{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:37VWI3C3GA5ITHNXELZYCUIBVP","short_pith_number":"pith:37VWI3C3","canonical_record":{"source":{"id":"1709.05804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T08:07:40Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"6a3c8b36bf7ef5cdc7b2b1fde93d84d04b3705e1a27d9f4d0f115e047e55025c","abstract_canon_sha256":"30a265033df178bd73224438285bd976ff315330e466b223e8ec30cbb24c19de"},"schema_version":"1.0"},"canonical_sha256":"dfeb646c5b303a899db722f3815101abf02d2b4b16d9a42bf280c182f8feaafb","source":{"kind":"arxiv","id":"1709.05804","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05804","created_at":"2026-05-18T00:34:22Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05804v1","created_at":"2026-05-18T00:34:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05804","created_at":"2026-05-18T00:34:22Z"},{"alias_kind":"pith_short_12","alias_value":"37VWI3C3GA5I","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"37VWI3C3GA5ITHNX","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"37VWI3C3","created_at":"2026-05-18T12:30:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:37VWI3C3GA5ITHNXELZYCUIBVP","target":"record","payload":{"canonical_record":{"source":{"id":"1709.05804","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T08:07:40Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"6a3c8b36bf7ef5cdc7b2b1fde93d84d04b3705e1a27d9f4d0f115e047e55025c","abstract_canon_sha256":"30a265033df178bd73224438285bd976ff315330e466b223e8ec30cbb24c19de"},"schema_version":"1.0"},"canonical_sha256":"dfeb646c5b303a899db722f3815101abf02d2b4b16d9a42bf280c182f8feaafb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:34:22.253989Z","signature_b64":"kK8ZK7OO+n7R5jYPzyuwUa9Yehsw5NEW90mZvIxcgueJUN2dtLF+Q2Jhgmrtk5P8+MmS3cosxUAPYixVMOJuCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfeb646c5b303a899db722f3815101abf02d2b4b16d9a42bf280c182f8feaafb","last_reissued_at":"2026-05-18T00:34:22.253598Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:34:22.253598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1709.05804","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":"2026-05-18T00:34:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QhyW0l/6Xv4MIiNdiGqNb5gAr1tzg8MaqMyoYvZvglbOiBA2/JcDu+D41mqlfcmQGjZAblUBzBhLwBrwYl7+CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:58:18.074362Z"},"content_sha256":"3e4f9e9c851cd646d9f9b045d0079ac5f0c035333204d5bd6b02a9e7156513bd","schema_version":"1.0","event_id":"sha256:3e4f9e9c851cd646d9f9b045d0079ac5f0c035333204d5bd6b02a9e7156513bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:37VWI3C3GA5ITHNXELZYCUIBVP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Minimal Effort Back Propagation for Convolutional Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhen Wei, Jingjing Xu, Xuancheng Ren, Xu Sun","submitted_at":"2017-09-18T08:07:40Z","abstract_excerpt":"As traditional neural network consumes a significant amount of computing resources during back propagation, \\citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset of the full gradients are computed to update the model parameters. In this paper we extend this technique into the Convolutional Neural Network(CNN) to reduce calculation in back propagation, and the surprising results verify its validity in CNN: only 5\\% of the gradients are passed back but the model still achieves the same effect as the traditional CNN, or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05804","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:34:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x28iyjsjN3V+51eXV+KeLTq6uWdHg5qzypYiAQeTkYNVadNr9nggLtXOkEu1PeqewA5eWD9IyyBnzCTl+z39DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T11:58:18.074712Z"},"content_sha256":"5144f0da74282eb9330c5a1a13e91ed3a81e93265b616ff34f1934f4bfdba5db","schema_version":"1.0","event_id":"sha256:5144f0da74282eb9330c5a1a13e91ed3a81e93265b616ff34f1934f4bfdba5db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37VWI3C3GA5ITHNXELZYCUIBVP/bundle.json","state_url":"https://pith.science/pith/37VWI3C3GA5ITHNXELZYCUIBVP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37VWI3C3GA5ITHNXELZYCUIBVP/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":"2026-06-06T11:58:18Z","links":{"resolver":"https://pith.science/pith/37VWI3C3GA5ITHNXELZYCUIBVP","bundle":"https://pith.science/pith/37VWI3C3GA5ITHNXELZYCUIBVP/bundle.json","state":"https://pith.science/pith/37VWI3C3GA5ITHNXELZYCUIBVP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37VWI3C3GA5ITHNXELZYCUIBVP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:37VWI3C3GA5ITHNXELZYCUIBVP","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":"30a265033df178bd73224438285bd976ff315330e466b223e8ec30cbb24c19de","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T08:07:40Z","title_canon_sha256":"6a3c8b36bf7ef5cdc7b2b1fde93d84d04b3705e1a27d9f4d0f115e047e55025c"},"schema_version":"1.0","source":{"id":"1709.05804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05804","created_at":"2026-05-18T00:34:22Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05804v1","created_at":"2026-05-18T00:34:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05804","created_at":"2026-05-18T00:34:22Z"},{"alias_kind":"pith_short_12","alias_value":"37VWI3C3GA5I","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_16","alias_value":"37VWI3C3GA5ITHNX","created_at":"2026-05-18T12:30:58Z"},{"alias_kind":"pith_short_8","alias_value":"37VWI3C3","created_at":"2026-05-18T12:30:58Z"}],"graph_snapshots":[{"event_id":"sha256:5144f0da74282eb9330c5a1a13e91ed3a81e93265b616ff34f1934f4bfdba5db","target":"graph","created_at":"2026-05-18T00:34:22Z","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"},"paper":{"abstract_excerpt":"As traditional neural network consumes a significant amount of computing resources during back propagation, \\citet{Sun2017mePropSB} propose a simple yet effective technique to alleviate this problem. In this technique, only a small subset of the full gradients are computed to update the model parameters. In this paper we extend this technique into the Convolutional Neural Network(CNN) to reduce calculation in back propagation, and the surprising results verify its validity in CNN: only 5\\% of the gradients are passed back but the model still achieves the same effect as the traditional CNN, or ","authors_text":"Bingzhen Wei, Jingjing Xu, Xuancheng Ren, Xu Sun","cross_cats":["cs.NE","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T08:07:40Z","title":"Minimal Effort Back Propagation for Convolutional Neural Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05804","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":"sha256:3e4f9e9c851cd646d9f9b045d0079ac5f0c035333204d5bd6b02a9e7156513bd","target":"record","created_at":"2026-05-18T00:34:22Z","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":"30a265033df178bd73224438285bd976ff315330e466b223e8ec30cbb24c19de","cross_cats_sorted":["cs.NE","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-09-18T08:07:40Z","title_canon_sha256":"6a3c8b36bf7ef5cdc7b2b1fde93d84d04b3705e1a27d9f4d0f115e047e55025c"},"schema_version":"1.0","source":{"id":"1709.05804","kind":"arxiv","version":1}},"canonical_sha256":"dfeb646c5b303a899db722f3815101abf02d2b4b16d9a42bf280c182f8feaafb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfeb646c5b303a899db722f3815101abf02d2b4b16d9a42bf280c182f8feaafb","first_computed_at":"2026-05-18T00:34:22.253598Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:22.253598Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kK8ZK7OO+n7R5jYPzyuwUa9Yehsw5NEW90mZvIxcgueJUN2dtLF+Q2Jhgmrtk5P8+MmS3cosxUAPYixVMOJuCA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:22.253989Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.05804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e4f9e9c851cd646d9f9b045d0079ac5f0c035333204d5bd6b02a9e7156513bd","sha256:5144f0da74282eb9330c5a1a13e91ed3a81e93265b616ff34f1934f4bfdba5db"],"state_sha256":"4af757bf1ccdf0bd665e292088181a93e7f583c8adecd42f975e48827af60885"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dxV44C6hezhCt6M69/KMdLN9+I/dv6lpqUqNs2df4Po33DiIPldacZ5RShNl2HuRckooth5qOyu9diokJCWVDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T11:58:18.077049Z","bundle_sha256":"bdf164db9bcf141ea26fa171161c3388b2a484625386a045baddd0a2daff71b6"}}