{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LWLE42BQZ5AHEDJG74RFUXAVM4","short_pith_number":"pith:LWLE42BQ","schema_version":"1.0","canonical_sha256":"5d964e6830cf40720d26ff225a5c156702e54af100eeeb27fe27a6b740720b51","source":{"kind":"arxiv","id":"2504.15296","version":1},"attestation_state":"computed","paper":{"title":"Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Yihong Jin, Ze Yang","submitted_at":"2025-04-16T04:00:04Z","abstract_excerpt":"The rapid expansion of AI inference services in the cloud necessitates a robust scalability solution to manage dynamic workloads and maintain high performance. This study proposes a comprehensive scalability optimization framework for cloud AI inference services, focusing on real-time load balancing and autoscaling strategies. The proposed model is a hybrid approach that combines reinforcement learning for adaptive load distribution and deep neural networks for accurate demand forecasting. This multi-layered approach enables the system to anticipate workload fluctuations and proactively adjust"},"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":"2504.15296","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.DC","submitted_at":"2025-04-16T04:00:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"23076588dd683c42c20130ac6b7106ad18f8933cd7bc5edd18e636bca9fe0898","abstract_canon_sha256":"1d881986c4821095d7ca9659c9220c4295728373ec3d0838e22a629cf621db1d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:00.098223Z","signature_b64":"TKMDEpUmbpsu8HppsKpo4EKA6Rqzyqo/pC+ACYKVrXQ8emJ1vVMm+mu9a0HTtbzPZOS6uZpkE8pnE0BlmqEsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d964e6830cf40720d26ff225a5c156702e54af100eeeb27fe27a6b740720b51","last_reissued_at":"2026-07-05T10:52:00.097716Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:00.097716Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scalability Optimization in Cloud-Based AI Inference Services: Strategies for Real-Time Load Balancing and Automated Scaling","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Yihong Jin, Ze Yang","submitted_at":"2025-04-16T04:00:04Z","abstract_excerpt":"The rapid expansion of AI inference services in the cloud necessitates a robust scalability solution to manage dynamic workloads and maintain high performance. This study proposes a comprehensive scalability optimization framework for cloud AI inference services, focusing on real-time load balancing and autoscaling strategies. The proposed model is a hybrid approach that combines reinforcement learning for adaptive load distribution and deep neural networks for accurate demand forecasting. This multi-layered approach enables the system to anticipate workload fluctuations and proactively adjust"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15296","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2504.15296/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":"2504.15296","created_at":"2026-07-05T10:52:00.097783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15296v1","created_at":"2026-07-05T10:52:00.097783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15296","created_at":"2026-07-05T10:52:00.097783+00:00"},{"alias_kind":"pith_short_12","alias_value":"LWLE42BQZ5AH","created_at":"2026-07-05T10:52:00.097783+00:00"},{"alias_kind":"pith_short_16","alias_value":"LWLE42BQZ5AHEDJG","created_at":"2026-07-05T10:52:00.097783+00:00"},{"alias_kind":"pith_short_8","alias_value":"LWLE42BQ","created_at":"2026-07-05T10:52:00.097783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.17900","citing_title":"Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platforms","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4","json":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4.json","graph_json":"https://pith.science/api/pith-number/LWLE42BQZ5AHEDJG74RFUXAVM4/graph.json","events_json":"https://pith.science/api/pith-number/LWLE42BQZ5AHEDJG74RFUXAVM4/events.json","paper":"https://pith.science/paper/LWLE42BQ"},"agent_actions":{"view_html":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4","download_json":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4.json","view_paper":"https://pith.science/paper/LWLE42BQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15296&json=true","fetch_graph":"https://pith.science/api/pith-number/LWLE42BQZ5AHEDJG74RFUXAVM4/graph.json","fetch_events":"https://pith.science/api/pith-number/LWLE42BQZ5AHEDJG74RFUXAVM4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4/action/storage_attestation","attest_author":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4/action/author_attestation","sign_citation":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4/action/citation_signature","submit_replication":"https://pith.science/pith/LWLE42BQZ5AHEDJG74RFUXAVM4/action/replication_record"}},"created_at":"2026-07-05T10:52:00.097783+00:00","updated_at":"2026-07-05T10:52:00.097783+00:00"}