{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2015:ZTT45TW4HK3P7BY75BUNSIAPQR","short_pith_number":"pith:ZTT45TW4","schema_version":"1.0","canonical_sha256":"cce7cecedc3ab6ff871fe868d9200f8460a108341c84f163372b884235af5385","source":{"kind":"arxiv","id":"1511.02030","version":1},"attestation_state":"computed","paper":{"title":"ALOJA-ML: A Framework for Automating Characterization and Knowledge Discovery in Hadoop Deployments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Aaron Call, Daron Green, David Carrera, Josep Ll. Berral, Nicolas Poggi, Rob Reinauer","submitted_at":"2015-11-06T10:55:18Z","abstract_excerpt":"This article presents ALOJA-Machine Learning (ALOJA-ML) an extension to the ALOJA project that uses machine learning techniques to interpret Hadoop benchmark performance data and performance tuning; here we detail the approach, efficacy of the model and initial results. Hadoop presents a complex execution environment, where costs and performance depends on a large number of software (SW) configurations and on multiple hardware (HW) deployment choices. These results are accompanied by a test bed and tools to deploy and evaluate the cost-effectiveness of the different hardware configurations, pa"},"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":"1511.02030","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2015-11-06T10:55:18Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"163a65ac13827b3cc78a2bd1826040ddea9bd7ac570c6f0ea660e9d6834e5b51","abstract_canon_sha256":"0d50f2c35075cdcc6b32dd341938e400dd8ef8bd5358dc870bb1e77815ca0903"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:27:38.018940Z","signature_b64":"pF4zTAfTIMQyIxodakxJ2mWIC5qHuXjZA7vkyyS7BWCI2vSSPETBYOi4vyadaPnqqNOeO4AZ8ZEnGeVy7EP6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cce7cecedc3ab6ff871fe868d9200f8460a108341c84f163372b884235af5385","last_reissued_at":"2026-05-18T01:27:38.018208Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:27:38.018208Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALOJA-ML: A Framework for Automating Characterization and Knowledge Discovery in Hadoop Deployments","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Aaron Call, Daron Green, David Carrera, Josep Ll. Berral, Nicolas Poggi, Rob Reinauer","submitted_at":"2015-11-06T10:55:18Z","abstract_excerpt":"This article presents ALOJA-Machine Learning (ALOJA-ML) an extension to the ALOJA project that uses machine learning techniques to interpret Hadoop benchmark performance data and performance tuning; here we detail the approach, efficacy of the model and initial results. Hadoop presents a complex execution environment, where costs and performance depends on a large number of software (SW) configurations and on multiple hardware (HW) deployment choices. These results are accompanied by a test bed and tools to deploy and evaluate the cost-effectiveness of the different hardware configurations, pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1511.02030","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":"1511.02030","created_at":"2026-05-18T01:27:38.018339+00:00"},{"alias_kind":"arxiv_version","alias_value":"1511.02030v1","created_at":"2026-05-18T01:27:38.018339+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1511.02030","created_at":"2026-05-18T01:27:38.018339+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZTT45TW4HK3P","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZTT45TW4HK3P7BY7","created_at":"2026-05-18T12:29:52.810259+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZTT45TW4","created_at":"2026-05-18T12:29:52.810259+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/ZTT45TW4HK3P7BY75BUNSIAPQR","json":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR.json","graph_json":"https://pith.science/api/pith-number/ZTT45TW4HK3P7BY75BUNSIAPQR/graph.json","events_json":"https://pith.science/api/pith-number/ZTT45TW4HK3P7BY75BUNSIAPQR/events.json","paper":"https://pith.science/paper/ZTT45TW4"},"agent_actions":{"view_html":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR","download_json":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR.json","view_paper":"https://pith.science/paper/ZTT45TW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1511.02030&json=true","fetch_graph":"https://pith.science/api/pith-number/ZTT45TW4HK3P7BY75BUNSIAPQR/graph.json","fetch_events":"https://pith.science/api/pith-number/ZTT45TW4HK3P7BY75BUNSIAPQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR/action/storage_attestation","attest_author":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR/action/author_attestation","sign_citation":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR/action/citation_signature","submit_replication":"https://pith.science/pith/ZTT45TW4HK3P7BY75BUNSIAPQR/action/replication_record"}},"created_at":"2026-05-18T01:27:38.018339+00:00","updated_at":"2026-05-18T01:27:38.018339+00:00"}