{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ADCTUXVPDHNLVDSBOPIW5JHNEW","short_pith_number":"pith:ADCTUXVP","schema_version":"1.0","canonical_sha256":"00c53a5eaf19daba8e4173d16ea4ed2586dc29043797d5103d75fa9c9e9cc6f6","source":{"kind":"arxiv","id":"1807.00981","version":3},"attestation_state":"computed","paper":{"title":"Learning concise representations for regression by evolving networks of trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"James Taggart, Jason H. Moore, Srinivas Suri, Tilak Raj Singh, William La Cava","submitted_at":"2018-07-03T05:21:30Z","abstract_excerpt":"We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition to other elementary functions. Differentiable features are trained via gradient descent, and the performance of features in a linear model is used to weight the rate of change among subcomponents of each representation. The search process maintains an archive of representations with accuracy-complexity trade-offs to assist in generalization and interpretati"},"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":"1807.00981","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2018-07-03T05:21:30Z","cross_cats_sorted":[],"title_canon_sha256":"6515e6d116115537b58588374cf49d71ae250601e5879760b015fb4de9374694","abstract_canon_sha256":"c682573d6d2f5f815d4715ddbb6534dad5fd42766352700fb67a58d8b753484a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:33.897000Z","signature_b64":"OGK/TESGeJgq+6isPyK1PouuI711VEBMhrdD8ywy5JghUTD0mxb37TN0WeSNLWiE6QRtpNyv1Ti/UWb9QZssCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00c53a5eaf19daba8e4173d16ea4ed2586dc29043797d5103d75fa9c9e9cc6f6","last_reissued_at":"2026-05-17T23:50:33.896376Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:33.896376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning concise representations for regression by evolving networks of trees","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"James Taggart, Jason H. Moore, Srinivas Suri, Tilak Raj Singh, William La Cava","submitted_at":"2018-07-03T05:21:30Z","abstract_excerpt":"We propose and study a method for learning interpretable representations for the task of regression. Features are represented as networks of multi-type expression trees comprised of activation functions common in neural networks in addition to other elementary functions. Differentiable features are trained via gradient descent, and the performance of features in a linear model is used to weight the rate of change among subcomponents of each representation. The search process maintains an archive of representations with accuracy-complexity trade-offs to assist in generalization and interpretati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00981","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":""},"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":"1807.00981","created_at":"2026-05-17T23:50:33.896469+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00981v3","created_at":"2026-05-17T23:50:33.896469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00981","created_at":"2026-05-17T23:50:33.896469+00:00"},{"alias_kind":"pith_short_12","alias_value":"ADCTUXVPDHNL","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ADCTUXVPDHNLVDSB","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ADCTUXVP","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2512.07961","citing_title":"Towards symbolic regression for interpretable clinical decision scores","ref_index":40,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW","json":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW.json","graph_json":"https://pith.science/api/pith-number/ADCTUXVPDHNLVDSBOPIW5JHNEW/graph.json","events_json":"https://pith.science/api/pith-number/ADCTUXVPDHNLVDSBOPIW5JHNEW/events.json","paper":"https://pith.science/paper/ADCTUXVP"},"agent_actions":{"view_html":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW","download_json":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW.json","view_paper":"https://pith.science/paper/ADCTUXVP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00981&json=true","fetch_graph":"https://pith.science/api/pith-number/ADCTUXVPDHNLVDSBOPIW5JHNEW/graph.json","fetch_events":"https://pith.science/api/pith-number/ADCTUXVPDHNLVDSBOPIW5JHNEW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW/action/storage_attestation","attest_author":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW/action/author_attestation","sign_citation":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW/action/citation_signature","submit_replication":"https://pith.science/pith/ADCTUXVPDHNLVDSBOPIW5JHNEW/action/replication_record"}},"created_at":"2026-05-17T23:50:33.896469+00:00","updated_at":"2026-05-17T23:50:33.896469+00:00"}