{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:4ZFHMIZZTGRPXXXRVIR6PU4N7N","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":"b081069806b1a34573868e68445ef6714ac5522af7c7269670e7f4749fb43373","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T17:10:32Z","title_canon_sha256":"aa7ad9c07b2949fd3428cbc18e1a80504ded218c748caa6501ca21113bdda434"},"schema_version":"1.0","source":{"id":"2506.22396","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.22396","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"arxiv_version","alias_value":"2506.22396v1","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22396","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"pith_short_12","alias_value":"4ZFHMIZZTGRP","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"pith_short_16","alias_value":"4ZFHMIZZTGRPXXXR","created_at":"2026-07-05T11:28:26Z"},{"alias_kind":"pith_short_8","alias_value":"4ZFHMIZZ","created_at":"2026-07-05T11:28:26Z"}],"graph_snapshots":[{"event_id":"sha256:f44b031aef8813c6e648bd5e3dcf27dffe5d526180b3c87ace18fb46c99dbbb1","target":"graph","created_at":"2026-07-05T11:28:26Z","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/2506.22396/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Inference accounts for the majority of latency and energy consumption in large language model (LLM) deployments, often exceeding 90% of total cost. While training-time efficiency has seen extensive progress, runtime optimization remains a key bottleneck, particularly under autoregressive decoding. Existing approaches -- such as pruning, quantization, early exits, and speculative decoding -- often require retraining, architectural changes, or disrupt decoding compatibility. We introduce QuickSilver, a modular, token-level framework that enables semantic adaptivity at inference time without alte","authors_text":"Aditya Kumar Guru, Aman Chadha, Amitava Das, Danush Khanna, Kripabandhu Ghosh, Meetu Malhotra, Rubhav Bahirwani, Srivarshinee Sridhar, Vinija Jain, Zidan Ahmed","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T17:10:32Z","title":"QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22396","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":"sha256:5a34a972a5ca3997152119e3d4f074d77879039ef81975d098c8c84c32813812","target":"record","created_at":"2026-07-05T11:28:26Z","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":"b081069806b1a34573868e68445ef6714ac5522af7c7269670e7f4749fb43373","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-27T17:10:32Z","title_canon_sha256":"aa7ad9c07b2949fd3428cbc18e1a80504ded218c748caa6501ca21113bdda434"},"schema_version":"1.0","source":{"id":"2506.22396","kind":"arxiv","version":1}},"canonical_sha256":"e64a76233999a2fbdef1aa23e7d38dfb6e9610417f51550b4b7f0842f9beccb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e64a76233999a2fbdef1aa23e7d38dfb6e9610417f51550b4b7f0842f9beccb5","first_computed_at":"2026-07-05T11:28:26.789239Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:28:26.789239Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uuwejOG5fl4I2laG/Ko4tJkT9pNMVjyeYTfUmpQ1WuAErg3nqfJyOyBT6c5/9FK8aOxO6D6egNy5Schxy3gzAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:28:26.789851Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.22396","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5a34a972a5ca3997152119e3d4f074d77879039ef81975d098c8c84c32813812","sha256:f44b031aef8813c6e648bd5e3dcf27dffe5d526180b3c87ace18fb46c99dbbb1"],"state_sha256":"593e6b005dd8a99346ff4b83f16912ee17da58bae77b41cae40f3cd669604ca3"}