{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:56XTK7FX6CJ5UNRGILKJOAPSWF","short_pith_number":"pith:56XTK7FX","schema_version":"1.0","canonical_sha256":"efaf357cb7f093da362642d49701f2b1781626f519388041f6e68f0be2f01b25","source":{"kind":"arxiv","id":"2502.05121","version":1},"attestation_state":"computed","paper":{"title":"Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ph"],"primary_cat":"hep-th","authors_text":"Matthias Wilhelm, Matt von Hippel","submitted_at":"2025-02-07T17:48:42Z","abstract_excerpt":"Integration-by-parts reductions of Feynman integrals pose a frequent bottle-neck in state-of-the-art calculations in theoretical particle and gravitational-wave physics, and rely on heuristic approaches for selecting integration-by-parts identities, whose quality heavily influences the performance. In this paper, we investigate the use of machine-learning techniques to find improved heuristics. We use funsearch, a genetic programming variant based on code generation by a Large Language Model, in order to explore possible approaches, then use strongly typed genetic programming to zero in on use"},"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":"2502.05121","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"hep-th","submitted_at":"2025-02-07T17:48:42Z","cross_cats_sorted":["cs.LG","hep-ph"],"title_canon_sha256":"72ecb29be51030311f96e9e4dd59728ff6cb2be706238b4cf5ecc0115817deaa","abstract_canon_sha256":"a15cf860970d434e8aaca7ad13bf13120d66cf710289575722fbcf06a3d09944"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:09.511235Z","signature_b64":"cNe02gHHEwMEwJ7cP2Eim/GLYTURXGk/2sOMVkhMBYoikPQug0L5KzS9qSQP+u/8nzL6yQjEBbkyrtv7YBt9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efaf357cb7f093da362642d49701f2b1781626f519388041f6e68f0be2f01b25","last_reissued_at":"2026-07-05T10:11:09.510748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:09.510748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refining Integration-by-Parts Reduction of Feynman Integrals with Machine Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","hep-ph"],"primary_cat":"hep-th","authors_text":"Matthias Wilhelm, Matt von Hippel","submitted_at":"2025-02-07T17:48:42Z","abstract_excerpt":"Integration-by-parts reductions of Feynman integrals pose a frequent bottle-neck in state-of-the-art calculations in theoretical particle and gravitational-wave physics, and rely on heuristic approaches for selecting integration-by-parts identities, whose quality heavily influences the performance. In this paper, we investigate the use of machine-learning techniques to find improved heuristics. We use funsearch, a genetic programming variant based on code generation by a Large Language Model, in order to explore possible approaches, then use strongly typed genetic programming to zero in on use"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05121","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/2502.05121/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":"2502.05121","created_at":"2026-07-05T10:11:09.510816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05121v1","created_at":"2026-07-05T10:11:09.510816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05121","created_at":"2026-07-05T10:11:09.510816+00:00"},{"alias_kind":"pith_short_12","alias_value":"56XTK7FX6CJ5","created_at":"2026-07-05T10:11:09.510816+00:00"},{"alias_kind":"pith_short_16","alias_value":"56XTK7FX6CJ5UNRG","created_at":"2026-07-05T10:11:09.510816+00:00"},{"alias_kind":"pith_short_8","alias_value":"56XTK7FX","created_at":"2026-07-05T10:11:09.510816+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08477","citing_title":"AMFlow 2.0: significant algorithmic and software improvements for Feynman integral evaluation","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2606.10698","citing_title":"Efficient AI-Inspired Reduction of Feynman Integrals via Tube Seeding","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13794","citing_title":"The spectrum of Feynman-integral geometries at two loops","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11164","citing_title":"Learning to Unscramble: Simplifying Symbolic Expressions via Self-Supervised Oracle Trajectories","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09534","citing_title":"The four-loop non-singlet splitting functions in QCD","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05034","citing_title":"Learning to Unscramble Feynman Loop Integrals with SAILIR","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF","json":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF.json","graph_json":"https://pith.science/api/pith-number/56XTK7FX6CJ5UNRGILKJOAPSWF/graph.json","events_json":"https://pith.science/api/pith-number/56XTK7FX6CJ5UNRGILKJOAPSWF/events.json","paper":"https://pith.science/paper/56XTK7FX"},"agent_actions":{"view_html":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF","download_json":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF.json","view_paper":"https://pith.science/paper/56XTK7FX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05121&json=true","fetch_graph":"https://pith.science/api/pith-number/56XTK7FX6CJ5UNRGILKJOAPSWF/graph.json","fetch_events":"https://pith.science/api/pith-number/56XTK7FX6CJ5UNRGILKJOAPSWF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF/action/storage_attestation","attest_author":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF/action/author_attestation","sign_citation":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF/action/citation_signature","submit_replication":"https://pith.science/pith/56XTK7FX6CJ5UNRGILKJOAPSWF/action/replication_record"}},"created_at":"2026-07-05T10:11:09.510816+00:00","updated_at":"2026-07-05T10:11:09.510816+00:00"}