{"_canonicalization":{"envelope_id":"axm_ + sha256(envelope minus {signature, axiom_id, anchors})","envelope_signature":"ed25519(envelope minus {signature, axiom_id})","json":"sort_keys=True, separators=(',',':'), ensure_ascii=False, allow_nan=False, utf-8","leaf_hash":"sha256(0x00 || canonical_json(envelope_full))","seal_signature":"ed25519(seal minus {signature, sig_algorithm})"},"axiom_id":"axm_05bdf4c1e72d54828bcd5cc467eebccaba9e97050b2ae809a3b6b239fddd965c","bitcoin_anchor":{"bitcoin_attestations":[],"calendar_attestations":[],"ots_url":"","stamped_at":"","status":"pending_next_stamp"},"envelope":{"anchors":[{"chain":"crovia.axiom_graph","height":0,"merkle_proof":"spider_vendor_press_v1","root_at_anchor":"spider_vendor_press_v1"}],"axiom_id":"axm_05bdf4c1e72d54828bcd5cc467eebccaba9e97050b2ae809a3b6b239fddd965c","axiom_type":"AX.OBS","body":{"axiom_subtype":"news.vendor_press.v1","category":"news","fingerprint":"d21a8603d976cc95478a14e6a199102fd0f51db42d8aff6650ea3f92ae154e7c","published":"Wed, 27 May 2026 00:00:00 -0400","receipt_hash":"d21a8603d976cc95478a14e6a199102fd0f51db42d8aff6650ea3f92ae154e7c","schema":"spider.news.vendor_press.v1","spider":"vendor_press","spider_record":{"axiom_subtype":"news.vendor_press.v1","category":"news","decision_hint":"POSITIVE","envelope_target":"AX.OBS","fingerprint":"d21a8603d976cc95478a14e6a199102fd0f51db42d8aff6650ea3f92ae154e7c","observed_at":"2026-05-27T04:43:18.926230Z","parent_run_hash":"6f581915edab4326e2b95fed7c82c2ee149e978d6d7c2443439442a927c31dfa","published":"Wed, 27 May 2026 00:00:00 -0400","runtime_version":"0.1.0","schema":"spider.news.vendor_press.v1","source_status":200,"source_url":"https://export.arxiv.org/rss/cs.AI","spider":"vendor_press","summary_excerpt":"arXiv:2510.01336v2 Announce Type: replace-cross \nAbstract: Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\\times$ slower than token generation when a 3B model speculates for a 70B target model), but most prior works focus only on accelerating drafting. $\\textit{``Intermediate\"}$ verification reduces verification time by discarding inaccurate draft tokens early, but existing methods incur substantial training overheads in incorporating the intermediate verifier, increase the memory footprint to orchestrate the intermediate verification step, and compromise accuracy by relying on approximate heuristics.\n  We propose $\\underline{\\textit{Hi}}\\textit{erarchical }\\underline{\\textit{Spec}}\\textit{ulative Decoding (HiSpec)}$, a framework for high-throughput speculative decoding that exploits $\\textit{early-exit (EE) models}$ for low-overhead inter","title":"HiSpec: Hierarchical Speculative Decoding for LLMs","url":"https://arxiv.org/abs/2510.01336","vendor":"arxiv_cs_ai"},"summary":"arXiv:2510.01336v2 Announce Type: replace-cross \nAbstract: Speculative decoding accelerates LLM inference by using a smaller draft model to speculate tokens that a larger target model verifies. Verification is often the bottleneck (e.g. verification is $4\\times$ slower than token generation when a 3B model speculates for a 70B target model), but most prior works focus only on accelerating drafting. $\\textit{``Intermediate\"}$ verification reduces verification time by discarding inaccurate draft tokens early, but existing methods incur substantial training overheads in incorporating the intermediate verifier, increase the memory footprint to orchestrate the intermediate verification step, and compromise accuracy by relying on approximate heuristics.\n  We propose $\\underline{\\textit{Hi}}\\textit{erarchical }\\underline{\\textit{Spec}}\\textit{ulative Decoding (HiSpec)}$, a framework for high-throughput speculative decoding that exploits $\\textit{early-exit (EE) models}$ for low-overhead inter","title":"HiSpec: Hierarchical Speculative Decoding for LLMs","vendor":"arxiv_cs_ai"},"confidence":{"method":"deterministic"},"decision":"POSITIVE","issued_at":"2026-05-27T04:43:18Z","notes":"Spider vendor_press (news) news.vendor_press.v1","object":{"captured_by":"crovia.spider.vendor_press","primary_source_url":"https://arxiv.org/abs/2510.01336"},"predecessors":[],"schema":"crovia.axiom.v1","signature":"ed25519:5d5df1c89ecc4f18789938b6c61e6034ed107853c50dc5c3c770ddb48977c7920b8ce406a9c2cd81d6c699630d999503da2ac8a50a81261686431de640844e02","signer":"crovia.substrate","subject":{"observed_at":"2026-05-27T04:43:18Z","source_collector":"spider:vendor_press","target_id":"https://arxiv.org/abs/2510.01336"},"tsa":{"authority":"crovia.substrate.bootstrap","rfc3161_token":"{\"kind\":\"crovia.bootstrap.tsa\",\"source_jsonl\":\"/opt/crovia/spider/data/news/vendor_press_v1.jsonl\",\"source_seal_merkle_root\":\"spider_vendor_press_v1\",\"upgrade_path\":\"Sessione H \\u2014 OpenTimestamps weekly anchor\"}"},"zk_mode":"clear","zk_proof":null},"ledger":{"leaf_hash":"6b82910bc4b76a5994fdbd95cbd6b7eb619874f06a9a0bf014ec8582a553ded7","leaf_index":153891,"ledger_path":"/opt/crovia/substrate/axiom_ledger.jsonl"},"merkle_proof":{"hash_alg":"sha256","leaf_prefix":"0x00","node_prefix":"0x01","odd_leaf_rule":"duplicate_last","path":[{"sibling":"313a2415fa36efbe4422a26dd1539ed7613fdc010640a83803244914470e0136","side":"left"},{"sibling":"327239224d34f5f8bd7d34d94b967354eb98cd44d33d6a2df4fa963984beb6d8","side":"left"},{"sibling":"ddd5e843dee6902eac9b2ec24f50d35c2a433d7fcb0ea3dbd9bd99ba60caeefa","side":"right"},{"sibling":"e091688b028505eb2b4feda2f710b1ef94c59a0c58ca227a9375a9ce6f1b8d0a","side":"right"},{"sibling":"f2563c23b5890da80e59949e43c9cc67ea75ee902d082649f5c38ed67060db62","side":"right"},{"sibling":"6644087266f827f79c1b05a55e9f69362c3695a15e4a1b4d950c8f57634f5521","side":"left"},{"sibling":"62e24c574a8b11b6817a5dfdbf87ff01cb3206c901cc1834307cc59fc60392d5","side":"right"},{"sibling":"16c794666e8ffc4b9e71a0bacc0e4f9bbc68a8544c340b385c6d1abff1d748e5","side":"right"},{"sibling":"c14a4eb4b07d22a6a83f548cf6c304559dc63f0e53071e550ecc566dbba50b14","side":"left"},{"sibling":"3165125427a29042fc9d02858a59a68858dbdcb2e19d1afa5f6dd6a95cfbce6a","side":"right"},{"sibling":"04b9a68b8ec6fa37251564383c685c23ce69e5e031df4eae69f79a3a334b68bf","side":"right"},{"sibling":"816f233274bb10f5a122aac086a0c8c697b78fec67a4af55190bb596b7506fab","side":"left"},{"sibling":"d415e6939aee710631f5062799379b547d2c3e3d9a68f263bbb5a693285ab2ca","side":"left"},{"sibling":"374c02d15fb12bd356c179c94766043a982052c6132af8bfc15361b431ffa9f7","side":"right"},{"sibling":"35ca36cee447f0ef7064a25d55f59357c66901e31427729c4c1d8b14aa8adb6c","side":"left"},{"sibling":"990705096edf483cc877217308f731dc42d6f6d99f82880167bbdbbfef32560a","side":"right"},{"sibling":"dd265753d95fa2e2fb4f5768e37fab6f691ccff09ad60d0910ff7dc23bac9226","side":"right"},{"sibling":"d841ad93efda0869e5eb97678f348f03f5caab4353e05ff4bf18f47fb945b822","side":"left"}]},"schema":"crovia.axiom_proof.v1","seal":{"first_collector_run_id":"","first_receipt_hash":"","jsonl_path":"/opt/crovia/substrate/axiom_ledger.jsonl","key_id":"430895f101d38164","last_collector_run_id":"","last_receipt_hash":"","leaf_count":154065,"merkle_root":"4993cfdc172e7880b60667f16789dc2e831ff000f81bb1ecba248e73f1510eca","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","run_id":"hourly_json_retrofit_20260527T053701Z","schema":"crovia.seal.v1","seal_family_version":"crovia-seal-family/1","seal_kind":"substrate_batch","sealed_at":"2026-05-27T05:37:36Z","sig_algorithm":"ed25519","signature":"76ecf118011540405e96506e6219752df04a2850632f2903dc6f10e08b98bc5a42c8d9e1cb5b7c5bf714479806a403df5f34399afa40c23fbb71493a1f77bd0c","signer_version":"1.1.0"},"trust_root":{"key_id":"430895f101d38164","public_key_hex":"cf742e26f75669dc673cb5c0786a1ae23ae8ca19c347317192ce40c28a7ff25c","signature_algorithm":"ed25519","url":"/registry/canon/TRUST_ROOT.md"},"verifier":{"spec":"/registry/canon/AXIOM_RECEIPT_v1.md","url":"/v/axm_05bdf4c1e72d54828bcd5cc467eebccaba9e97050b2ae809a3b6b239fddd965c"}}