{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:BY2NRMTXTPCRKFR4NSQFPNAT2W","short_pith_number":"pith:BY2NRMTX","schema_version":"1.0","canonical_sha256":"0e34d8b2779bc515163c6ca057b413d5bad6efaed97cc9bcc7fb300a976a686d","source":{"kind":"arxiv","id":"1711.00552","version":1},"attestation_state":"computed","paper":{"title":"Exploiting Apache Spark platform for CMS computing analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.data-an","authors_text":"Daniele Bonacorsi, Justinas Rum\\v{s}evi\\v{c}ius, Luca Menichetti, Marco Meoni, Tommaso Boccali, Valentin Kuznetsov","submitted_at":"2017-11-01T22:17:12Z","abstract_excerpt":"The CERN IT provides a set of Hadoop clusters featuring more than 5 PBytes of raw storage with different open-source, user-level tools available for analytical purposes. The CMS experiment started collecting a large set of computing meta-data, e.g. dataset, file access logs, since 2015. These records represent a valuable, yet scarcely investigated, set of information that needs to be cleaned, categorized and analyzed. CMS can use this information to discover useful patterns and enhance the overall efficiency of the distributed data, improve CPU and site utilization as well as tasks completion "},"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":"1711.00552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.data-an","submitted_at":"2017-11-01T22:17:12Z","cross_cats_sorted":["physics.comp-ph"],"title_canon_sha256":"7f5067094545e8dfc8de048e5eeb776bad4706c19d6b259b4aa7583de32cdf8e","abstract_canon_sha256":"33af589ab9583f9a9018d6386836aef2064da0f55f7c9ba580eab3421930c0bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:30.251061Z","signature_b64":"v1+Gx5Hyf9IC2t6GQpeljDSUkk8rSGPW9CQNxsonAnYdCatXeBw3f/xwSBw9gRHEhxp92cc2R84lJ4Q2GwDABg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e34d8b2779bc515163c6ca057b413d5bad6efaed97cc9bcc7fb300a976a686d","last_reissued_at":"2026-05-18T00:31:30.250573Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:30.250573Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Exploiting Apache Spark platform for CMS computing analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["physics.comp-ph"],"primary_cat":"physics.data-an","authors_text":"Daniele Bonacorsi, Justinas Rum\\v{s}evi\\v{c}ius, Luca Menichetti, Marco Meoni, Tommaso Boccali, Valentin Kuznetsov","submitted_at":"2017-11-01T22:17:12Z","abstract_excerpt":"The CERN IT provides a set of Hadoop clusters featuring more than 5 PBytes of raw storage with different open-source, user-level tools available for analytical purposes. The CMS experiment started collecting a large set of computing meta-data, e.g. dataset, file access logs, since 2015. These records represent a valuable, yet scarcely investigated, set of information that needs to be cleaned, categorized and analyzed. CMS can use this information to discover useful patterns and enhance the overall efficiency of the distributed data, improve CPU and site utilization as well as tasks completion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1711.00552","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":"1711.00552","created_at":"2026-05-18T00:31:30.250655+00:00"},{"alias_kind":"arxiv_version","alias_value":"1711.00552v1","created_at":"2026-05-18T00:31:30.250655+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1711.00552","created_at":"2026-05-18T00:31:30.250655+00:00"},{"alias_kind":"pith_short_12","alias_value":"BY2NRMTXTPCR","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_16","alias_value":"BY2NRMTXTPCRKFR4","created_at":"2026-05-18T12:31:08.081275+00:00"},{"alias_kind":"pith_short_8","alias_value":"BY2NRMTX","created_at":"2026-05-18T12:31:08.081275+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/BY2NRMTXTPCRKFR4NSQFPNAT2W","json":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W.json","graph_json":"https://pith.science/api/pith-number/BY2NRMTXTPCRKFR4NSQFPNAT2W/graph.json","events_json":"https://pith.science/api/pith-number/BY2NRMTXTPCRKFR4NSQFPNAT2W/events.json","paper":"https://pith.science/paper/BY2NRMTX"},"agent_actions":{"view_html":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W","download_json":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W.json","view_paper":"https://pith.science/paper/BY2NRMTX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1711.00552&json=true","fetch_graph":"https://pith.science/api/pith-number/BY2NRMTXTPCRKFR4NSQFPNAT2W/graph.json","fetch_events":"https://pith.science/api/pith-number/BY2NRMTXTPCRKFR4NSQFPNAT2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W/action/storage_attestation","attest_author":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W/action/author_attestation","sign_citation":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W/action/citation_signature","submit_replication":"https://pith.science/pith/BY2NRMTXTPCRKFR4NSQFPNAT2W/action/replication_record"}},"created_at":"2026-05-18T00:31:30.250655+00:00","updated_at":"2026-05-18T00:31:30.250655+00:00"}