{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:2MY2NUXRJOX23EIYWL5RFHZ5A2","short_pith_number":"pith:2MY2NUXR","canonical_record":{"source":{"id":"1711.06528","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T13:36:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a5d999571c5d49ddbd43b385a1bea0b71fb0ec942d25a84caf351c0fa2fff0c4","abstract_canon_sha256":"a68d691bf6d7fd6617f4b70001cc20bc33889551059cbc2a116df5e9405ca5b0"},"schema_version":"1.0"},"canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","source":{"kind":"arxiv","id":"1711.06528","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06528","created_at":"2026-05-17T23:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06528v2","created_at":"2026-05-17T23:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06528","created_at":"2026-05-17T23:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"2MY2NUXRJOX2","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2MY2NUXRJOX23EIY","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2MY2NUXR","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:2MY2NUXRJOX23EIYWL5RFHZ5A2","target":"record","payload":{"canonical_record":{"source":{"id":"1711.06528","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T13:36:51Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a5d999571c5d49ddbd43b385a1bea0b71fb0ec942d25a84caf351c0fa2fff0c4","abstract_canon_sha256":"a68d691bf6d7fd6617f4b70001cc20bc33889551059cbc2a116df5e9405ca5b0"},"schema_version":"1.0"},"canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:51:34.316480Z","signature_b64":"fgQTPetQvbG5gVuCFCKlYkBONJzRWLDMRQcSHweGS7MCHAn8M18C5QG/7ZXtL52xoVoWFfc1nHO1GzSMDsZyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","last_reissued_at":"2026-05-17T23:51:34.315821Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:51:34.315821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1711.06528","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z5KPm8qjoxGKpqAUvHKqpyV3KRQaz8i4RFsEqbx6Q+RdRucdcqwvcH9ze+iyijZhLxDGNNsJEaffMZDRJv0+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:02:57.166636Z"},"content_sha256":"a1454870ca35336ee66269ba319cb9e292e1655c3babccf7b2e0cc3e88d500bc","schema_version":"1.0","event_id":"sha256:a1454870ca35336ee66269ba319cb9e292e1655c3babccf7b2e0cc3e88d500bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:2MY2NUXRJOX23EIYWL5RFHZ5A2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bingzhen Wei, Houfeng Wang, Jingjing Xu, Shuming Ma, Wei Li, Xuancheng Ren, Xu Sun, Yi Zhang","submitted_at":"2017-11-17T13:36:51Z","abstract_excerpt":"We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-k elements (in terms of magnitude) are kept. As a result, only k rows or columns (depending on the layout) of the weight matrix are modified, leading to a linear reduction in the computational cost. Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06528","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:51:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QBIe96a7CDhdJsM2GfMq8r0cfKcxyr064IKtL1WngnjlUws/e/1myBpJEhLVd9uQcAiZ997S31L5KXz1wDuZCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:02:57.166998Z"},"content_sha256":"107c091c827ab30b7d1156ff614c20d97632946bd542a67f53e544f5892d0e5e","schema_version":"1.0","event_id":"sha256:107c091c827ab30b7d1156ff614c20d97632946bd542a67f53e544f5892d0e5e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/bundle.json","state_url":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/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":"2026-06-02T01:02:57Z","links":{"resolver":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2","bundle":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/bundle.json","state":"https://pith.science/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2MY2NUXRJOX23EIYWL5RFHZ5A2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:2MY2NUXRJOX23EIYWL5RFHZ5A2","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":"a68d691bf6d7fd6617f4b70001cc20bc33889551059cbc2a116df5e9405ca5b0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T13:36:51Z","title_canon_sha256":"a5d999571c5d49ddbd43b385a1bea0b71fb0ec942d25a84caf351c0fa2fff0c4"},"schema_version":"1.0","source":{"id":"1711.06528","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1711.06528","created_at":"2026-05-17T23:51:34Z"},{"alias_kind":"arxiv_version","alias_value":"1711.06528v2","created_at":"2026-05-17T23:51:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.06528","created_at":"2026-05-17T23:51:34Z"},{"alias_kind":"pith_short_12","alias_value":"2MY2NUXRJOX2","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"2MY2NUXRJOX23EIY","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"2MY2NUXR","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:107c091c827ab30b7d1156ff614c20d97632946bd542a67f53e544f5892d0e5e","target":"graph","created_at":"2026-05-17T23:51:34Z","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":"We propose a simple yet effective technique to simplify the training and the resulting model of neural networks. In back propagation, only a small subset of the full gradient is computed to update the model parameters. The gradient vectors are sparsified in such a way that only the top-k elements (in terms of magnitude) are kept. As a result, only k rows or columns (depending on the layout) of the weight matrix are modified, leading to a linear reduction in the computational cost. Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldo","authors_text":"Bingzhen Wei, Houfeng Wang, Jingjing Xu, Shuming Ma, Wei Li, Xuancheng Ren, Xu Sun, Yi Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T13:36:51Z","title":"Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.06528","kind":"arxiv","version":2},"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:a1454870ca35336ee66269ba319cb9e292e1655c3babccf7b2e0cc3e88d500bc","target":"record","created_at":"2026-05-17T23:51:34Z","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":"a68d691bf6d7fd6617f4b70001cc20bc33889551059cbc2a116df5e9405ca5b0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-11-17T13:36:51Z","title_canon_sha256":"a5d999571c5d49ddbd43b385a1bea0b71fb0ec942d25a84caf351c0fa2fff0c4"},"schema_version":"1.0","source":{"id":"1711.06528","kind":"arxiv","version":2}},"canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d331a6d2f14bafad9118b2fb129f3d06a2207da4b355f06f5739e501e1da9d76","first_computed_at":"2026-05-17T23:51:34.315821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:51:34.315821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fgQTPetQvbG5gVuCFCKlYkBONJzRWLDMRQcSHweGS7MCHAn8M18C5QG/7ZXtL52xoVoWFfc1nHO1GzSMDsZyCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:51:34.316480Z","signed_message":"canonical_sha256_bytes"},"source_id":"1711.06528","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1454870ca35336ee66269ba319cb9e292e1655c3babccf7b2e0cc3e88d500bc","sha256:107c091c827ab30b7d1156ff614c20d97632946bd542a67f53e544f5892d0e5e"],"state_sha256":"0cc9faeb1ac2687cdb1b95b765787a2b4444bae3337b28771c37416de977ab4a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TcLLo2Sw/JH4D0bueQH+5iDcsKQeyG7xGU2qsEHQ32E1bDuqp4G8cBEV5dOr+50kTAV/KdlRIm1/Z14VSBGICg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:02:57.169650Z","bundle_sha256":"b66b536f9ad47eb20572c62e3c6e3838f7d4b608a3431fe1768b5fac63779e0f"}}