{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:OUDPKC2WRTRF5MZD7JDZ5YESG4","short_pith_number":"pith:OUDPKC2W","schema_version":"1.0","canonical_sha256":"7506f50b568ce25eb323fa479ee09237042f922d57802da292df985c7d8e6f0e","source":{"kind":"arxiv","id":"1810.09376","version":1},"attestation_state":"computed","paper":{"title":"Data Motif-based Proxy Benchmarks for Big Data and AI Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Chen Zheng, Chunjie Luo, Daoyi Zheng, Haibin Wang, Hainan Ye, Jianfeng Zhan, Lei Wang, Rui Ren, Wanling Gao, Xiwen He, Zhen Jia","submitted_at":"2018-10-18T13:58:00Z","abstract_excerpt":"For the architecture community, reasonable simulation time is a strong requirement in addition to performance data accuracy. However, emerging big data and AI workloads are too huge at binary size level and prohibitively expensive to run on cycle-accurate simulators. The concept of data motif, which is identified as a class of units of computation performed on initial or intermediate data, is the first step towards building proxy benchmark to mimic the real-world big data and AI workloads. However, there is no practical way to construct a proxy benchmark based on the data motifs to help simula"},"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":"1810.09376","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2018-10-18T13:58:00Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"e7e4c600b2272074a2f2f4a44285457a1669bd0ab6b43dd5121e7a45ab5b227e","abstract_canon_sha256":"a59c44859186be66b101b5d5002a935a3b1f1915ca49785995b976b4abb86bcd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:02:40.298789Z","signature_b64":"yFFOkqFGC1dpB5J75il4td1r9EzGhkotyWziJF0zEcp6yDUT9UhWtJSQEG7v86QhJyEHZMdgBShtL0z9EuOfDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7506f50b568ce25eb323fa479ee09237042f922d57802da292df985c7d8e6f0e","last_reissued_at":"2026-05-18T00:02:40.298218Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:02:40.298218Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Data Motif-based Proxy Benchmarks for Big Data and AI Workloads","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.DC","authors_text":"Chen Zheng, Chunjie Luo, Daoyi Zheng, Haibin Wang, Hainan Ye, Jianfeng Zhan, Lei Wang, Rui Ren, Wanling Gao, Xiwen He, Zhen Jia","submitted_at":"2018-10-18T13:58:00Z","abstract_excerpt":"For the architecture community, reasonable simulation time is a strong requirement in addition to performance data accuracy. However, emerging big data and AI workloads are too huge at binary size level and prohibitively expensive to run on cycle-accurate simulators. The concept of data motif, which is identified as a class of units of computation performed on initial or intermediate data, is the first step towards building proxy benchmark to mimic the real-world big data and AI workloads. However, there is no practical way to construct a proxy benchmark based on the data motifs to help simula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.09376","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":"1810.09376","created_at":"2026-05-18T00:02:40.298295+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.09376v1","created_at":"2026-05-18T00:02:40.298295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.09376","created_at":"2026-05-18T00:02:40.298295+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/OUDPKC2WRTRF5MZD7JDZ5YESG4","json":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4.json","graph_json":"https://pith.science/api/pith-number/OUDPKC2WRTRF5MZD7JDZ5YESG4/graph.json","events_json":"https://pith.science/api/pith-number/OUDPKC2WRTRF5MZD7JDZ5YESG4/events.json","paper":"https://pith.science/paper/OUDPKC2W"},"agent_actions":{"view_html":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4","download_json":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4.json","view_paper":"https://pith.science/paper/OUDPKC2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.09376&json=true","fetch_graph":"https://pith.science/api/pith-number/OUDPKC2WRTRF5MZD7JDZ5YESG4/graph.json","fetch_events":"https://pith.science/api/pith-number/OUDPKC2WRTRF5MZD7JDZ5YESG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4/action/storage_attestation","attest_author":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4/action/author_attestation","sign_citation":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4/action/citation_signature","submit_replication":"https://pith.science/pith/OUDPKC2WRTRF5MZD7JDZ5YESG4/action/replication_record"}},"created_at":"2026-05-18T00:02:40.298295+00:00","updated_at":"2026-05-18T00:02:40.298295+00:00"}