{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MEOHK6UWB7O6TNBLOBUH4P4CY6","short_pith_number":"pith:MEOHK6UW","schema_version":"1.0","canonical_sha256":"611c757a960fdde9b42b70687e3f82c7b818fbd1ccf2bea7e0dffa24544b54e6","source":{"kind":"arxiv","id":"2409.19209","version":1},"attestation_state":"computed","paper":{"title":"Boosting SISSO Performance on Small Sample Datasets by Using Random Forests Prescreening for Complex Feature Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Guanqi Liu, Jiaying Xie, Xiaolin Jiang, Zhenpeng Hu","submitted_at":"2024-09-28T02:15:39Z","abstract_excerpt":"In materials science, data-driven methods accelerate material discovery and optimization while reducing costs and improving success rates. Symbolic regression is a key to extracting material descriptors from large datasets, in particular the Sure Independence Screening and Sparsifying Operator (SISSO) method. While SISSO needs to store the entire expression space to impose heavy memory demands, it limits the performance in complex problems. To address this issue, we propose a RF-SISSO algorithm by combining Random Forests (RF) with SISSO. In this algorithm, the Random Forest algorithm is used "},"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":"2409.19209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-28T02:15:39Z","cross_cats_sorted":["cond-mat.mtrl-sci","physics.data-an"],"title_canon_sha256":"34b54b58133720fba2cf047e12918c08c13f554fc6d5dcb049b273f323e8c4de","abstract_canon_sha256":"ef6e60d1bb747c9e5e6e3b02a0767f4b866e8d7672ec55c74f3c88f4169590ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:13:12.226690Z","signature_b64":"AgXl8nyB0t5Tu8yBlsZXdtvyCq9ergTgb3o5HYoYw9g1KUxGmyv3Sena37IMMG+rBaaaxmXk7PaqQ5S4m7C3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"611c757a960fdde9b42b70687e3f82c7b818fbd1ccf2bea7e0dffa24544b54e6","last_reissued_at":"2026-07-05T09:13:12.226187Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:13:12.226187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting SISSO Performance on Small Sample Datasets by Using Random Forests Prescreening for Complex Feature Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.mtrl-sci","physics.data-an"],"primary_cat":"cs.LG","authors_text":"Guanqi Liu, Jiaying Xie, Xiaolin Jiang, Zhenpeng Hu","submitted_at":"2024-09-28T02:15:39Z","abstract_excerpt":"In materials science, data-driven methods accelerate material discovery and optimization while reducing costs and improving success rates. Symbolic regression is a key to extracting material descriptors from large datasets, in particular the Sure Independence Screening and Sparsifying Operator (SISSO) method. While SISSO needs to store the entire expression space to impose heavy memory demands, it limits the performance in complex problems. To address this issue, we propose a RF-SISSO algorithm by combining Random Forests (RF) with SISSO. In this algorithm, the Random Forest algorithm is used "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.19209","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/2409.19209/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":"2409.19209","created_at":"2026-07-05T09:13:12.226247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.19209v1","created_at":"2026-07-05T09:13:12.226247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.19209","created_at":"2026-07-05T09:13:12.226247+00:00"},{"alias_kind":"pith_short_12","alias_value":"MEOHK6UWB7O6","created_at":"2026-07-05T09:13:12.226247+00:00"},{"alias_kind":"pith_short_16","alias_value":"MEOHK6UWB7O6TNBL","created_at":"2026-07-05T09:13:12.226247+00:00"},{"alias_kind":"pith_short_8","alias_value":"MEOHK6UW","created_at":"2026-07-05T09:13:12.226247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.12109","citing_title":"A critical assessment of bonding descriptors for predicting materials properties","ref_index":102,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6","json":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6.json","graph_json":"https://pith.science/api/pith-number/MEOHK6UWB7O6TNBLOBUH4P4CY6/graph.json","events_json":"https://pith.science/api/pith-number/MEOHK6UWB7O6TNBLOBUH4P4CY6/events.json","paper":"https://pith.science/paper/MEOHK6UW"},"agent_actions":{"view_html":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6","download_json":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6.json","view_paper":"https://pith.science/paper/MEOHK6UW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.19209&json=true","fetch_graph":"https://pith.science/api/pith-number/MEOHK6UWB7O6TNBLOBUH4P4CY6/graph.json","fetch_events":"https://pith.science/api/pith-number/MEOHK6UWB7O6TNBLOBUH4P4CY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6/action/storage_attestation","attest_author":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6/action/author_attestation","sign_citation":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6/action/citation_signature","submit_replication":"https://pith.science/pith/MEOHK6UWB7O6TNBLOBUH4P4CY6/action/replication_record"}},"created_at":"2026-07-05T09:13:12.226247+00:00","updated_at":"2026-07-05T09:13:12.226247+00:00"}