{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:XSTSVLX3HI4GIUOMKWKJBDPGHQ","short_pith_number":"pith:XSTSVLX3","schema_version":"1.0","canonical_sha256":"bca72aaefb3a386451cc5594908de63c1277ad8d83bb69f77fdd823533938118","source":{"kind":"arxiv","id":"1807.00847","version":1},"attestation_state":"computed","paper":{"title":"Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayi Liu, Mohak Shah, Samarth Tripathi, Unmesh Kurup","submitted_at":"2018-07-02T18:12:32Z","abstract_excerpt":"Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We propose a new method to improve the performance of nearly every model including pre-trained models. The proposed method uses an ensemble approach where the networks in the ensemble are constructed by reassigning model parameter values based on the probabilistic distribution of these parameters, calculated towards the end of the training process. For pre-trained m"},"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":"1807.00847","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-07-02T18:12:32Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"6af3ba7c90b8eaace920145858ee71377b8cf6ae70f659917880fd6884d3ee62","abstract_canon_sha256":"2d2022022a8aa5012d3aa26d04b7d75fc7ed8676db97e4b2f5a05dc112761a78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:11:46.271640Z","signature_b64":"kUEmuj/Gt4RP8cJTYmatz+KNhfhljU9FpzeGcWDv+zCMYD1oatCyuc7KXZ5Xb5/rs+z0oiHfhnvKs6/huyFEBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bca72aaefb3a386451cc5594908de63c1277ad8d83bb69f77fdd823533938118","last_reissued_at":"2026-05-18T00:11:46.270893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:11:46.270893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Make (Nearly) Every Neural Network Better: Generating Neural Network Ensembles by Weight Parameter Resampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiayi Liu, Mohak Shah, Samarth Tripathi, Unmesh Kurup","submitted_at":"2018-07-02T18:12:32Z","abstract_excerpt":"Deep Neural Networks (DNNs) have become increasingly popular in computer vision, natural language processing, and other areas. However, training and fine-tuning a deep learning model is computationally intensive and time-consuming. We propose a new method to improve the performance of nearly every model including pre-trained models. The proposed method uses an ensemble approach where the networks in the ensemble are constructed by reassigning model parameter values based on the probabilistic distribution of these parameters, calculated towards the end of the training process. For pre-trained m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.00847","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":""},"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":"1807.00847","created_at":"2026-05-18T00:11:46.271006+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.00847v1","created_at":"2026-05-18T00:11:46.271006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.00847","created_at":"2026-05-18T00:11:46.271006+00:00"},{"alias_kind":"pith_short_12","alias_value":"XSTSVLX3HI4G","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_16","alias_value":"XSTSVLX3HI4GIUOM","created_at":"2026-05-18T12:33:01.666342+00:00"},{"alias_kind":"pith_short_8","alias_value":"XSTSVLX3","created_at":"2026-05-18T12:33:01.666342+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ","json":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ.json","graph_json":"https://pith.science/api/pith-number/XSTSVLX3HI4GIUOMKWKJBDPGHQ/graph.json","events_json":"https://pith.science/api/pith-number/XSTSVLX3HI4GIUOMKWKJBDPGHQ/events.json","paper":"https://pith.science/paper/XSTSVLX3"},"agent_actions":{"view_html":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ","download_json":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ.json","view_paper":"https://pith.science/paper/XSTSVLX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.00847&json=true","fetch_graph":"https://pith.science/api/pith-number/XSTSVLX3HI4GIUOMKWKJBDPGHQ/graph.json","fetch_events":"https://pith.science/api/pith-number/XSTSVLX3HI4GIUOMKWKJBDPGHQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ/action/storage_attestation","attest_author":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ/action/author_attestation","sign_citation":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ/action/citation_signature","submit_replication":"https://pith.science/pith/XSTSVLX3HI4GIUOMKWKJBDPGHQ/action/replication_record"}},"created_at":"2026-05-18T00:11:46.271006+00:00","updated_at":"2026-05-18T00:11:46.271006+00:00"}