{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZX77UFRM5BR7IXMSLUFRNOVE4","short_pith_number":"pith:AZX77UFR","schema_version":"1.0","canonical_sha256":"066fffd0b167431fa2ec92e858b5d5271f254f7dcb8327b49ff8e50ed5056136","source":{"kind":"arxiv","id":"2608.06557","version":1},"attestation_state":"computed","paper":{"title":"Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Daniel Berger, Esha Choukse, Muhammad Adnan, Pantea Zardoshti, Prashant J. Nair, Rodrigo Fonseca, Rohan Mahapatra","submitted_at":"2026-08-06T20:14:21Z","abstract_excerpt":"The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests. LLM serving platforms today define response-latency service-level objectives, even though requests within the same service can differ by orders of magnitude in input length, generation length, execution cost, and the availability of reusable KV-cache state. As a result, requests governed by the same service level objective have different urgency: after accounting for the time required to execute them, some have s"},"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":"2608.06557","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-08-06T20:14:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"bf4b861498588538771f68532f0e9f739138131211d185539fff87e3f0da4e02","abstract_canon_sha256":"35b9a1cdf085a61ebb1bae2e61b35a6b11507dba45d2d9f849539abe6d4cdefe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:11:16.389624Z","signature_b64":"ZU/AlAzMWDcY92RITfWP9/BgaB9ncIpt7VLs8pqoGZgvLNgSD+qOXX8lkhW41+LxNdVWTEWhXBIlxYRRRC1hDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"066fffd0b167431fa2ec92e858b5d5271f254f7dcb8327b49ff8e50ed5056136","last_reissued_at":"2026-08-10T01:11:16.387119Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:11:16.387119Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Daniel Berger, Esha Choukse, Muhammad Adnan, Pantea Zardoshti, Prashant J. Nair, Rodrigo Fonseca, Rohan Mahapatra","submitted_at":"2026-08-06T20:14:21Z","abstract_excerpt":"The reasoning and agentic capabilities of large language models have expanded the range of applications they support, from short interactive exchanges to long, compute-heavy requests. LLM serving platforms today define response-latency service-level objectives, even though requests within the same service can differ by orders of magnitude in input length, generation length, execution cost, and the availability of reusable KV-cache state. As a result, requests governed by the same service level objective have different urgency: after accounting for the time required to execute them, some have s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.06557","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/2608.06557/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":"2608.06557","created_at":"2026-08-10T01:11:16.388056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.06557v1","created_at":"2026-08-10T01:11:16.388056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.06557","created_at":"2026-08-10T01:11:16.388056+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZX77UFRM5BR","created_at":"2026-08-10T01:11:16.388056+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZX77UFRM5BR7IXM","created_at":"2026-08-10T01:11:16.388056+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZX77UFR","created_at":"2026-08-10T01:11:16.388056+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/AZX77UFRM5BR7IXMSLUFRNOVE4","json":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4.json","graph_json":"https://pith.science/api/pith-number/AZX77UFRM5BR7IXMSLUFRNOVE4/graph.json","events_json":"https://pith.science/api/pith-number/AZX77UFRM5BR7IXMSLUFRNOVE4/events.json","paper":"https://pith.science/paper/AZX77UFR"},"agent_actions":{"view_html":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4","download_json":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4.json","view_paper":"https://pith.science/paper/AZX77UFR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.06557&json=true","fetch_graph":"https://pith.science/api/pith-number/AZX77UFRM5BR7IXMSLUFRNOVE4/graph.json","fetch_events":"https://pith.science/api/pith-number/AZX77UFRM5BR7IXMSLUFRNOVE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4/action/storage_attestation","attest_author":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4/action/author_attestation","sign_citation":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4/action/citation_signature","submit_replication":"https://pith.science/pith/AZX77UFRM5BR7IXMSLUFRNOVE4/action/replication_record"}},"created_at":"2026-08-10T01:11:16.388056+00:00","updated_at":"2026-08-10T01:11:16.388056+00:00"}