01:40:27.210837+00:00"},{"alias_kind":"pith_short_12","alias_value":"AE2FHABGTXCF","created_at":"2026-07-05T01:40:27.210837+00:00"},{"alias_kind":"pith_short_16","alias_value":"AE2FHABGTXCF55RV","created_at":"2026-07-05T01:40:27.210837+00:00"},{"alias_kind":"pith_short_8","alias_value":"AE2FHABG","created_at":"2026-07-05T01:40:27.210837+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18030","citing_title":"ParaTutor: Coordinating Parent and Child Math Tutoring through Role Separated LLM Scaffolding","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08728","citing_title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","ref_index":132,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D","json":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D.json","graph_json":"https://pith.science/api/pith-number/AE2FHABGTXCF55RVBUH7CO7H6D/graph.json","events_json":"https://pith.science/api/pith-number/AE2FHABGTXCF55RVBUH7CO7H6D/events.json","paper":"https://pith.science/paper/AE2FHABG"},"agent_actions":{"view_html":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D","download_json":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D.json","view_paper":"https://pith.science/paper/AE2FHABG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.13781&json=true","fetch_graph":"https://pith.science/api/pith-number/AE2FHABGTXCF55RVBUH7CO7H6D/graph.json","fetch_events":"https://pith.science/api/pith-number/AE2FHABGTXCF55RVBUH7CO7H6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D/action/storage_attestation","attest_author":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D/action/author_attestation","sign_citation":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D/action/citation_signature","submit_replication":"https://pith.science/pith/AE2FHABGTXCF55RVBUH7CO7H6D/action/replication_record"}},"created_at":"2026-07-05T01:40:27.210837+00:00","updated_at":"2026-07-05T01:40:27.210837+00:00"}