{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:VPO3OYGFYMF2NYNIBFYRVHZXND","short_pith_number":"pith:VPO3OYGF","schema_version":"1.0","canonical_sha256":"abddb760c5c30ba6e1a809711a9f3768d6d64f1a13afe2ec23df7d868f558bbe","source":{"kind":"arxiv","id":"1809.10505","version":1},"attestation_state":"computed","paper":{"title":"The Convergence of Sparsified Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Renggli, Dan Alistarh, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, Torsten Hoefler","submitted_at":"2018-09-27T13:23:35Z","abstract_excerpt":"Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization, large-batch methods, and gradient sparsification, have been proposed. To date, gradient sparsification methods - where each node sorts gradients by magnitude, and only communicates a subset of the components, accumulating the rest locally - are known to yield some of the largest practical gains. Such methods can reduce the amount of communication per step by up to th"},"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":"1809.10505","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-09-27T13:23:35Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"f6c2668a0d38bf0f7a0c75f64b0efb80f0d5f78b4eae1bc0ba594ed5e726184b","abstract_canon_sha256":"989847ca7c4477f43ebeae2a86ea6d7e8531887042b79b0baac0ff735bc319af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:04:38.204142Z","signature_b64":"Gpd0/DOh+n9qZW4e7qP5MxRBWZquPb96TZ2f2A/6kb2dnsGkck+OygEF6yHueV2hk8EWM9Sq1I3Qgw+DIhrwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"abddb760c5c30ba6e1a809711a9f3768d6d64f1a13afe2ec23df7d868f558bbe","last_reissued_at":"2026-05-18T00:04:38.203530Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:04:38.203530Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Convergence of Sparsified Gradient Methods","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"C\\'edric Renggli, Dan Alistarh, Mikael Johansson, Nikola Konstantinov, Sarit Khirirat, Torsten Hoefler","submitted_at":"2018-09-27T13:23:35Z","abstract_excerpt":"Distributed training of massive machine learning models, in particular deep neural networks, via Stochastic Gradient Descent (SGD) is becoming commonplace. Several families of communication-reduction methods, such as quantization, large-batch methods, and gradient sparsification, have been proposed. To date, gradient sparsification methods - where each node sorts gradients by magnitude, and only communicates a subset of the components, accumulating the rest locally - are known to yield some of the largest practical gains. Such methods can reduce the amount of communication per step by up to th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.10505","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.10505","created_at":"2026-05-18T00:04:38.203610+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.10505v1","created_at":"2026-05-18T00:04:38.203610+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.10505","created_at":"2026-05-18T00:04:38.203610+00:00"},{"alias_kind":"pith_short_12","alias_value":"VPO3OYGFYMF2","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_16","alias_value":"VPO3OYGFYMF2NYNI","created_at":"2026-05-18T12:32:59.047623+00:00"},{"alias_kind":"pith_short_8","alias_value":"VPO3OYGF","created_at":"2026-05-18T12:32:59.047623+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/VPO3OYGFYMF2NYNIBFYRVHZXND","json":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND.json","graph_json":"https://pith.science/api/pith-number/VPO3OYGFYMF2NYNIBFYRVHZXND/graph.json","events_json":"https://pith.science/api/pith-number/VPO3OYGFYMF2NYNIBFYRVHZXND/events.json","paper":"https://pith.science/paper/VPO3OYGF"},"agent_actions":{"view_html":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND","download_json":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND.json","view_paper":"https://pith.science/paper/VPO3OYGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.10505&json=true","fetch_graph":"https://pith.science/api/pith-number/VPO3OYGFYMF2NYNIBFYRVHZXND/graph.json","fetch_events":"https://pith.science/api/pith-number/VPO3OYGFYMF2NYNIBFYRVHZXND/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND/action/storage_attestation","attest_author":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND/action/author_attestation","sign_citation":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND/action/citation_signature","submit_replication":"https://pith.science/pith/VPO3OYGFYMF2NYNIBFYRVHZXND/action/replication_record"}},"created_at":"2026-05-18T00:04:38.203610+00:00","updated_at":"2026-05-18T00:04:38.203610+00:00"}