{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:AWOVRVAJQYABBGUMTLBAX4T6LX","short_pith_number":"pith:AWOVRVAJ","canonical_record":{"source":{"id":"2005.07292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T23:08:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b78d5d91f608add38ad2fc0dde8e3c8ad7119d231cc940f0f1e434ffb4e7fc2","abstract_canon_sha256":"35680ef80b9dc12de006ab431385b44bb191732b2db71724d549324a90e04abd"},"schema_version":"1.0"},"canonical_sha256":"059d58d4098600109a8c9ac20bf27e5dc16ad23d32fcb95c670f176421f10bf1","source":{"kind":"arxiv","id":"2005.07292","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07292","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07292v1","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07292","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"AWOVRVAJQYAB","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"AWOVRVAJQYABBGUM","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"AWOVRVAJ","created_at":"2026-07-05T01:03:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:AWOVRVAJQYABBGUMTLBAX4T6LX","target":"record","payload":{"canonical_record":{"source":{"id":"2005.07292","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T23:08:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"5b78d5d91f608add38ad2fc0dde8e3c8ad7119d231cc940f0f1e434ffb4e7fc2","abstract_canon_sha256":"35680ef80b9dc12de006ab431385b44bb191732b2db71724d549324a90e04abd"},"schema_version":"1.0"},"canonical_sha256":"059d58d4098600109a8c9ac20bf27e5dc16ad23d32fcb95c670f176421f10bf1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:01.043977Z","signature_b64":"QhEUHkJF3Rzda594gbVtH3k42H/jEZ2zXJ27lGu6f7UO8zUq56DtCGtufIDYlWpXkyfih+XDGnsMSKKnsq2JAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"059d58d4098600109a8c9ac20bf27e5dc16ad23d32fcb95c670f176421f10bf1","last_reissued_at":"2026-07-05T01:03:01.043522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:01.043522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.07292","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DDQ8cR2MMfllbv6jxDaUjWyDP0yXtTXLpbYaXFLxNgoKBZNosu0WziJgE4aQAsLpMdxRshcWGRdjW5wJ/4WYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:13:30.618744Z"},"content_sha256":"eb7a580d8347805790ef000f6e0b317c9dc2fdb13159a1d10bad33506f0b8c83","schema_version":"1.0","event_id":"sha256:eb7a580d8347805790ef000f6e0b317c9dc2fdb13159a1d10bad33506f0b8c83"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:AWOVRVAJQYABBGUMTLBAX4T6LX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dmitry Vetrov, Ekaterina Lobacheva, Nadezhda Chirkova","submitted_at":"2020-05-14T23:08:31Z","abstract_excerpt":"One of the generally accepted views of modern deep learning is that increasing the number of parameters usually leads to better quality. The two easiest ways to increase the number of parameters is to increase the size of the network, e.g. width, or to train a deep ensemble; both approaches improve the performance in practice. In this work, we consider a fixed memory budget setting, and investigate, what is more effective: to train a single wide network, or to perform a memory split -- to train an ensemble of several thinner networks, with the same total number of parameters? We find that, for"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07292","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/2005.07292/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YcYkLFkVGJJgjSR7qfdbOQGIs68O/Xj3QeWzq+b3dqkvalfPaGl+P2t2HUwxSOkYy9zn5myzAB2zBaY8mrW1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T07:13:30.619120Z"},"content_sha256":"0b8895bbea8da9803cfd62b65e98848c0f806f71edcd683feb0f00c103320115","schema_version":"1.0","event_id":"sha256:0b8895bbea8da9803cfd62b65e98848c0f806f71edcd683feb0f00c103320115"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AWOVRVAJQYABBGUMTLBAX4T6LX/bundle.json","state_url":"https://pith.science/pith/AWOVRVAJQYABBGUMTLBAX4T6LX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AWOVRVAJQYABBGUMTLBAX4T6LX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-05T07:13:30Z","links":{"resolver":"https://pith.science/pith/AWOVRVAJQYABBGUMTLBAX4T6LX","bundle":"https://pith.science/pith/AWOVRVAJQYABBGUMTLBAX4T6LX/bundle.json","state":"https://pith.science/pith/AWOVRVAJQYABBGUMTLBAX4T6LX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AWOVRVAJQYABBGUMTLBAX4T6LX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:AWOVRVAJQYABBGUMTLBAX4T6LX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"35680ef80b9dc12de006ab431385b44bb191732b2db71724d549324a90e04abd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T23:08:31Z","title_canon_sha256":"5b78d5d91f608add38ad2fc0dde8e3c8ad7119d231cc940f0f1e434ffb4e7fc2"},"schema_version":"1.0","source":{"id":"2005.07292","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.07292","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"arxiv_version","alias_value":"2005.07292v1","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.07292","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_12","alias_value":"AWOVRVAJQYAB","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_16","alias_value":"AWOVRVAJQYABBGUM","created_at":"2026-07-05T01:03:01Z"},{"alias_kind":"pith_short_8","alias_value":"AWOVRVAJ","created_at":"2026-07-05T01:03:01Z"}],"graph_snapshots":[{"event_id":"sha256:0b8895bbea8da9803cfd62b65e98848c0f806f71edcd683feb0f00c103320115","target":"graph","created_at":"2026-07-05T01:03:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2005.07292/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the generally accepted views of modern deep learning is that increasing the number of parameters usually leads to better quality. The two easiest ways to increase the number of parameters is to increase the size of the network, e.g. width, or to train a deep ensemble; both approaches improve the performance in practice. In this work, we consider a fixed memory budget setting, and investigate, what is more effective: to train a single wide network, or to perform a memory split -- to train an ensemble of several thinner networks, with the same total number of parameters? We find that, for","authors_text":"Dmitry Vetrov, Ekaterina Lobacheva, Nadezhda Chirkova","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T23:08:31Z","title":"Deep Ensembles on a Fixed Memory Budget: One Wide Network or Several Thinner Ones?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.07292","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:eb7a580d8347805790ef000f6e0b317c9dc2fdb13159a1d10bad33506f0b8c83","target":"record","created_at":"2026-07-05T01:03:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"35680ef80b9dc12de006ab431385b44bb191732b2db71724d549324a90e04abd","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-14T23:08:31Z","title_canon_sha256":"5b78d5d91f608add38ad2fc0dde8e3c8ad7119d231cc940f0f1e434ffb4e7fc2"},"schema_version":"1.0","source":{"id":"2005.07292","kind":"arxiv","version":1}},"canonical_sha256":"059d58d4098600109a8c9ac20bf27e5dc16ad23d32fcb95c670f176421f10bf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"059d58d4098600109a8c9ac20bf27e5dc16ad23d32fcb95c670f176421f10bf1","first_computed_at":"2026-07-05T01:03:01.043522Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:01.043522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QhEUHkJF3Rzda594gbVtH3k42H/jEZ2zXJ27lGu6f7UO8zUq56DtCGtufIDYlWpXkyfih+XDGnsMSKKnsq2JAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:01.043977Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.07292","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb7a580d8347805790ef000f6e0b317c9dc2fdb13159a1d10bad33506f0b8c83","sha256:0b8895bbea8da9803cfd62b65e98848c0f806f71edcd683feb0f00c103320115"],"state_sha256":"d4f2c17a563e44fc15f8bb6084dee063cdc845f3404a33f6ab8ef030b9826db2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3zQwTRirOjuqcLjsdRZmyjNPKLuQPseSmzUpbG1RUhkwKjYGpVxU8mcrmmDrHNARN7TvSz4MxtY/agowBz33Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T07:13:30.621398Z","bundle_sha256":"2024cdf6de88857e31b742ce86ffc08f414472015afd7adab163a0cdaf050498"}}