{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CIPQ2BGSK6FRR2SIEBWHRZDMPL","short_pith_number":"pith:CIPQ2BGS","schema_version":"1.0","canonical_sha256":"121f0d04d2578b18ea48206c78e46c7aecd2e8f7b78e50414e3565826b2242f1","source":{"kind":"arxiv","id":"2606.20577","version":1},"attestation_state":"computed","paper":{"title":"Human-Less LLM Serving: Quantifying the Human Tax on Throughput","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.NI","authors_text":"Dan Li, Jianhui Lian, Li Chen, Yong Jiang","submitted_at":"2026-05-03T05:31:35Z","abstract_excerpt":"Every major LLM serving system is designed to meet TTFT and TPOT SLOs. These metrics capture latency as a human user perceives it, and the mechanisms built to satisfy them are now standard infrastructure. We observe that long-horizon AI tasks call LLMs programmatically in tight loops where no human observes TTFT or TPOT. We ask: how much throughput do serving systems sacrifice to meet TTFT and TPOT SLAs that these workloads never need? We conduct a systematic measurement study across chunk sizes, SLO settings, context lengths, and concurrency levels. We find that the human tax on throughput gr"},"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":"2606.20577","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2026-05-03T05:31:35Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"4b22aaf28cf653616b8c41af6535f8b8e7f722226628a3600146e6b026281d70","abstract_canon_sha256":"db6e0c968861bfe344fc116c8e8da7646fb2a4581e89c51e0c424cffc23e5192"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T00:11:50.369911Z","signature_b64":"8t/nOYyGu+OQeUqCVBf5ZXJu+E7OW1LH9tBkc2Sg5LY/X6n+xBzx33x0EvzNO9OOzUd0i4Ku7guPHd7HfRzhBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"121f0d04d2578b18ea48206c78e46c7aecd2e8f7b78e50414e3565826b2242f1","last_reissued_at":"2026-06-23T00:11:50.369382Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T00:11:50.369382Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-Less LLM Serving: Quantifying the Human Tax on Throughput","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.NI","authors_text":"Dan Li, Jianhui Lian, Li Chen, Yong Jiang","submitted_at":"2026-05-03T05:31:35Z","abstract_excerpt":"Every major LLM serving system is designed to meet TTFT and TPOT SLOs. These metrics capture latency as a human user perceives it, and the mechanisms built to satisfy them are now standard infrastructure. We observe that long-horizon AI tasks call LLMs programmatically in tight loops where no human observes TTFT or TPOT. We ask: how much throughput do serving systems sacrifice to meet TTFT and TPOT SLAs that these workloads never need? We conduct a systematic measurement study across chunk sizes, SLO settings, context lengths, and concurrency levels. We find that the human tax on throughput gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20577","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/2606.20577/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":"2606.20577","created_at":"2026-06-23T00:11:50.369445+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.20577v1","created_at":"2026-06-23T00:11:50.369445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20577","created_at":"2026-06-23T00:11:50.369445+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIPQ2BGSK6FR","created_at":"2026-06-23T00:11:50.369445+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIPQ2BGSK6FRR2SI","created_at":"2026-06-23T00:11:50.369445+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIPQ2BGS","created_at":"2026-06-23T00:11:50.369445+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/CIPQ2BGSK6FRR2SIEBWHRZDMPL","json":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL.json","graph_json":"https://pith.science/api/pith-number/CIPQ2BGSK6FRR2SIEBWHRZDMPL/graph.json","events_json":"https://pith.science/api/pith-number/CIPQ2BGSK6FRR2SIEBWHRZDMPL/events.json","paper":"https://pith.science/paper/CIPQ2BGS"},"agent_actions":{"view_html":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL","download_json":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL.json","view_paper":"https://pith.science/paper/CIPQ2BGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.20577&json=true","fetch_graph":"https://pith.science/api/pith-number/CIPQ2BGSK6FRR2SIEBWHRZDMPL/graph.json","fetch_events":"https://pith.science/api/pith-number/CIPQ2BGSK6FRR2SIEBWHRZDMPL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL/action/storage_attestation","attest_author":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL/action/author_attestation","sign_citation":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL/action/citation_signature","submit_replication":"https://pith.science/pith/CIPQ2BGSK6FRR2SIEBWHRZDMPL/action/replication_record"}},"created_at":"2026-06-23T00:11:50.369445+00:00","updated_at":"2026-06-23T00:11:50.369445+00:00"}