{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2014:R4N6FYHTVTUWRQKBI2MAYLXIJG","short_pith_number":"pith:R4N6FYHT","schema_version":"1.0","canonical_sha256":"8f1be2e0f3ace968c14146980c2ee849939e4ac4af96e430d6aa301c9dcc0361","source":{"kind":"arxiv","id":"1411.3436","version":2},"attestation_state":"computed","paper":{"title":"SelfieBoost: A Boosting Algorithm for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Shai Shalev-Shwartz","submitted_at":"2014-11-13T03:34:32Z","abstract_excerpt":"We describe and analyze a new boosting algorithm for deep learning called SelfieBoost. Unlike other boosting algorithms, like AdaBoost, which construct ensembles of classifiers, SelfieBoost boosts the accuracy of a single network. We prove a $\\log(1/\\epsilon)$ convergence rate for SelfieBoost under some \"SGD success\" assumption which seems to hold in practice."},"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":"1411.3436","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-11-13T03:34:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"1bdfef5463a149924c35b69b97808722ac7eed80277fcba3b16e8a1da0f56ac8","abstract_canon_sha256":"53838268f57c57be17c3147f5c06f999f399524cd36f3ef6e426e1169429b000"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:46:49.889158Z","signature_b64":"Eq0R4aZNu+iTDHZOhIMq6y9iK47AZD387VnkK//BHQJp7oBG+72IX7+X5/dbDp6MxYHJDtc/x+ftj+T2OZJCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1be2e0f3ace968c14146980c2ee849939e4ac4af96e430d6aa301c9dcc0361","last_reissued_at":"2026-05-18T00:46:49.888491Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:46:49.888491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SelfieBoost: A Boosting Algorithm for Deep Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Shai Shalev-Shwartz","submitted_at":"2014-11-13T03:34:32Z","abstract_excerpt":"We describe and analyze a new boosting algorithm for deep learning called SelfieBoost. Unlike other boosting algorithms, like AdaBoost, which construct ensembles of classifiers, SelfieBoost boosts the accuracy of a single network. We prove a $\\log(1/\\epsilon)$ convergence rate for SelfieBoost under some \"SGD success\" assumption which seems to hold in practice."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1411.3436","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":""},"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":"1411.3436","created_at":"2026-05-18T00:46:49.888589+00:00"},{"alias_kind":"arxiv_version","alias_value":"1411.3436v2","created_at":"2026-05-18T00:46:49.888589+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1411.3436","created_at":"2026-05-18T00:46:49.888589+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4N6FYHTVTUW","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4N6FYHTVTUWRQKB","created_at":"2026-05-18T12:28:46.137349+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4N6FYHT","created_at":"2026-05-18T12:28:46.137349+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/R4N6FYHTVTUWRQKBI2MAYLXIJG","json":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG.json","graph_json":"https://pith.science/api/pith-number/R4N6FYHTVTUWRQKBI2MAYLXIJG/graph.json","events_json":"https://pith.science/api/pith-number/R4N6FYHTVTUWRQKBI2MAYLXIJG/events.json","paper":"https://pith.science/paper/R4N6FYHT"},"agent_actions":{"view_html":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG","download_json":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG.json","view_paper":"https://pith.science/paper/R4N6FYHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1411.3436&json=true","fetch_graph":"https://pith.science/api/pith-number/R4N6FYHTVTUWRQKBI2MAYLXIJG/graph.json","fetch_events":"https://pith.science/api/pith-number/R4N6FYHTVTUWRQKBI2MAYLXIJG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG/action/storage_attestation","attest_author":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG/action/author_attestation","sign_citation":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG/action/citation_signature","submit_replication":"https://pith.science/pith/R4N6FYHTVTUWRQKBI2MAYLXIJG/action/replication_record"}},"created_at":"2026-05-18T00:46:49.888589+00:00","updated_at":"2026-05-18T00:46:49.888589+00:00"}