{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:5RPWHSF3MWFNST6FZOQVFKRQWS","short_pith_number":"pith:5RPWHSF3","schema_version":"1.0","canonical_sha256":"ec5f63c8bb658ad94fc5cba152aa30b48ada23c72d54d82531416fd005d8b3aa","source":{"kind":"arxiv","id":"2605.22374","version":1},"attestation_state":"computed","paper":{"title":"Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.NE","authors_text":"Deaglan J. Bartlett, Fabricio Olivetti de Franca, Gabriel Kronberger, Harry Desmond, Pedro G. Ferreira","submitted_at":"2026-05-21T12:07:05Z","abstract_excerpt":"Symbolic regression with genetic programming (GPSR) may suffer from overfitting and structural bloat, especially when noise is present. In this paper we evaluate description length (DL) and fractional Bayes factor (FBF) criteria as principled, data-efficient alternatives to heuristics for selecting compact expressions that generalise well. We implement DL using a Fisher-information-based parameter encoding and compare it to AIC and BIC across multiple datasets, including noisy synthetic benchmarks and real-world regression problems. We study three search/selection strategies: (i) multi-objecti"},"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":"2605.22374","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2026-05-21T12:07:05Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"78324533139acc795339354dd92acadf5376f98c13777996f7f596047af159e5","abstract_canon_sha256":"c785204fe3b38322bde1b8dff09a8f3c882384c7382223d9624d17530ad61e41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:04:40.518404Z","signature_b64":"qE0ooqil5BknF8nyjatMTNvmzXjpIdHb4vHMJFItX/embRtabfBoXO4oDsuhjNuGYZm9A+Ez5Xr9K8/6te6DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec5f63c8bb658ad94fc5cba152aa30b48ada23c72d54d82531416fd005d8b3aa","last_reissued_at":"2026-05-22T01:04:40.517607Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:04:40.517607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Guiding Multi-Objective Genetic Programming with Description Length Improves Symbolic Regression Solutions","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.NE","authors_text":"Deaglan J. Bartlett, Fabricio Olivetti de Franca, Gabriel Kronberger, Harry Desmond, Pedro G. Ferreira","submitted_at":"2026-05-21T12:07:05Z","abstract_excerpt":"Symbolic regression with genetic programming (GPSR) may suffer from overfitting and structural bloat, especially when noise is present. In this paper we evaluate description length (DL) and fractional Bayes factor (FBF) criteria as principled, data-efficient alternatives to heuristics for selecting compact expressions that generalise well. We implement DL using a Fisher-information-based parameter encoding and compare it to AIC and BIC across multiple datasets, including noisy synthetic benchmarks and real-world regression problems. We study three search/selection strategies: (i) multi-objecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.22374","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/2605.22374/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":"2605.22374","created_at":"2026-05-22T01:04:40.517737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.22374v1","created_at":"2026-05-22T01:04:40.517737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.22374","created_at":"2026-05-22T01:04:40.517737+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RPWHSF3MWFN","created_at":"2026-05-22T01:04:40.517737+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RPWHSF3MWFNST6F","created_at":"2026-05-22T01:04:40.517737+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RPWHSF3","created_at":"2026-05-22T01:04:40.517737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS","json":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS.json","graph_json":"https://pith.science/api/pith-number/5RPWHSF3MWFNST6FZOQVFKRQWS/graph.json","events_json":"https://pith.science/api/pith-number/5RPWHSF3MWFNST6FZOQVFKRQWS/events.json","paper":"https://pith.science/paper/5RPWHSF3"},"agent_actions":{"view_html":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS","download_json":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS.json","view_paper":"https://pith.science/paper/5RPWHSF3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.22374&json=true","fetch_graph":"https://pith.science/api/pith-number/5RPWHSF3MWFNST6FZOQVFKRQWS/graph.json","fetch_events":"https://pith.science/api/pith-number/5RPWHSF3MWFNST6FZOQVFKRQWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS/action/storage_attestation","attest_author":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS/action/author_attestation","sign_citation":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS/action/citation_signature","submit_replication":"https://pith.science/pith/5RPWHSF3MWFNST6FZOQVFKRQWS/action/replication_record"}},"created_at":"2026-05-22T01:04:40.517737+00:00","updated_at":"2026-05-22T01:04:40.517737+00:00"}