{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XCQTCWSRZMMWVAWRD5HFXRSDAG","short_pith_number":"pith:XCQTCWSR","canonical_record":{"source":{"id":"1906.06440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-15T00:02:36Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"387e94d5116459ae18f185bceabe9ad860ce4f4509606e9dc20c38e557fedacb","abstract_canon_sha256":"e77d4b146e1f80d08d316004df120648d44b1d2fc5c7fdb0fe06767699811d0d"},"schema_version":"1.0"},"canonical_sha256":"b8a1315a51cb196a82d11f4e5bc643019209f6b1c457c59437cf49a164a9a333","source":{"kind":"arxiv","id":"1906.06440","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06440","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06440v2","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06440","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"XCQTCWSRZMMW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XCQTCWSRZMMWVAWR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XCQTCWSR","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XCQTCWSRZMMWVAWRD5HFXRSDAG","target":"record","payload":{"canonical_record":{"source":{"id":"1906.06440","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-15T00:02:36Z","cross_cats_sorted":["cs.DC","stat.ML"],"title_canon_sha256":"387e94d5116459ae18f185bceabe9ad860ce4f4509606e9dc20c38e557fedacb","abstract_canon_sha256":"e77d4b146e1f80d08d316004df120648d44b1d2fc5c7fdb0fe06767699811d0d"},"schema_version":"1.0"},"canonical_sha256":"b8a1315a51cb196a82d11f4e5bc643019209f6b1c457c59437cf49a164a9a333","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:08.705368Z","signature_b64":"L1s5JdjgyGSUpeIAEprE/oF/66LSEC6mR7pL+SvCNlRiedRJfE5GvRbYKjhQfEii/xZeOska8h1079F9x8oqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8a1315a51cb196a82d11f4e5bc643019209f6b1c457c59437cf49a164a9a333","last_reissued_at":"2026-05-17T23:43:08.704880Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:08.704880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.06440","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":"2026-05-17T23:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cA2Wi2DYLvKlFYbNaufFI2+YGG09Ryr3AjO7ynXzu6buM9TWJ6gObdu1msjlscpZCZXRyuzEpGcuuSN04bibAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:55:40.739462Z"},"content_sha256":"cb34d923f1e191771e3e4c12aa96980ee380f472978ef2536b362b59747ee672","schema_version":"1.0","event_id":"sha256:cb34d923f1e191771e3e4c12aa96980ee380f472978ef2536b362b59747ee672"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XCQTCWSRZMMWVAWRD5HFXRSDAG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"High-Performance Deep Learning via a Single Building Block","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexander Heinecke, Anand Venkat, Dhiraj Kalamkar, Evangelos Georganas, Greg Henry, Hans Pabst, Kunal Banerjee, Michael Anderson, Sasikanth Avancha","submitted_at":"2019-06-15T00:02:36Z","abstract_excerpt":"Deep learning (DL) is one of the most prominent branches of machine learning. Due to the immense computational cost of DL workloads, industry and academia have developed DL libraries with highly-specialized kernels for each workload/architecture, leading to numerous, complex code-bases that strive for performance, yet they are hard to maintain and do not generalize. In this work, we introduce the batch-reduce GEMM kernel and show how the most popular DL algorithms can be formulated with this kernel as the basic building-block. Consequently, the DL library-development degenerates to mere (poten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06440","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":"2026-05-17T23:43:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cWLwMVDHrlqjsovPzWJ6TSqsUdU1BBiFjnM1zHrpxe3N3TArSM9kJRhgluhIo2oWrm98JyuuKFtlsvr8aFdDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T05:55:40.740129Z"},"content_sha256":"220b455049d29adbc08571b6067efb4fb75f8f8c32c23d499bee53d28b8666f0","schema_version":"1.0","event_id":"sha256:220b455049d29adbc08571b6067efb4fb75f8f8c32c23d499bee53d28b8666f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG/bundle.json","state_url":"https://pith.science/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG/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":"2026-05-27T05:55:40Z","links":{"resolver":"https://pith.science/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG","bundle":"https://pith.science/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG/bundle.json","state":"https://pith.science/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XCQTCWSRZMMWVAWRD5HFXRSDAG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XCQTCWSRZMMWVAWRD5HFXRSDAG","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":"e77d4b146e1f80d08d316004df120648d44b1d2fc5c7fdb0fe06767699811d0d","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-15T00:02:36Z","title_canon_sha256":"387e94d5116459ae18f185bceabe9ad860ce4f4509606e9dc20c38e557fedacb"},"schema_version":"1.0","source":{"id":"1906.06440","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06440","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06440v2","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06440","created_at":"2026-05-17T23:43:08Z"},{"alias_kind":"pith_short_12","alias_value":"XCQTCWSRZMMW","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XCQTCWSRZMMWVAWR","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XCQTCWSR","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:220b455049d29adbc08571b6067efb4fb75f8f8c32c23d499bee53d28b8666f0","target":"graph","created_at":"2026-05-17T23:43:08Z","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":"Deep learning (DL) is one of the most prominent branches of machine learning. Due to the immense computational cost of DL workloads, industry and academia have developed DL libraries with highly-specialized kernels for each workload/architecture, leading to numerous, complex code-bases that strive for performance, yet they are hard to maintain and do not generalize. In this work, we introduce the batch-reduce GEMM kernel and show how the most popular DL algorithms can be formulated with this kernel as the basic building-block. Consequently, the DL library-development degenerates to mere (poten","authors_text":"Alexander Heinecke, Anand Venkat, Dhiraj Kalamkar, Evangelos Georganas, Greg Henry, Hans Pabst, Kunal Banerjee, Michael Anderson, Sasikanth Avancha","cross_cats":["cs.DC","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-15T00:02:36Z","title":"High-Performance Deep Learning via a Single Building Block"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06440","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:cb34d923f1e191771e3e4c12aa96980ee380f472978ef2536b362b59747ee672","target":"record","created_at":"2026-05-17T23:43:08Z","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":"e77d4b146e1f80d08d316004df120648d44b1d2fc5c7fdb0fe06767699811d0d","cross_cats_sorted":["cs.DC","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-06-15T00:02:36Z","title_canon_sha256":"387e94d5116459ae18f185bceabe9ad860ce4f4509606e9dc20c38e557fedacb"},"schema_version":"1.0","source":{"id":"1906.06440","kind":"arxiv","version":2}},"canonical_sha256":"b8a1315a51cb196a82d11f4e5bc643019209f6b1c457c59437cf49a164a9a333","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b8a1315a51cb196a82d11f4e5bc643019209f6b1c457c59437cf49a164a9a333","first_computed_at":"2026-05-17T23:43:08.704880Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:08.704880Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"L1s5JdjgyGSUpeIAEprE/oF/66LSEC6mR7pL+SvCNlRiedRJfE5GvRbYKjhQfEii/xZeOska8h1079F9x8oqAA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:08.705368Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06440","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cb34d923f1e191771e3e4c12aa96980ee380f472978ef2536b362b59747ee672","sha256:220b455049d29adbc08571b6067efb4fb75f8f8c32c23d499bee53d28b8666f0"],"state_sha256":"7e7ae867a0fc0aa7f7831a82f68e0320b96cd8bc876d7f1f4910163c95e9c12b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9bUgSAFWrfdQ0ezxaw/VWl/rN3ern2yl2CHo6ao3Bu80SW2AvvgRpgjnGaQF1tjsD4U6VlPbFAtcwIbLP7pvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T05:55:40.743718Z","bundle_sha256":"ed6650e85e3bc65acd9e4b8aa0421f99bf2c84480b2fb27612029fae03810271"}}