{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MW47OT4JPVDTP7CGOOTNGOLVCY","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b4ff200fd305a217a67573c590ba09e8d24fe35e6366fddb1ac32981c27b933c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-11T21:35:19Z","title_canon_sha256":"c8be66a8a4bd772901fb05150c97955abe609dba7370f722c507a353dede8f5f"},"schema_version":"1.0","source":{"id":"2509.09864","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.09864","created_at":"2026-07-05T12:09:50Z"},{"alias_kind":"arxiv_version","alias_value":"2509.09864v1","created_at":"2026-07-05T12:09:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09864","created_at":"2026-07-05T12:09:50Z"},{"alias_kind":"pith_short_12","alias_value":"MW47OT4JPVDT","created_at":"2026-07-05T12:09:50Z"},{"alias_kind":"pith_short_16","alias_value":"MW47OT4JPVDTP7CG","created_at":"2026-07-05T12:09:50Z"},{"alias_kind":"pith_short_8","alias_value":"MW47OT4J","created_at":"2026-07-05T12:09:50Z"}],"graph_snapshots":[{"event_id":"sha256:b93e1e987e332b788ae54cf40354142029a12c3b7a125c62c9c8b13c7014bd7b","target":"graph","created_at":"2026-07-05T12:09:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.09864/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference-time scaling has emerged as a powerful way to improve large language model (LLM) performance by generating multiple candidate responses and selecting among them. However, existing work on dynamic allocation for test-time compute typically considers only parallel generation methods such as best-of-N, overlooking incremental decoding methods like beam search, and has largely ignored latency, focusing only on token usage. We formulate inference-time scaling as a problem of dynamic compute allocation and method selection, where the system must decide which strategy to apply and how much ","authors_text":"Jenny Y. Huang, Mehul Damani, Ramon Astudillo, Wei Sun, Yousef El-Kurdi","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-11T21:35:19Z","title":"Latency and Token-Aware Test-Time Compute"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09864","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c1f94aa4477d3c2321ae9ddbe745ab0d623363731f2a81e2f2d1a2b34018b9da","target":"record","created_at":"2026-07-05T12:09:50Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b4ff200fd305a217a67573c590ba09e8d24fe35e6366fddb1ac32981c27b933c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-11T21:35:19Z","title_canon_sha256":"c8be66a8a4bd772901fb05150c97955abe609dba7370f722c507a353dede8f5f"},"schema_version":"1.0","source":{"id":"2509.09864","kind":"arxiv","version":1}},"canonical_sha256":"65b9f74f897d4737fc4673a6d3397516246917fe9490a9e41477f583f3bb7a1c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"65b9f74f897d4737fc4673a6d3397516246917fe9490a9e41477f583f3bb7a1c","first_computed_at":"2026-07-05T12:09:50.861563Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:50.861563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S8yiEbhl5rDqxJSpiDVJN3kiu3jSeTApmxbD+Jm6OskFTnErl8LzFMvFD9j5cv/wl0fTSp2kfie0/WiT+H1hDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:50.862097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.09864","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1f94aa4477d3c2321ae9ddbe745ab0d623363731f2a81e2f2d1a2b34018b9da","sha256:b93e1e987e332b788ae54cf40354142029a12c3b7a125c62c9c8b13c7014bd7b"],"state_sha256":"e9bb101149e4f57c7992beec35011e6ba1008f0fd67c4a0f69d9d35ca7d4a458"}