{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PCTROGYUD4JEZPARU4NYP4OBUG","short_pith_number":"pith:PCTROGYU","schema_version":"1.0","canonical_sha256":"78a7171b141f124cbc11a71b87f1c1a1985ae71b5d1b58a0f0e79bf1d016286d","source":{"kind":"arxiv","id":"2605.15809","version":1},"attestation_state":"computed","paper":{"title":"Diversified Residual Symbolic Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Symbolic regression now collects multiple expressions that differ in which observations they treat as outliers.","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Koki Ikeda, Masahiro Nomura, Ryoki Hamano","submitted_at":"2026-05-15T10:04:03Z","abstract_excerpt":"Symbolic regression (SR) aims to discover explicit mathematical expressions that explain observed data and is widely used in domains where interpretability is essential. Because interpretability requires expressions to reflect meaningful regularities, SR is sensitive to observations that deviate from the dominant relationship. Such irregular observations, or outliers, are common in real-world data and can hinder SR from identifying underlying regularities. Robust regression mitigates this by downweighting observations with large residuals. However, deciding which observations should be treated"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15809","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2026-05-15T10:04:03Z","cross_cats_sorted":[],"title_canon_sha256":"25ceed6329a7c42b748294a92716ef7bb681f23daa953a296d6192c2dbcc355d","abstract_canon_sha256":"e69a208e11fbcd24185a19d1f5bf769754d6d649a04d9f1b8aa53ccbc9cf20b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:19.673008Z","signature_b64":"P2JWeIjzYKGKJjTZegE0AntmwPnFLFflq7WXwJrMs5zqSgvO4CYzWy6dJwcbyinVlXCtcdPUYUU71OSPhMEmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a7171b141f124cbc11a71b87f1c1a1985ae71b5d1b58a0f0e79bf1d016286d","last_reissued_at":"2026-05-20T00:01:19.672265Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:19.672265Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversified Residual Symbolic Regression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Symbolic regression now collects multiple expressions that differ in which observations they treat as outliers.","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Koki Ikeda, Masahiro Nomura, Ryoki Hamano","submitted_at":"2026-05-15T10:04:03Z","abstract_excerpt":"Symbolic regression (SR) aims to discover explicit mathematical expressions that explain observed data and is widely used in domains where interpretability is essential. Because interpretability requires expressions to reflect meaningful regularities, SR is sensitive to observations that deviate from the dominant relationship. Such irregular observations, or outliers, are common in real-world data and can hinder SR from identifying underlying regularities. Robust regression mitigates this by downweighting observations with large residuals. However, deciding which observations should be treated"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"On a synthetic mixture dataset, DRSR produces more diverse expressions than conventional SR while capturing multiple underlying relationships. On a real-world astronomical dataset, DRSR discovers multiple expressions consistent with known physical relationships.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That diversity in residual patterns produced by the Quality-Diversity archive corresponds to distinct, meaningful underlying relationships that domain experts can reliably distinguish and select among, rather than superficial variations.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DRSR uses Quality-Diversity to produce diverse symbolic regression expressions differing in residual distributions, enabling post-search selection on synthetic and astronomical data.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Symbolic regression now collects multiple expressions that differ in which observations they treat as outliers.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"01a3e8870258887c721ff237515c01b9f5e538186fdc99e876770f684225c299"},"source":{"id":"2605.15809","kind":"arxiv","version":1},"verdict":{"id":"d30ec0cf-8ad1-47ff-b794-057c004e7868","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:41:57.469809Z","strongest_claim":"On a synthetic mixture dataset, DRSR produces more diverse expressions than conventional SR while capturing multiple underlying relationships. On a real-world astronomical dataset, DRSR discovers multiple expressions consistent with known physical relationships.","one_line_summary":"DRSR uses Quality-Diversity to produce diverse symbolic regression expressions differing in residual distributions, enabling post-search selection on synthetic and astronomical data.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That diversity in residual patterns produced by the Quality-Diversity archive corresponds to distinct, meaningful underlying relationships that domain experts can reliably distinguish and select among, rather than superficial variations.","pith_extraction_headline":"Symbolic regression now collects multiple expressions that differ in which observations they treat as outliers."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15809/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T19:01:19.012410Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:52:12.711718Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:48.733243Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:21:55.890002Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"8c25b2ee2164c105d373651b806638937656b6e2ea4f37fac0f364e8559871a9"},"references":{"count":37,"sample":[{"doi":"","year":2014,"title":"2014.Segmentation, Revenue Management, and Pricing Analytics","work_id":"d728e503-7e22-4b0f-82fe-6a8a5faf750f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48550/arxiv.2503.19043","year":2025,"title":"Jean-Philippe Bruneton. 2025. Enhancing Symbolic Regression with Quality- Diversity and Physics-Inspired Constraints. doi:10.48550/arXiv.2503.19043","work_id":"6e758ceb-a20a-4daf-ba5a-a3236df5008e","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48550/arxiv.1906.03959","year":2019,"title":"Exploration and Exploitation in Symbolic Regression using Quality-Diversity and Evolutionary Strategies Algorithms","work_id":"6d304ad3-e6f0-4904-a853-987cdfd61809","ref_index":3,"cited_arxiv_id":"1906.03959","is_internal_anchor":true},{"doi":"10.3389/fevo.2020.530135","year":2020,"title":"Pedro Cardoso, Vasco V. Branco, Paulo A.V. Borges, José C. Carvalho, François Rigal, Rosalina Gabriel, Stefano Mammola, José Cascalho, and Luís Correia. 2020. Automated Discovery of Relationships, Mod","work_id":"1a12c753-e305-485c-b956-8ecf3c4ee8b3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.1093/bioinformatics/btac405","year":2022,"title":"Niels Johan Christensen, Samuel Demharter, Meera Machado, Lykke Pedersen, Marco Salvatore, Valdemar Stentoft-Hansen, and Miquel Tri- ana Iglesias. 2022. Identifying interactions in omics data for clin","work_id":"d284ae91-6e99-44cc-bf65-96c9ea9914b1","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":37,"snapshot_sha256":"8d91c09855dff3a87ab341eec8ff5b01809318ff57e7108850e6f2faca895954","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6208b9459d6602b6415d3cf82fcb87277eb2246d3f87b811e3e86e2e68bc9dfb"},"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":"2605.15809","created_at":"2026-05-20T00:01:19.672389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15809v1","created_at":"2026-05-20T00:01:19.672389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15809","created_at":"2026-05-20T00:01:19.672389+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCTROGYUD4JE","created_at":"2026-05-20T00:01:19.672389+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCTROGYUD4JEZPAR","created_at":"2026-05-20T00:01:19.672389+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCTROGYU","created_at":"2026-05-20T00:01:19.672389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG","json":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG.json","graph_json":"https://pith.science/api/pith-number/PCTROGYUD4JEZPARU4NYP4OBUG/graph.json","events_json":"https://pith.science/api/pith-number/PCTROGYUD4JEZPARU4NYP4OBUG/events.json","paper":"https://pith.science/paper/PCTROGYU"},"agent_actions":{"view_html":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG","download_json":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG.json","view_paper":"https://pith.science/paper/PCTROGYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15809&json=true","fetch_graph":"https://pith.science/api/pith-number/PCTROGYUD4JEZPARU4NYP4OBUG/graph.json","fetch_events":"https://pith.science/api/pith-number/PCTROGYUD4JEZPARU4NYP4OBUG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG/action/storage_attestation","attest_author":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG/action/author_attestation","sign_citation":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG/action/citation_signature","submit_replication":"https://pith.science/pith/PCTROGYUD4JEZPARU4NYP4OBUG/action/replication_record"}},"created_at":"2026-05-20T00:01:19.672389+00:00","updated_at":"2026-05-20T00:01:19.672389+00:00"}