{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:BMMYAUMSVLTTH2BXILL7JLE5E4","short_pith_number":"pith:BMMYAUMS","schema_version":"1.0","canonical_sha256":"0b19805192aae733e83742d7f4ac9d2725740878b6f21d4f70ed759ed9b2cc4d","source":{"kind":"arxiv","id":"2202.11782","version":2},"attestation_state":"computed","paper":{"title":"Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Darrell Whitley, Tim Whitaker","submitted_at":"2022-02-23T20:53:54Z","abstract_excerpt":"Ensemble Learning is an effective method for improving generalization in machine learning. However, as state-of-the-art neural networks grow larger, the computational cost associated with training several independent networks becomes expensive. We introduce a fast, low-cost method for creating diverse ensembles of neural networks without needing to train multiple models from scratch. We do this by first training a single parent network. We then create child networks by cloning the parent and dramatically pruning the parameters of each child to create an ensemble of members with unique and dive"},"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":"2202.11782","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-02-23T20:53:54Z","cross_cats_sorted":[],"title_canon_sha256":"20c52697731ad784e57276cebedae2a1afeedf7429da082fc0dc6ff71112d46a","abstract_canon_sha256":"ee96ebcad5517a74f1725bfc044b1a86bebf806a26b87da769d9ee61711c224d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:08:28.892415Z","signature_b64":"TZzlYgw2U0HUUIPlvPr8O4Hl6pAuHAbOh5g4bi1ET3Fcwt41GT58PYGkFUbdlmxPPLC8nGxgcmmI1XEnIe1xAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b19805192aae733e83742d7f4ac9d2725740878b6f21d4f70ed759ed9b2cc4d","last_reissued_at":"2026-07-05T04:08:28.892004Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:08:28.892004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prune and Tune Ensembles: Low-Cost Ensemble Learning With Sparse Independent Subnetworks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Darrell Whitley, Tim Whitaker","submitted_at":"2022-02-23T20:53:54Z","abstract_excerpt":"Ensemble Learning is an effective method for improving generalization in machine learning. However, as state-of-the-art neural networks grow larger, the computational cost associated with training several independent networks becomes expensive. We introduce a fast, low-cost method for creating diverse ensembles of neural networks without needing to train multiple models from scratch. We do this by first training a single parent network. We then create child networks by cloning the parent and dramatically pruning the parameters of each child to create an ensemble of members with unique and dive"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.11782","kind":"arxiv","version":2},"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/2202.11782/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":"2202.11782","created_at":"2026-07-05T04:08:28.892062+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.11782v2","created_at":"2026-07-05T04:08:28.892062+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.11782","created_at":"2026-07-05T04:08:28.892062+00:00"},{"alias_kind":"pith_short_12","alias_value":"BMMYAUMSVLTT","created_at":"2026-07-05T04:08:28.892062+00:00"},{"alias_kind":"pith_short_16","alias_value":"BMMYAUMSVLTTH2BX","created_at":"2026-07-05T04:08:28.892062+00:00"},{"alias_kind":"pith_short_8","alias_value":"BMMYAUMS","created_at":"2026-07-05T04:08:28.892062+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.17909","citing_title":"NeuroTrails: Training with Dynamic Sparse Heads as the Key to Effective Ensembling","ref_index":72,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4","json":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4.json","graph_json":"https://pith.science/api/pith-number/BMMYAUMSVLTTH2BXILL7JLE5E4/graph.json","events_json":"https://pith.science/api/pith-number/BMMYAUMSVLTTH2BXILL7JLE5E4/events.json","paper":"https://pith.science/paper/BMMYAUMS"},"agent_actions":{"view_html":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4","download_json":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4.json","view_paper":"https://pith.science/paper/BMMYAUMS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.11782&json=true","fetch_graph":"https://pith.science/api/pith-number/BMMYAUMSVLTTH2BXILL7JLE5E4/graph.json","fetch_events":"https://pith.science/api/pith-number/BMMYAUMSVLTTH2BXILL7JLE5E4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4/action/storage_attestation","attest_author":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4/action/author_attestation","sign_citation":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4/action/citation_signature","submit_replication":"https://pith.science/pith/BMMYAUMSVLTTH2BXILL7JLE5E4/action/replication_record"}},"created_at":"2026-07-05T04:08:28.892062+00:00","updated_at":"2026-07-05T04:08:28.892062+00:00"}