{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:FNZH53RPRXVLQHRHMERPH4WLIN","short_pith_number":"pith:FNZH53RP","schema_version":"1.0","canonical_sha256":"2b727eee2f8deab81e276122f3f2cb435b44646e711769bb5aef7f5ff3f49c25","source":{"kind":"arxiv","id":"2107.01431","version":1},"attestation_state":"computed","paper":{"title":"Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianheng Tang, Jinghui Qin, Liang Lin, Xiaodan Liang, Yining Hong","submitted_at":"2021-07-03T13:14:58Z","abstract_excerpt":"Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose Neural-Symbolic Solver (NS-Solver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks. Our NS-Solver consists of a problem reader to encode problems, a programmer to generate symbolic equations, and a symbolic executor to obtain answers. Along with target expression supervision, our solver is also optimized via 4 new auxiliary objec"},"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":"2107.01431","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-03T13:14:58Z","cross_cats_sorted":[],"title_canon_sha256":"d13d66873e785df2d4d4730b40e1544049567987ed45eaffc444ce1cc623735c","abstract_canon_sha256":"86177d9fd7faea2aa8c29d443d6f6305ee6117faecb822f0ceae81e76c674d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:43.128074Z","signature_b64":"SNJWzYqlpZF3aLqldefCS7s5lhl4jOfOEPCNJYfxtY3q2qdgGAPZHI4FDa6+HGFmO37w06zx32Gsi5I8i4D1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b727eee2f8deab81e276122f3f2cb435b44646e711769bb5aef7f5ff3f49c25","last_reissued_at":"2026-07-05T02:54:43.127646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:43.127646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Symbolic Solver for Math Word Problems with Auxiliary Tasks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianheng Tang, Jinghui Qin, Liang Lin, Xiaodan Liang, Yining Hong","submitted_at":"2021-07-03T13:14:58Z","abstract_excerpt":"Previous math word problem solvers following the encoder-decoder paradigm fail to explicitly incorporate essential math symbolic constraints, leading to unexplainable and unreasonable predictions. Herein, we propose Neural-Symbolic Solver (NS-Solver) to explicitly and seamlessly incorporate different levels of symbolic constraints by auxiliary tasks. Our NS-Solver consists of a problem reader to encode problems, a programmer to generate symbolic equations, and a symbolic executor to obtain answers. Along with target expression supervision, our solver is also optimized via 4 new auxiliary objec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.01431","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/2107.01431/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":"2107.01431","created_at":"2026-07-05T02:54:43.127708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.01431v1","created_at":"2026-07-05T02:54:43.127708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.01431","created_at":"2026-07-05T02:54:43.127708+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNZH53RPRXVL","created_at":"2026-07-05T02:54:43.127708+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNZH53RPRXVLQHRH","created_at":"2026-07-05T02:54:43.127708+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNZH53RP","created_at":"2026-07-05T02:54:43.127708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"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":146,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11974","citing_title":"Towards Order Fairness: Mitigating LLMs Order Sensitivity through Dual Group Advantage Optimization","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN","json":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN.json","graph_json":"https://pith.science/api/pith-number/FNZH53RPRXVLQHRHMERPH4WLIN/graph.json","events_json":"https://pith.science/api/pith-number/FNZH53RPRXVLQHRHMERPH4WLIN/events.json","paper":"https://pith.science/paper/FNZH53RP"},"agent_actions":{"view_html":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN","download_json":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN.json","view_paper":"https://pith.science/paper/FNZH53RP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.01431&json=true","fetch_graph":"https://pith.science/api/pith-number/FNZH53RPRXVLQHRHMERPH4WLIN/graph.json","fetch_events":"https://pith.science/api/pith-number/FNZH53RPRXVLQHRHMERPH4WLIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN/action/storage_attestation","attest_author":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN/action/author_attestation","sign_citation":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN/action/citation_signature","submit_replication":"https://pith.science/pith/FNZH53RPRXVLQHRHMERPH4WLIN/action/replication_record"}},"created_at":"2026-07-05T02:54:43.127708+00:00","updated_at":"2026-07-05T02:54:43.127708+00:00"}