{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M2MHJIQRGDSQF7B4ZU7VD6FBNY","short_pith_number":"pith:M2MHJIQR","schema_version":"1.0","canonical_sha256":"669874a21130e502fc3ccd3f51f8a16e1b0ccc3fe7926dc9028ebd3cf28297bc","source":{"kind":"arxiv","id":"2503.07545","version":1},"attestation_state":"computed","paper":{"title":"Queueing, Predictions, and LLMs: Challenges and Open Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.AI","authors_text":"Michael Mitzenmacher, Rana Shahout","submitted_at":"2025-03-10T17:12:47Z","abstract_excerpt":"Queueing systems present many opportunities for applying machine-learning predictions, such as estimated service times, to improve system performance. This integration raises numerous open questions about how predictions can be effectively leveraged to improve scheduling decisions. Recent studies explore queues with predicted service times, typically aiming to minimize job time in the system. We review these works, highlight the effectiveness of predictions, and present open questions on queue performance. We then move to consider an important practical example of using predictions in scheduli"},"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":"2503.07545","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-03-10T17:12:47Z","cross_cats_sorted":["cs.DS"],"title_canon_sha256":"a1a76e73e9b563cb77fcc995316cc10931c48b91ee5ae05b2cf9b341166f8f54","abstract_canon_sha256":"4baba983b4ad58d7bc1671cfe384a7a1e3b78128f4cf023ea4cca11fd338b707"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:06.767817Z","signature_b64":"obxa14soRPguiRJu1ZX07g4TbCQrPKCARM9HdJADW2F5kxyCQQIjW1PJU7qFTqa9nuaPjxFuQZOWMM/yXTWvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"669874a21130e502fc3ccd3f51f8a16e1b0ccc3fe7926dc9028ebd3cf28297bc","last_reissued_at":"2026-07-05T10:28:06.766734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:06.766734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Queueing, Predictions, and LLMs: Challenges and Open Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DS"],"primary_cat":"cs.AI","authors_text":"Michael Mitzenmacher, Rana Shahout","submitted_at":"2025-03-10T17:12:47Z","abstract_excerpt":"Queueing systems present many opportunities for applying machine-learning predictions, such as estimated service times, to improve system performance. This integration raises numerous open questions about how predictions can be effectively leveraged to improve scheduling decisions. Recent studies explore queues with predicted service times, typically aiming to minimize job time in the system. We review these works, highlight the effectiveness of predictions, and present open questions on queue performance. We then move to consider an important practical example of using predictions in scheduli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.07545","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/2503.07545/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":"2503.07545","created_at":"2026-07-05T10:28:06.766912+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.07545v1","created_at":"2026-07-05T10:28:06.766912+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.07545","created_at":"2026-07-05T10:28:06.766912+00:00"},{"alias_kind":"pith_short_12","alias_value":"M2MHJIQRGDSQ","created_at":"2026-07-05T10:28:06.766912+00:00"},{"alias_kind":"pith_short_16","alias_value":"M2MHJIQRGDSQF7B4","created_at":"2026-07-05T10:28:06.766912+00:00"},{"alias_kind":"pith_short_8","alias_value":"M2MHJIQR","created_at":"2026-07-05T10:28:06.766912+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04595","citing_title":"A Queueing-Theoretic Framework for Stability Analysis of LLM Inference with KV Cache Memory Constraints","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY","json":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY.json","graph_json":"https://pith.science/api/pith-number/M2MHJIQRGDSQF7B4ZU7VD6FBNY/graph.json","events_json":"https://pith.science/api/pith-number/M2MHJIQRGDSQF7B4ZU7VD6FBNY/events.json","paper":"https://pith.science/paper/M2MHJIQR"},"agent_actions":{"view_html":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY","download_json":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY.json","view_paper":"https://pith.science/paper/M2MHJIQR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.07545&json=true","fetch_graph":"https://pith.science/api/pith-number/M2MHJIQRGDSQF7B4ZU7VD6FBNY/graph.json","fetch_events":"https://pith.science/api/pith-number/M2MHJIQRGDSQF7B4ZU7VD6FBNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY/action/storage_attestation","attest_author":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY/action/author_attestation","sign_citation":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY/action/citation_signature","submit_replication":"https://pith.science/pith/M2MHJIQRGDSQF7B4ZU7VD6FBNY/action/replication_record"}},"created_at":"2026-07-05T10:28:06.766912+00:00","updated_at":"2026-07-05T10:28:06.766912+00:00"}