{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:GNMABAXALPRSZSNOL2IEZ5FEZA","short_pith_number":"pith:GNMABAXA","canonical_record":{"source":{"id":"2005.00570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T18:56:18Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"65f9ba1cb91bb5888393bd312dddd711fe205cabdc6ec97771314f236991a53d","abstract_canon_sha256":"8ac9baa3084b7302e47925ed734618dd986529f25e352a79b6e1591753331427"},"schema_version":"1.0"},"canonical_sha256":"33580082e05be32cc9ae5e904cf4a4c8082df083837e17ff7cb7010eb16dca16","source":{"kind":"arxiv","id":"2005.00570","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00570","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00570v1","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00570","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"pith_short_12","alias_value":"GNMABAXALPRS","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"pith_short_16","alias_value":"GNMABAXALPRSZSNO","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"pith_short_8","alias_value":"GNMABAXA","created_at":"2026-07-05T00:59:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:GNMABAXALPRSZSNOL2IEZ5FEZA","target":"record","payload":{"canonical_record":{"source":{"id":"2005.00570","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T18:56:18Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"65f9ba1cb91bb5888393bd312dddd711fe205cabdc6ec97771314f236991a53d","abstract_canon_sha256":"8ac9baa3084b7302e47925ed734618dd986529f25e352a79b6e1591753331427"},"schema_version":"1.0"},"canonical_sha256":"33580082e05be32cc9ae5e904cf4a4c8082df083837e17ff7cb7010eb16dca16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:59.585364Z","signature_b64":"9zcskPHj94EWDqQqTvuNpojq1t61jgGNIJ3NE2cilG+wP6RS5serI9CclJXSZlD/mRq2fx9hGb0ZH+/7fDJ3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33580082e05be32cc9ae5e904cf4a4c8082df083837e17ff7cb7010eb16dca16","last_reissued_at":"2026-07-05T00:59:59.585007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:59.585007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.00570","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":"2026-07-05T00:59:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L6pPkQIz08RHAqlIKqe5vufb9wOOe6QYZ7Qvd7VjVv362sqUJguNoW6V/lW0JVOqMqS5nZzsHFxoGv50u8IBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:53:42.726103Z"},"content_sha256":"96c21d827c5a71fc19a33d653f8a208ea93c9d05a0de4dcbd1ed87497e803bfb","schema_version":"1.0","event_id":"sha256:96c21d827c5a71fc19a33d653f8a208ea93c9d05a0de4dcbd1ed87497e803bfb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:GNMABAXALPRSZSNOL2IEZ5FEZA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When Ensembling Smaller Models is More Efficient than Single Large Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Boqing Gong, Dan Kondratyuk, Matthew Brown, Mingxing Tan","submitted_at":"2020-05-01T18:56:18Z","abstract_excerpt":"Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their predictions. This approach is commonly reserved for the largest models, as it is commonly held that increasing the model size provides a more substantial reduction in error than ensembling smaller models. However, we show results from experiments on CIFAR-10 and ImageNet that ensembles can outperform single models with both higher accuracy and requiring fewer total FLOPs to compute, even when those individual models' weights a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00570","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/2005.00570/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":"2026-07-05T00:59:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9pXoeGQnM0EKdAHBzLhE9vhlDyU94qgqgCdDY9+sDlyf+Q+aXge19F3UBfSCJrN1PyyZowAYejKkeEBRe5oYCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:53:42.726493Z"},"content_sha256":"f88fc72fe5f5dcb69aa70f1cb824a13d86b0336f54c25bb6a40c47cb774e815a","schema_version":"1.0","event_id":"sha256:f88fc72fe5f5dcb69aa70f1cb824a13d86b0336f54c25bb6a40c47cb774e815a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GNMABAXALPRSZSNOL2IEZ5FEZA/bundle.json","state_url":"https://pith.science/pith/GNMABAXALPRSZSNOL2IEZ5FEZA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GNMABAXALPRSZSNOL2IEZ5FEZA/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":"2026-08-05T03:53:42Z","links":{"resolver":"https://pith.science/pith/GNMABAXALPRSZSNOL2IEZ5FEZA","bundle":"https://pith.science/pith/GNMABAXALPRSZSNOL2IEZ5FEZA/bundle.json","state":"https://pith.science/pith/GNMABAXALPRSZSNOL2IEZ5FEZA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GNMABAXALPRSZSNOL2IEZ5FEZA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:GNMABAXALPRSZSNOL2IEZ5FEZA","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":"8ac9baa3084b7302e47925ed734618dd986529f25e352a79b6e1591753331427","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T18:56:18Z","title_canon_sha256":"65f9ba1cb91bb5888393bd312dddd711fe205cabdc6ec97771314f236991a53d"},"schema_version":"1.0","source":{"id":"2005.00570","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.00570","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"arxiv_version","alias_value":"2005.00570v1","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00570","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"pith_short_12","alias_value":"GNMABAXALPRS","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"pith_short_16","alias_value":"GNMABAXALPRSZSNO","created_at":"2026-07-05T00:59:59Z"},{"alias_kind":"pith_short_8","alias_value":"GNMABAXA","created_at":"2026-07-05T00:59:59Z"}],"graph_snapshots":[{"event_id":"sha256:f88fc72fe5f5dcb69aa70f1cb824a13d86b0336f54c25bb6a40c47cb774e815a","target":"graph","created_at":"2026-07-05T00:59:59Z","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/2005.00570/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Ensembling is a simple and popular technique for boosting evaluation performance by training multiple models (e.g., with different initializations) and aggregating their predictions. This approach is commonly reserved for the largest models, as it is commonly held that increasing the model size provides a more substantial reduction in error than ensembling smaller models. However, we show results from experiments on CIFAR-10 and ImageNet that ensembles can outperform single models with both higher accuracy and requiring fewer total FLOPs to compute, even when those individual models' weights a","authors_text":"Boqing Gong, Dan Kondratyuk, Matthew Brown, Mingxing Tan","cross_cats":["cs.CV","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T18:56:18Z","title":"When Ensembling Smaller Models is More Efficient than Single Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00570","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":"sha256:96c21d827c5a71fc19a33d653f8a208ea93c9d05a0de4dcbd1ed87497e803bfb","target":"record","created_at":"2026-07-05T00:59:59Z","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":"8ac9baa3084b7302e47925ed734618dd986529f25e352a79b6e1591753331427","cross_cats_sorted":["cs.CV","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-05-01T18:56:18Z","title_canon_sha256":"65f9ba1cb91bb5888393bd312dddd711fe205cabdc6ec97771314f236991a53d"},"schema_version":"1.0","source":{"id":"2005.00570","kind":"arxiv","version":1}},"canonical_sha256":"33580082e05be32cc9ae5e904cf4a4c8082df083837e17ff7cb7010eb16dca16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"33580082e05be32cc9ae5e904cf4a4c8082df083837e17ff7cb7010eb16dca16","first_computed_at":"2026-07-05T00:59:59.585007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:59.585007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9zcskPHj94EWDqQqTvuNpojq1t61jgGNIJ3NE2cilG+wP6RS5serI9CclJXSZlD/mRq2fx9hGb0ZH+/7fDJ3Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:59.585364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.00570","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96c21d827c5a71fc19a33d653f8a208ea93c9d05a0de4dcbd1ed87497e803bfb","sha256:f88fc72fe5f5dcb69aa70f1cb824a13d86b0336f54c25bb6a40c47cb774e815a"],"state_sha256":"034cb21271b6c1b1c0acc040837d87ec220449a78e3e168a6352f637db738183"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gbSuatGB5eEapDeSsX/TB5arN9ez5C/WdyIy55MWmQekWUNe2/WV8i1aGEbUcquiyv8mPUbGQxi4Pe028xtbAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:53:42.728852Z","bundle_sha256":"a6c36cd280ec376512256ae73e002459d52a6ca0f9b3af2e6e62f347f65accfa"}}