{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IN2RBZBSPH55ZVB5CBKHASMC6B","short_pith_number":"pith:IN2RBZBS","schema_version":"1.0","canonical_sha256":"437510e43279fbdcd43d1054704982f067c1e29af30faca509da0d601473ee94","source":{"kind":"arxiv","id":"2306.09064","version":1},"attestation_state":"computed","paper":{"title":"Learning by Analogy: Diverse Questions Generation in Math Word Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Yao, Kaizhu Huang, Maizhen Ning, Qiufeng Wang, Wei Wang, Xiaowei Huang, Zihao Zhou","submitted_at":"2023-06-15T11:47:07Z","abstract_excerpt":"Solving math word problem (MWP) with AI techniques has recently made great progress with the success of deep neural networks (DNN), but it is far from being solved. We argue that the ability of learning by analogy is essential for an MWP solver to better understand same problems which may typically be formulated in diverse ways. However most existing works exploit the shortcut learning to train MWP solvers simply based on samples with a single question. In lack of diverse questions, these methods merely learn shallow heuristics. In this paper, we make a first attempt to solve MWPs by generatin"},"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":"2306.09064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-15T11:47:07Z","cross_cats_sorted":[],"title_canon_sha256":"4cc488568d889ceb0f25e4e5ff58bc21199c28503ca03c76e64e1d1aa89ef808","abstract_canon_sha256":"f58976a7b2a18125b0e701a8931b3abf9b44cd45e7e950b15cd79228ab55a620"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:21:08.194835Z","signature_b64":"dSSj3R1LrRz/ikKshAyjj0ycPuLECsCMRWgxNekKos5joi23RZnUH5eF/jnNmVN03nIo2M379JcrWsiGWsuGCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"437510e43279fbdcd43d1054704982f067c1e29af30faca509da0d601473ee94","last_reissued_at":"2026-07-05T06:21:08.194466Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:21:08.194466Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning by Analogy: Diverse Questions Generation in Math Word Problem","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jie Yao, Kaizhu Huang, Maizhen Ning, Qiufeng Wang, Wei Wang, Xiaowei Huang, Zihao Zhou","submitted_at":"2023-06-15T11:47:07Z","abstract_excerpt":"Solving math word problem (MWP) with AI techniques has recently made great progress with the success of deep neural networks (DNN), but it is far from being solved. We argue that the ability of learning by analogy is essential for an MWP solver to better understand same problems which may typically be formulated in diverse ways. However most existing works exploit the shortcut learning to train MWP solvers simply based on samples with a single question. In lack of diverse questions, these methods merely learn shallow heuristics. In this paper, we make a first attempt to solve MWPs by generatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.09064","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/2306.09064/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":"2306.09064","created_at":"2026-07-05T06:21:08.194522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.09064v1","created_at":"2026-07-05T06:21:08.194522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.09064","created_at":"2026-07-05T06:21:08.194522+00:00"},{"alias_kind":"pith_short_12","alias_value":"IN2RBZBSPH55","created_at":"2026-07-05T06:21:08.194522+00:00"},{"alias_kind":"pith_short_16","alias_value":"IN2RBZBSPH55ZVB5","created_at":"2026-07-05T06:21:08.194522+00:00"},{"alias_kind":"pith_short_8","alias_value":"IN2RBZBS","created_at":"2026-07-05T06:21:08.194522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02565","citing_title":"Towards Generating Controllable and Solvable Geometry Problem by Leveraging Symbolic Deduction Engine","ref_index":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B","json":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B.json","graph_json":"https://pith.science/api/pith-number/IN2RBZBSPH55ZVB5CBKHASMC6B/graph.json","events_json":"https://pith.science/api/pith-number/IN2RBZBSPH55ZVB5CBKHASMC6B/events.json","paper":"https://pith.science/paper/IN2RBZBS"},"agent_actions":{"view_html":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B","download_json":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B.json","view_paper":"https://pith.science/paper/IN2RBZBS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.09064&json=true","fetch_graph":"https://pith.science/api/pith-number/IN2RBZBSPH55ZVB5CBKHASMC6B/graph.json","fetch_events":"https://pith.science/api/pith-number/IN2RBZBSPH55ZVB5CBKHASMC6B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B/action/storage_attestation","attest_author":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B/action/author_attestation","sign_citation":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B/action/citation_signature","submit_replication":"https://pith.science/pith/IN2RBZBSPH55ZVB5CBKHASMC6B/action/replication_record"}},"created_at":"2026-07-05T06:21:08.194522+00:00","updated_at":"2026-07-05T06:21:08.194522+00:00"}