{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZAZ2JELSYBQINLREZBSPFP5RJW","short_pith_number":"pith:ZAZ2JELS","schema_version":"1.0","canonical_sha256":"c833a49172c06086ae24c864f2bfb14d99af2b857c6f82a6fb8577ec3fae0da5","source":{"kind":"arxiv","id":"2408.02301","version":2},"attestation_state":"computed","paper":{"title":"Network Fission Ensembles for Low-Cost Self-Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hojung Lee, Jong-Seok Lee","submitted_at":"2024-08-05T08:23:59Z","abstract_excerpt":"Recent ensemble learning methods for image classification have been shown to improve classification accuracy with low extra cost. However, they still require multiple trained models for ensemble inference, which eventually becomes a significant burden when the model size increases. In this paper, we propose a low-cost ensemble learning and inference, called Network Fission Ensembles (NFE), by converting a conventional network itself into a multi-exit structure. Starting from a given initial network, we first prune some of the weights to reduce the training burden. We then group the remaining w"},"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":"2408.02301","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T08:23:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6d7617b4ff41fc7d0190bfb77f20089080e3e8704ff9a523e13f26e76e4c2a91","abstract_canon_sha256":"d437d1d4f3077daa08870d0d36820911cb9bbe79a5daa58ad614ba72c2953d4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:42.744337Z","signature_b64":"qGmOfpMHkwUhSZJam+7WmPG5XtZuNpX6zxtfI3LYkoJhPMyLDW7FxdWvZ/CgxsUPz/wmXaK6QRZ7o+PEPUuAAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c833a49172c06086ae24c864f2bfb14d99af2b857c6f82a6fb8577ec3fae0da5","last_reissued_at":"2026-07-05T10:06:42.743779Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:42.743779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Network Fission Ensembles for Low-Cost Self-Ensembles","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hojung Lee, Jong-Seok Lee","submitted_at":"2024-08-05T08:23:59Z","abstract_excerpt":"Recent ensemble learning methods for image classification have been shown to improve classification accuracy with low extra cost. However, they still require multiple trained models for ensemble inference, which eventually becomes a significant burden when the model size increases. In this paper, we propose a low-cost ensemble learning and inference, called Network Fission Ensembles (NFE), by converting a conventional network itself into a multi-exit structure. Starting from a given initial network, we first prune some of the weights to reduce the training burden. We then group the remaining w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02301","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/2408.02301/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":"2408.02301","created_at":"2026-07-05T10:06:42.743843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02301v2","created_at":"2026-07-05T10:06:42.743843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02301","created_at":"2026-07-05T10:06:42.743843+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAZ2JELSYBQI","created_at":"2026-07-05T10:06:42.743843+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAZ2JELSYBQINLRE","created_at":"2026-07-05T10:06:42.743843+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAZ2JELS","created_at":"2026-07-05T10:06:42.743843+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":41,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW","json":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW.json","graph_json":"https://pith.science/api/pith-number/ZAZ2JELSYBQINLREZBSPFP5RJW/graph.json","events_json":"https://pith.science/api/pith-number/ZAZ2JELSYBQINLREZBSPFP5RJW/events.json","paper":"https://pith.science/paper/ZAZ2JELS"},"agent_actions":{"view_html":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW","download_json":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW.json","view_paper":"https://pith.science/paper/ZAZ2JELS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02301&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAZ2JELSYBQINLREZBSPFP5RJW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAZ2JELSYBQINLREZBSPFP5RJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW/action/storage_attestation","attest_author":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW/action/author_attestation","sign_citation":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW/action/citation_signature","submit_replication":"https://pith.science/pith/ZAZ2JELSYBQINLREZBSPFP5RJW/action/replication_record"}},"created_at":"2026-07-05T10:06:42.743843+00:00","updated_at":"2026-07-05T10:06:42.743843+00:00"}