{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EEWGKQH2PA4OU37HDISKGOCNDL","short_pith_number":"pith:EEWGKQH2","schema_version":"1.0","canonical_sha256":"212c6540fa7838ea6fe71a24a3384d1ad308f3be425f552f2322e3e1935205d2","source":{"kind":"arxiv","id":"2604.09557","version":2},"attestation_state":"computed","paper":{"title":"SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SPEED-Bench establishes a unified benchmark for speculative decoding that covers diverse semantic domains, throughput across concurrencies, and integration with production engines.","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Benjamin Chislett, Bita Darvish Rouhani, Izzy Putterman, Maor Ashkenazi, Ran Zilberstein, Talor Abramovich, Tiyasa Mitra, Yonatan Geifman","submitted_at":"2026-02-10T16:19:56Z","abstract_excerpt":"Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its effectiveness. Existing benchmarks suffer from limited task diversity, inadequate support for throughput-oriented evaluation, and a reliance on high-level implementations that fail to reflect production environments. To address this, we introduce SPEED-Bench, a comprehensive suite designed to standard"},"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":"2604.09557","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2026-02-10T16:19:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b2cdf3e6cae54ea497f4b57ad966171f2db553c8a8345929034a4d94a88e77c3","abstract_canon_sha256":"219ba16ef468f7d6d98bc8dd6c07845dc2ad5977599c585d9020df519514f8ef"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:44.438371Z","signature_b64":"4pzp2P0kbXQmonuIBvGvdHXFV/VSPTiFG+fiFV9uhWxzsLr2jIo1RDMa5T1Kusggzq5caVfkftaq799d1lwbAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"212c6540fa7838ea6fe71a24a3384d1ad308f3be425f552f2322e3e1935205d2","last_reissued_at":"2026-05-29T02:05:44.437764Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:44.437764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"SPEED-Bench establishes a unified benchmark for speculative decoding that covers diverse semantic domains, throughput across concurrencies, and integration with production engines.","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Benjamin Chislett, Bita Darvish Rouhani, Izzy Putterman, Maor Ashkenazi, Ran Zilberstein, Talor Abramovich, Tiyasa Mitra, Yonatan Geifman","submitted_at":"2026-02-10T16:19:56Z","abstract_excerpt":"Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is inherently data-dependent, meaning that diverse and representative workloads are essential for accurately measuring its effectiveness. Existing benchmarks suffer from limited task diversity, inadequate support for throughput-oriented evaluation, and a reliance on high-level implementations that fail to reflect production environments. To address this, we introduce SPEED-Bench, a comprehensive suite designed to standard"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SPEED-Bench establishes a unified evaluation standard for practical comparisons of SD algorithms by offering diverse semantic domains, throughput splits across concurrencies, and integration with production engines like vLLM and TensorRT-LLM.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the qualitative data split, curated by prioritizing semantic diversity across samples, sufficiently represents real-world workloads and that integration with the named production engines accurately exposes behaviors masked by other benchmarks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"SPEED-Bench is a new standardized benchmark for speculative decoding that supplies semantically diverse qualitative data and throughput-oriented splits across concurrency levels, integrated with vLLM and TensorRT-LLM.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"SPEED-Bench establishes a unified benchmark for speculative decoding that covers diverse semantic domains, throughput across concurrencies, and integration with production engines.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"175995a3c54657284e858c8b6d83def9ca9c5dc6f75644999908b5535f472656"},"source":{"id":"2604.09557","kind":"arxiv","version":2},"verdict":{"id":"8782035f-fd2d-4952-8abc-2d3819e344e0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T03:05:43.307851Z","strongest_claim":"SPEED-Bench establishes a unified evaluation standard for practical comparisons of SD algorithms by offering diverse semantic domains, throughput splits across concurrencies, and integration with production engines like vLLM and TensorRT-LLM.","one_line_summary":"SPEED-Bench is a new standardized benchmark for speculative decoding that supplies semantically diverse qualitative data and throughput-oriented splits across concurrency levels, integrated with vLLM and TensorRT-LLM.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the qualitative data split, curated by prioritizing semantic diversity across samples, sufficiently represents real-world workloads and that integration with the named production engines accurately exposes behaviors masked by other benchmarks.","pith_extraction_headline":"SPEED-Bench establishes a unified benchmark for speculative decoding that covers diverse semantic domains, throughput across concurrencies, and integration with production engines."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09557/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":"2604.09557","created_at":"2026-05-29T02:05:44.437863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09557v2","created_at":"2026-05-29T02:05:44.437863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09557","created_at":"2026-05-29T02:05:44.437863+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEWGKQH2PA4O","created_at":"2026-05-29T02:05:44.437863+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEWGKQH2PA4OU37H","created_at":"2026-05-29T02:05:44.437863+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEWGKQH2","created_at":"2026-05-29T02:05:44.437863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.15609","citing_title":"PSD: Pushing the Pareto Frontier of Diffusion LLMs via Parallel Speculative Decoding","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL","json":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL.json","graph_json":"https://pith.science/api/pith-number/EEWGKQH2PA4OU37HDISKGOCNDL/graph.json","events_json":"https://pith.science/api/pith-number/EEWGKQH2PA4OU37HDISKGOCNDL/events.json","paper":"https://pith.science/paper/EEWGKQH2"},"agent_actions":{"view_html":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL","download_json":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL.json","view_paper":"https://pith.science/paper/EEWGKQH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09557&json=true","fetch_graph":"https://pith.science/api/pith-number/EEWGKQH2PA4OU37HDISKGOCNDL/graph.json","fetch_events":"https://pith.science/api/pith-number/EEWGKQH2PA4OU37HDISKGOCNDL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL/action/storage_attestation","attest_author":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL/action/author_attestation","sign_citation":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL/action/citation_signature","submit_replication":"https://pith.science/pith/EEWGKQH2PA4OU37HDISKGOCNDL/action/replication_record"}},"created_at":"2026-05-29T02:05:44.437863+00:00","updated_at":"2026-05-29T02:05:44.437863+00:00"}