{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NNAKNNCK2G2EHG3P6XTICO2WHP","short_pith_number":"pith:NNAKNNCK","schema_version":"1.0","canonical_sha256":"6b40a6b44ad1b4439b6ff5e6813b563be503d76726215520396cbd0150e95ece","source":{"kind":"arxiv","id":"2207.01018","version":3},"attestation_state":"computed","paper":{"title":"Symbolic Regression is NP-hard","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Marco Virgolin, Solon P. Pissis","submitted_at":"2022-07-03T12:10:28Z","abstract_excerpt":"Symbolic regression (SR) is the task of learning a model of data in the form of a mathematical expression. By their nature, SR models have the potential to be accurate and human-interpretable at the same time. Unfortunately, finding such models, i.e., performing SR, appears to be a computationally intensive task. Historically, SR has been tackled with heuristics such as greedy or genetic algorithms and, while some works have hinted at the possible hardness of SR, no proof has yet been given that SR is, in fact, NP-hard. This begs the question: Is there an exact polynomial-time algorithm to com"},"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":"2207.01018","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-07-03T12:10:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"49c91705086f27f56741f55add0c7ae366e6c2a4cfae051b96f95c25d8a01a2d","abstract_canon_sha256":"0537d6dd6142970996a0b0cbaea335c0c3e29e206ddb2585ffc282607cc8744a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:38:54.298080Z","signature_b64":"lE01P36OqDUAeRwOlc1egzH5oGhhgH4ISEHqIEqhklH9EK7GZ8KZNRmQsUHA4XvnSx7IaoHdkprxkIVgwSDtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b40a6b44ad1b4439b6ff5e6813b563be503d76726215520396cbd0150e95ece","last_reissued_at":"2026-07-05T04:38:54.297607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:38:54.297607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Symbolic Regression is NP-hard","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Marco Virgolin, Solon P. Pissis","submitted_at":"2022-07-03T12:10:28Z","abstract_excerpt":"Symbolic regression (SR) is the task of learning a model of data in the form of a mathematical expression. By their nature, SR models have the potential to be accurate and human-interpretable at the same time. Unfortunately, finding such models, i.e., performing SR, appears to be a computationally intensive task. Historically, SR has been tackled with heuristics such as greedy or genetic algorithms and, while some works have hinted at the possible hardness of SR, no proof has yet been given that SR is, in fact, NP-hard. This begs the question: Is there an exact polynomial-time algorithm to com"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.01018","kind":"arxiv","version":3},"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/2207.01018/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":"2207.01018","created_at":"2026-07-05T04:38:54.297664+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.01018v3","created_at":"2026-07-05T04:38:54.297664+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.01018","created_at":"2026-07-05T04:38:54.297664+00:00"},{"alias_kind":"pith_short_12","alias_value":"NNAKNNCK2G2E","created_at":"2026-07-05T04:38:54.297664+00:00"},{"alias_kind":"pith_short_16","alias_value":"NNAKNNCK2G2EHG3P","created_at":"2026-07-05T04:38:54.297664+00:00"},{"alias_kind":"pith_short_8","alias_value":"NNAKNNCK","created_at":"2026-07-05T04:38:54.297664+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07745","citing_title":"CMBolic: Symbolic emulators for the Cosmic Microwave Background. I. Lensing","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07704","citing_title":"FunctionEvolve: Structure-Guided Symbolic Regression with LLMs","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24170","citing_title":"Learning dynamical systems with biochemically informed neural ordinary differential equations","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2502.01476","citing_title":"Neuro-Symbolic AI for Analytical Solutions of Differential Equations","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09696","citing_title":"Discovery of Nonlinear Dynamics with Automated Basis Function Generation","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10687","citing_title":"The finite expression method for turbulent dynamics with high-order moment recovery","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP","json":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP.json","graph_json":"https://pith.science/api/pith-number/NNAKNNCK2G2EHG3P6XTICO2WHP/graph.json","events_json":"https://pith.science/api/pith-number/NNAKNNCK2G2EHG3P6XTICO2WHP/events.json","paper":"https://pith.science/paper/NNAKNNCK"},"agent_actions":{"view_html":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP","download_json":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP.json","view_paper":"https://pith.science/paper/NNAKNNCK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.01018&json=true","fetch_graph":"https://pith.science/api/pith-number/NNAKNNCK2G2EHG3P6XTICO2WHP/graph.json","fetch_events":"https://pith.science/api/pith-number/NNAKNNCK2G2EHG3P6XTICO2WHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP/action/storage_attestation","attest_author":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP/action/author_attestation","sign_citation":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP/action/citation_signature","submit_replication":"https://pith.science/pith/NNAKNNCK2G2EHG3P6XTICO2WHP/action/replication_record"}},"created_at":"2026-07-05T04:38:54.297664+00:00","updated_at":"2026-07-05T04:38:54.297664+00:00"}