{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ISCUR4AYTGHF4DP5SVHG67EF4Q","short_pith_number":"pith:ISCUR4AY","schema_version":"1.0","canonical_sha256":"448548f018998e5e0dfd954e6f7c85e435ddd7da9234d89fbb9bcf10543a7416","source":{"kind":"arxiv","id":"1912.01412","version":1},"attestation_state":"computed","paper":{"title":"Deep Learning for Symbolic Mathematics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SC","authors_text":"Fran\\c{c}ois Charton, Guillaume Lample","submitted_at":"2019-12-02T15:05:24Z","abstract_excerpt":"Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica."},"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":"1912.01412","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SC","submitted_at":"2019-12-02T15:05:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"18dcdf905689c5d101d0b36797994ab501c6a8a3e53f88ce78b0d22154455851","abstract_canon_sha256":"c333c21c5dc7a0dbbccdfaa23bff375b8d2eadd1e6f3b8a7d476df39eef50975"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:23:30.823101Z","signature_b64":"Mj4qzgHxNkfpET2uK8kitVuY5Z/ZSomT41tVUfq5boOL2f78rGypbqt/uE2vcAVcL95ubRwhsdIzwswNnXYqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"448548f018998e5e0dfd954e6f7c85e435ddd7da9234d89fbb9bcf10543a7416","last_reissued_at":"2026-07-05T00:23:30.822596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:23:30.822596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Deep Learning for Symbolic Mathematics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.SC","authors_text":"Fran\\c{c}ois Charton, Guillaume Lample","submitted_at":"2019-12-02T15:05:24Z","abstract_excerpt":"Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.01412","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/1912.01412/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":"1912.01412","created_at":"2026-07-05T00:23:30.822656+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.01412v1","created_at":"2026-07-05T00:23:30.822656+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.01412","created_at":"2026-07-05T00:23:30.822656+00:00"},{"alias_kind":"pith_short_12","alias_value":"ISCUR4AYTGHF","created_at":"2026-07-05T00:23:30.822656+00:00"},{"alias_kind":"pith_short_16","alias_value":"ISCUR4AYTGHF4DP5","created_at":"2026-07-05T00:23:30.822656+00:00"},{"alias_kind":"pith_short_8","alias_value":"ISCUR4AY","created_at":"2026-07-05T00:23:30.822656+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07915","citing_title":"EditSR: Enhancing Neural Symbolic Regression via Edit-based Rectification","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27245","citing_title":"Symbolic Regression via Latent Iterative Refinement","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2110.14168","citing_title":"Training Verifiers to Solve Math Word Problems","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2408.11065","citing_title":"Statistical Patterns in the Equations of Physics and the Emergence of a Meta-Law of Nature","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2009.03393","citing_title":"Generative Language Modeling for Automated Theorem Proving","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2502.01476","citing_title":"Neuro-Symbolic AI for Analytical Solutions of Differential Equations","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21160","citing_title":"Learning First Integrals via Backward-Generated Data and Guided Reinforcement Learning","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2402.17762","citing_title":"Massive Activations in Large Language Models","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11164","citing_title":"Learning to Unscramble: Simplifying Symbolic Expressions via Self-Supervised Oracle Trajectories","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13082","citing_title":"The Long Delay to Arithmetic Generalization: When Learned Representations Outrun Behavior","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04978","citing_title":"Exhaustive Symbolic Integration: Integration by Differentiation and the Landscape of Symbolic Integrability","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07240","citing_title":"$k$-server-bench: Automating Potential Discovery for the $k$-Server Conjecture","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16232","citing_title":"Neuro-Symbolic ODE Discovery with Latent Grammar Flow","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q","json":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q.json","graph_json":"https://pith.science/api/pith-number/ISCUR4AYTGHF4DP5SVHG67EF4Q/graph.json","events_json":"https://pith.science/api/pith-number/ISCUR4AYTGHF4DP5SVHG67EF4Q/events.json","paper":"https://pith.science/paper/ISCUR4AY"},"agent_actions":{"view_html":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q","download_json":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q.json","view_paper":"https://pith.science/paper/ISCUR4AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.01412&json=true","fetch_graph":"https://pith.science/api/pith-number/ISCUR4AYTGHF4DP5SVHG67EF4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/ISCUR4AYTGHF4DP5SVHG67EF4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q/action/storage_attestation","attest_author":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q/action/author_attestation","sign_citation":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q/action/citation_signature","submit_replication":"https://pith.science/pith/ISCUR4AYTGHF4DP5SVHG67EF4Q/action/replication_record"}},"created_at":"2026-07-05T00:23:30.822656+00:00","updated_at":"2026-07-05T00:23:30.822656+00:00"}