{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GFFRXU2JXNNKQYKMRYSFK4JRI5","short_pith_number":"pith:GFFRXU2J","schema_version":"1.0","canonical_sha256":"314b1bd349bb5aa8614c8e245571314746023e205fe55ad0002bf8b2630be74e","source":{"kind":"arxiv","id":"1810.01963","version":4},"attestation_state":"computed","paper":{"title":"Learning Scheduling Algorithms for Data Processing Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongzi Mao, Malte Schwarzkopf, Mohammad Alizadeh, Shaileshh Bojja Venkatakrishnan, Zili Meng","submitted_at":"2018-10-03T20:43:31Z","abstract_excerpt":"Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms. Current systems, however, use simple generalized heuristics and ignore workload characteristics, since developing and tuning a scheduling policy for each workload is infeasible. In this paper, we show that modern machine learning techniques can generate highly-efficient policies automatically. Decima uses reinforcement learning (RL) and neural networks to learn workload-specific scheduling algorithms without any human instruction beyond a high-level objective such as minimizing average job "},"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":"1810.01963","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-10-03T20:43:31Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"457bb029f2887faf446e895bd80c29e5e9b0d34d15cf94d52920ef3d01767f44","abstract_canon_sha256":"71026bc5fd4721de8be59a06577e4f2ae65150169d399c33b7de7e20aaf98640"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:59:05.233880Z","signature_b64":"Xt4ccaA2z3LKDctxtDup9hnuhs80fSdLr5CGWxHuTobT6Gxidb+JW8l3+48/y9bUbSZcYc+hZexyVnjWsZaIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"314b1bd349bb5aa8614c8e245571314746023e205fe55ad0002bf8b2630be74e","last_reissued_at":"2026-07-04T23:59:05.233405Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:59:05.233405Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Scheduling Algorithms for Data Processing Clusters","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Hongzi Mao, Malte Schwarzkopf, Mohammad Alizadeh, Shaileshh Bojja Venkatakrishnan, Zili Meng","submitted_at":"2018-10-03T20:43:31Z","abstract_excerpt":"Efficiently scheduling data processing jobs on distributed compute clusters requires complex algorithms. Current systems, however, use simple generalized heuristics and ignore workload characteristics, since developing and tuning a scheduling policy for each workload is infeasible. In this paper, we show that modern machine learning techniques can generate highly-efficient policies automatically. Decima uses reinforcement learning (RL) and neural networks to learn workload-specific scheduling algorithms without any human instruction beyond a high-level objective such as minimizing average job "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1810.01963","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1810.01963/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1810.01963","created_at":"2026-07-04T23:59:05.233471+00:00"},{"alias_kind":"arxiv_version","alias_value":"1810.01963v4","created_at":"2026-07-04T23:59:05.233471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1810.01963","created_at":"2026-07-04T23:59:05.233471+00:00"},{"alias_kind":"pith_short_12","alias_value":"GFFRXU2JXNNK","created_at":"2026-07-04T23:59:05.233471+00:00"},{"alias_kind":"pith_short_16","alias_value":"GFFRXU2JXNNKQYKM","created_at":"2026-07-04T23:59:05.233471+00:00"},{"alias_kind":"pith_short_8","alias_value":"GFFRXU2J","created_at":"2026-07-04T23:59:05.233471+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.09120","citing_title":"AutoPilot: Learning to Steer High Speed Robust BFT","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07923","citing_title":"Larch: Learned Query Optimization for Semantic Predicates","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"1906.08879","citing_title":"Placeto: Learning Generalizable Device Placement Algorithms for Distributed Machine Learning","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5","json":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5.json","graph_json":"https://pith.science/api/pith-number/GFFRXU2JXNNKQYKMRYSFK4JRI5/graph.json","events_json":"https://pith.science/api/pith-number/GFFRXU2JXNNKQYKMRYSFK4JRI5/events.json","paper":"https://pith.science/paper/GFFRXU2J"},"agent_actions":{"view_html":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5","download_json":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5.json","view_paper":"https://pith.science/paper/GFFRXU2J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1810.01963&json=true","fetch_graph":"https://pith.science/api/pith-number/GFFRXU2JXNNKQYKMRYSFK4JRI5/graph.json","fetch_events":"https://pith.science/api/pith-number/GFFRXU2JXNNKQYKMRYSFK4JRI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5/action/storage_attestation","attest_author":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5/action/author_attestation","sign_citation":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5/action/citation_signature","submit_replication":"https://pith.science/pith/GFFRXU2JXNNKQYKMRYSFK4JRI5/action/replication_record"}},"created_at":"2026-07-04T23:59:05.233471+00:00","updated_at":"2026-07-04T23:59:05.233471+00:00"}