{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7X36HFZGCWUMFJV2YR5HBH2P64","short_pith_number":"pith:7X36HFZG","schema_version":"1.0","canonical_sha256":"fdf7e3972615a8c2a6bac47a709f4ff70128e4c70128a8beb8c81f43456439c6","source":{"kind":"arxiv","id":"2608.06135","version":1},"attestation_state":"computed","paper":{"title":"LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anjali Gangadhar Katageria, Raghu Nandan Sengupta, Shobha Rani","submitted_at":"2026-08-06T15:07:43Z","abstract_excerpt":"Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving. Recent work has focused on improving scheduling algorithms to boost throughput while maintaining low latency. However, these approaches often assume Poisson request arrivals with constant rates - an assumption that fails to reflect the inherently bursty and dynamic nature of real-world traffic. We propose a lightweight extension to the state-of-the-art WAIT algorithm [1], which adapts to time-varying arrival rates without prior traffic knowledge. The proposed algorithm perform"},"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":"2608.06135","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-08-06T15:07:43Z","cross_cats_sorted":[],"title_canon_sha256":"6fa08622809c0e09d979a30da6418012d94475d4e391dfc80a2aa2afc2ddfe6b","abstract_canon_sha256":"6600306ec329c9e89d679019ac90d511e94b0325a7908e10c6a051bb484ec863"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-07T01:40:40.071519Z","signature_b64":"yIJdXs69L0WgEam2aTJ9eK6pXqtIJkG4AuMPhIwljoe1hoHOqmMxR1hL0mDEqBLK4eKLmBNrcu8APg5LaC/BDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdf7e3972615a8c2a6bac47a709f4ff70128e4c70128a8beb8c81f43456439c6","last_reissued_at":"2026-08-07T01:40:40.069561Z","signature_status":"signed_v1","first_computed_at":"2026-08-07T01:40:40.069561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Inference Under Bursty Workload Distribution: Modifying the WAIT Algorithm","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anjali Gangadhar Katageria, Raghu Nandan Sengupta, Shobha Rani","submitted_at":"2026-08-06T15:07:43Z","abstract_excerpt":"Large Language Models (LLMs) such as ChatGPT and Claude are widely used for information retrieval and problem-solving. Recent work has focused on improving scheduling algorithms to boost throughput while maintaining low latency. However, these approaches often assume Poisson request arrivals with constant rates - an assumption that fails to reflect the inherently bursty and dynamic nature of real-world traffic. We propose a lightweight extension to the state-of-the-art WAIT algorithm [1], which adapts to time-varying arrival rates without prior traffic knowledge. The proposed algorithm perform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06135","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/2608.06135/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":"2608.06135","created_at":"2026-08-07T01:40:40.072409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06135v1","created_at":"2026-08-07T01:40:40.072409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06135","created_at":"2026-08-07T01:40:40.072409+00:00"},{"alias_kind":"pith_short_12","alias_value":"7X36HFZGCWUM","created_at":"2026-08-07T01:40:40.072409+00:00"},{"alias_kind":"pith_short_16","alias_value":"7X36HFZGCWUMFJV2","created_at":"2026-08-07T01:40:40.072409+00:00"},{"alias_kind":"pith_short_8","alias_value":"7X36HFZG","created_at":"2026-08-07T01:40:40.072409+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/7X36HFZGCWUMFJV2YR5HBH2P64","json":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64.json","graph_json":"https://pith.science/api/pith-number/7X36HFZGCWUMFJV2YR5HBH2P64/graph.json","events_json":"https://pith.science/api/pith-number/7X36HFZGCWUMFJV2YR5HBH2P64/events.json","paper":"https://pith.science/paper/7X36HFZG"},"agent_actions":{"view_html":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64","download_json":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64.json","view_paper":"https://pith.science/paper/7X36HFZG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06135&json=true","fetch_graph":"https://pith.science/api/pith-number/7X36HFZGCWUMFJV2YR5HBH2P64/graph.json","fetch_events":"https://pith.science/api/pith-number/7X36HFZGCWUMFJV2YR5HBH2P64/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64/action/storage_attestation","attest_author":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64/action/author_attestation","sign_citation":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64/action/citation_signature","submit_replication":"https://pith.science/pith/7X36HFZGCWUMFJV2YR5HBH2P64/action/replication_record"}},"created_at":"2026-08-07T01:40:40.072409+00:00","updated_at":"2026-08-07T01:40:40.072409+00:00"}