{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JVLBNCIKRCTLWEYWJH6PEJY2NT","short_pith_number":"pith:JVLBNCIK","schema_version":"1.0","canonical_sha256":"4d5616890a88a6bb131649fcf2271a6ce8c1ff214629e49b83eb9fd7f822d15d","source":{"kind":"arxiv","id":"2410.23948","version":1},"attestation_state":"computed","paper":{"title":"Transformers to Predict the Applicability of Symbolic Integration Routines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.LG","authors_text":"Juergen Gerhard, Matthew England, Rashid Barket, Uzma Shafiq","submitted_at":"2024-10-31T14:03:37Z","abstract_excerpt":"Symbolic integration is a fundamental problem in mathematics: we consider how machine learning may be used to optimise this task in a Computer Algebra System (CAS). We train transformers that predict whether a particular integration method will be successful, and compare against the existing human-made heuristics (called guards) that perform this task in a leading CAS. We find the transformer can outperform these guards, gaining up to 30% accuracy and 70% precision. We further show that the inference time of the transformer is inconsequential which shows that it is well-suited to include as a "},"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":"2410.23948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-31T14:03:37Z","cross_cats_sorted":["cs.SC"],"title_canon_sha256":"5b43fb14b367d2b74e48d60cf126c226c0f90fa2a2f14ff35ef22b4fd32623a7","abstract_canon_sha256":"b39706ea55708f370d4c03b16d86c4307b4ffd4d00a3991e290d38d8a6977545"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:16.651780Z","signature_b64":"wOPeyahP0L4dWC8KUAhJ2Xc2Z+k+2LVpml9LxDmZCE3MTNI2XFsCnmCIrGWxh4cmwCCLLI7cukWR4vOqV7jBCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d5616890a88a6bb131649fcf2271a6ce8c1ff214629e49b83eb9fd7f822d15d","last_reissued_at":"2026-07-05T09:29:16.651222Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:16.651222Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers to Predict the Applicability of Symbolic Integration Routines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.LG","authors_text":"Juergen Gerhard, Matthew England, Rashid Barket, Uzma Shafiq","submitted_at":"2024-10-31T14:03:37Z","abstract_excerpt":"Symbolic integration is a fundamental problem in mathematics: we consider how machine learning may be used to optimise this task in a Computer Algebra System (CAS). We train transformers that predict whether a particular integration method will be successful, and compare against the existing human-made heuristics (called guards) that perform this task in a leading CAS. We find the transformer can outperform these guards, gaining up to 30% accuracy and 70% precision. We further show that the inference time of the transformer is inconsequential which shows that it is well-suited to include as a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23948","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/2410.23948/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":"2410.23948","created_at":"2026-07-05T09:29:16.651298+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.23948v1","created_at":"2026-07-05T09:29:16.651298+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23948","created_at":"2026-07-05T09:29:16.651298+00:00"},{"alias_kind":"pith_short_12","alias_value":"JVLBNCIKRCTL","created_at":"2026-07-05T09:29:16.651298+00:00"},{"alias_kind":"pith_short_16","alias_value":"JVLBNCIKRCTLWEYW","created_at":"2026-07-05T09:29:16.651298+00:00"},{"alias_kind":"pith_short_8","alias_value":"JVLBNCIK","created_at":"2026-07-05T09:29:16.651298+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.10335","citing_title":"Studying number theory with deep learning: a case study with the M\\\"obius and squarefree indicator functions","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT","json":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT.json","graph_json":"https://pith.science/api/pith-number/JVLBNCIKRCTLWEYWJH6PEJY2NT/graph.json","events_json":"https://pith.science/api/pith-number/JVLBNCIKRCTLWEYWJH6PEJY2NT/events.json","paper":"https://pith.science/paper/JVLBNCIK"},"agent_actions":{"view_html":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT","download_json":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT.json","view_paper":"https://pith.science/paper/JVLBNCIK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.23948&json=true","fetch_graph":"https://pith.science/api/pith-number/JVLBNCIKRCTLWEYWJH6PEJY2NT/graph.json","fetch_events":"https://pith.science/api/pith-number/JVLBNCIKRCTLWEYWJH6PEJY2NT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT/action/storage_attestation","attest_author":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT/action/author_attestation","sign_citation":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT/action/citation_signature","submit_replication":"https://pith.science/pith/JVLBNCIKRCTLWEYWJH6PEJY2NT/action/replication_record"}},"created_at":"2026-07-05T09:29:16.651298+00:00","updated_at":"2026-07-05T09:29:16.651298+00:00"}