{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:6XKPDF4KK2G6KRNHVO332L6I2T","short_pith_number":"pith:6XKPDF4K","canonical_record":{"source":{"id":"2605.14005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T18:11:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62e3f32e581681bde61c43d619770be3d8632e779f42938b1439fcf33bd969bd","abstract_canon_sha256":"e3cc60dc8e75596b52e76d36c94fea39cac98fd01f9c4769032acbd6ce9efc56"},"schema_version":"1.0"},"canonical_sha256":"f5d4f1978a568de545a7abb7bd2fc8d4c7db6a8f94e6137f4b24625049a5959b","source":{"kind":"arxiv","id":"2605.14005","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14005","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14005v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14005","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"6XKPDF4KK2G6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6XKPDF4KK2G6KRNH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6XKPDF4K","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:6XKPDF4KK2G6KRNHVO332L6I2T","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14005","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T18:11:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"62e3f32e581681bde61c43d619770be3d8632e779f42938b1439fcf33bd969bd","abstract_canon_sha256":"e3cc60dc8e75596b52e76d36c94fea39cac98fd01f9c4769032acbd6ce9efc56"},"schema_version":"1.0"},"canonical_sha256":"f5d4f1978a568de545a7abb7bd2fc8d4c7db6a8f94e6137f4b24625049a5959b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:13.119827Z","signature_b64":"q4bZ3IzIY8zrFukkWtJ3LK39Rp8Ju2TaZoJiM0GhDzEBD5/ts2uNX16/IXGL9ojB0lsadrQjFArR8P34UJyvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5d4f1978a568de545a7abb7bd2fc8d4c7db6a8f94e6137f4b24625049a5959b","last_reissued_at":"2026-05-17T23:39:13.119332Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:13.119332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14005","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzXmHEqQcB3psyBmi0ZhiC/NJGnFppakW4p8sZGoMzooNFj13EJ6rJMZOJHBWOZP2XSVAugbokYDQ3T0pPiNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T10:25:28.951261Z"},"content_sha256":"b8a21acf54b061b397940e65b7742997a297d3fe441ebb1fb8ba048c0dcfeb5e","schema_version":"1.0","event_id":"sha256:b8a21acf54b061b397940e65b7742997a297d3fe441ebb1fb8ba048c0dcfeb5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:6XKPDF4KK2G6KRNHVO332L6I2T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Mistletoe attacks collapse speculative decoding speedup by slashing average accepted draft length while leaving output quality unchanged.","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Chen, Chang Da, Fan Mo, Hao Fang, Kuofeng Gao, Shuoyang Sun, Shu-Tao Xia, Xinhao Zhong, Yi Sun","submitted_at":"2026-05-13T18:11:42Z","abstract_excerpt":"Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically depends on the average accepted length $\\tau$, i.e., how many draft tokens survive each verification step. In this work, we identify a new mechanism-level vulnerability in model-based speculative decoding: the drafter is trained to approximate the target model distribution, but this approximation is inevitably imperfect. Such a drafter-target mismatch creates"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Mistletoe substantially reduces average accepted length τ, collapses speedup, and lowers averaged token throughput, while preserving output quality and perplexity.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that small perturbations can preserve the target model's visible behavior while substantially reducing draft-token acceptability via null-space projection of degradation gradients.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Mistletoe is a stealthy attack that collapses the speedup of speculative decoding by reducing average accepted length τ without changing output semantics or perplexity.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Mistletoe attacks collapse speculative decoding speedup by slashing average accepted draft length while leaving output quality unchanged.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"2f1cbfda2e142373fc47385d6b8996bd062310aaf74c9ccf979a927cec33e339"},"source":{"id":"2605.14005","kind":"arxiv","version":1},"verdict":{"id":"d61135cf-1ae7-49a8-92d2-51daa0fbcdf0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:36:12.382649Z","strongest_claim":"Mistletoe substantially reduces average accepted length τ, collapses speedup, and lowers averaged token throughput, while preserving output quality and perplexity.","one_line_summary":"Mistletoe is a stealthy attack that collapses the speedup of speculative decoding by reducing average accepted length τ without changing output semantics or perplexity.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that small perturbations can preserve the target model's visible behavior while substantially reducing draft-token acceptability via null-space projection of degradation gradients.","pith_extraction_headline":"Mistletoe attacks collapse speculative decoding speedup by slashing average accepted draft length while leaving output quality unchanged."},"references":{"count":15,"sample":[{"doi":"","year":null,"title":"Hydra: Sequentially-dependent draft heads for medusa decoding","work_id":"e51f556b-4111-49b3-96b0-6191c097ea33","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","work_id":"f6202cd1-1a78-4c19-8242-688acf4952b6","ref_index":2,"cited_arxiv_id":"2401.10774","is_internal_anchor":true},{"doi":"","year":null,"title":"Accelerating Large Language Model Decoding with Speculative Sampling","work_id":"b53b11e5-8613-439d-9d9d-0e2a9090d79f","ref_index":3,"cited_arxiv_id":"2302.01318","is_internal_anchor":true},{"doi":"","year":null,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","ref_index":4,"cited_arxiv_id":"2107.03374","is_internal_anchor":true},{"doi":"","year":2023,"title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna","work_id":"9ae0c422-f9e3-4f20-bcc9-3ec30d9df7dd","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":15,"snapshot_sha256":"09a2ee1f7aa0e9a362be8c39addfcbea2a1046604e15f93a46853eaf012e9ccc","internal_anchors":8},"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"},"verdict_id":"d61135cf-1ae7-49a8-92d2-51daa0fbcdf0"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N01sN6bXRDnCKD5D2zqaV7dBmQ5bUrGHF/pkqOcN/82hR0ITdezQpPlLJ+/xJd90fXWLlAUJihpxuuSb32wLCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-21T10:25:28.952196Z"},"content_sha256":"c81e9d835ad058791e3ec5c611afa57f55a02a2ec5ddd492c19efbeb248c5969","schema_version":"1.0","event_id":"sha256:c81e9d835ad058791e3ec5c611afa57f55a02a2ec5ddd492c19efbeb248c5969"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6XKPDF4KK2G6KRNHVO332L6I2T/bundle.json","state_url":"https://pith.science/pith/6XKPDF4KK2G6KRNHVO332L6I2T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6XKPDF4KK2G6KRNHVO332L6I2T/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-21T10:25:28Z","links":{"resolver":"https://pith.science/pith/6XKPDF4KK2G6KRNHVO332L6I2T","bundle":"https://pith.science/pith/6XKPDF4KK2G6KRNHVO332L6I2T/bundle.json","state":"https://pith.science/pith/6XKPDF4KK2G6KRNHVO332L6I2T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6XKPDF4KK2G6KRNHVO332L6I2T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6XKPDF4KK2G6KRNHVO332L6I2T","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":"e3cc60dc8e75596b52e76d36c94fea39cac98fd01f9c4769032acbd6ce9efc56","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T18:11:42Z","title_canon_sha256":"62e3f32e581681bde61c43d619770be3d8632e779f42938b1439fcf33bd969bd"},"schema_version":"1.0","source":{"id":"2605.14005","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14005","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14005v1","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14005","created_at":"2026-05-17T23:39:13Z"},{"alias_kind":"pith_short_12","alias_value":"6XKPDF4KK2G6","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"6XKPDF4KK2G6KRNH","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"6XKPDF4K","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:c81e9d835ad058791e3ec5c611afa57f55a02a2ec5ddd492c19efbeb248c5969","target":"graph","created_at":"2026-05-17T23:39:13Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Mistletoe substantially reduces average accepted length τ, collapses speedup, and lowers averaged token throughput, while preserving output quality and perplexity."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that small perturbations can preserve the target model's visible behavior while substantially reducing draft-token acceptability via null-space projection of degradation gradients."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Mistletoe is a stealthy attack that collapses the speedup of speculative decoding by reducing average accepted length τ without changing output semantics or perplexity."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Mistletoe attacks collapse speculative decoding speedup by slashing average accepted draft length while leaving output quality unchanged."}],"snapshot_sha256":"2f1cbfda2e142373fc47385d6b8996bd062310aaf74c9ccf979a927cec33e339"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Speculative decoding has become a widely adopted technique for accelerating large language model (LLM) inference by drafting multiple candidate tokens and verifying them with a target model in parallel. Its efficiency, however, critically depends on the average accepted length $\\tau$, i.e., how many draft tokens survive each verification step. In this work, we identify a new mechanism-level vulnerability in model-based speculative decoding: the drafter is trained to approximate the target model distribution, but this approximation is inevitably imperfect. Such a drafter-target mismatch creates","authors_text":"Bin Chen, Chang Da, Fan Mo, Hao Fang, Kuofeng Gao, Shuoyang Sun, Shu-Tao Xia, Xinhao Zhong, Yi Sun","cross_cats":["cs.LG"],"headline":"Mistletoe attacks collapse speculative decoding speedup by slashing average accepted draft length while leaving output quality unchanged.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T18:11:42Z","title":"Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding"},"references":{"count":15,"internal_anchors":8,"resolved_work":15,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Hydra: Sequentially-dependent draft heads for medusa decoding","work_id":"e51f556b-4111-49b3-96b0-6191c097ea33","year":null},{"cited_arxiv_id":"2401.10774","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","work_id":"f6202cd1-1a78-4c19-8242-688acf4952b6","year":null},{"cited_arxiv_id":"2302.01318","doi":"","is_internal_anchor":true,"ref_index":3,"title":"Accelerating Large Language Model Decoding with Speculative Sampling","work_id":"b53b11e5-8613-439d-9d9d-0e2a9090d79f","year":null},{"cited_arxiv_id":"2107.03374","doi":"","is_internal_anchor":true,"ref_index":4,"title":"Evaluating Large Language Models Trained on Code","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality.See https://vicuna","work_id":"9ae0c422-f9e3-4f20-bcc9-3ec30d9df7dd","year":2023}],"snapshot_sha256":"09a2ee1f7aa0e9a362be8c39addfcbea2a1046604e15f93a46853eaf012e9ccc"},"source":{"id":"2605.14005","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T05:36:12.382649Z","id":"d61135cf-1ae7-49a8-92d2-51daa0fbcdf0","model_set":{"reader":"grok-4.3"},"one_line_summary":"Mistletoe is a stealthy attack that collapses the speedup of speculative decoding by reducing average accepted length τ without changing output semantics or perplexity.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Mistletoe attacks collapse speculative decoding speedup by slashing average accepted draft length while leaving output quality unchanged.","strongest_claim":"Mistletoe substantially reduces average accepted length τ, collapses speedup, and lowers averaged token throughput, while preserving output quality and perplexity.","weakest_assumption":"The assumption that small perturbations can preserve the target model's visible behavior while substantially reducing draft-token acceptability via null-space projection of degradation gradients."}},"verdict_id":"d61135cf-1ae7-49a8-92d2-51daa0fbcdf0"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b8a21acf54b061b397940e65b7742997a297d3fe441ebb1fb8ba048c0dcfeb5e","target":"record","created_at":"2026-05-17T23:39:13Z","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":"e3cc60dc8e75596b52e76d36c94fea39cac98fd01f9c4769032acbd6ce9efc56","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T18:11:42Z","title_canon_sha256":"62e3f32e581681bde61c43d619770be3d8632e779f42938b1439fcf33bd969bd"},"schema_version":"1.0","source":{"id":"2605.14005","kind":"arxiv","version":1}},"canonical_sha256":"f5d4f1978a568de545a7abb7bd2fc8d4c7db6a8f94e6137f4b24625049a5959b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5d4f1978a568de545a7abb7bd2fc8d4c7db6a8f94e6137f4b24625049a5959b","first_computed_at":"2026-05-17T23:39:13.119332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:13.119332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"q4bZ3IzIY8zrFukkWtJ3LK39Rp8Ju2TaZoJiM0GhDzEBD5/ts2uNX16/IXGL9ojB0lsadrQjFArR8P34UJyvBg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:13.119827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14005","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b8a21acf54b061b397940e65b7742997a297d3fe441ebb1fb8ba048c0dcfeb5e","sha256:c81e9d835ad058791e3ec5c611afa57f55a02a2ec5ddd492c19efbeb248c5969"],"state_sha256":"cc3a97fd66d42bd094e9d236a95a487c959ec4535fb5e62e7a25f7b0523fc4b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nspFK7HjD+lLhcgdQh1MCoEK8DiYpJpOsoIwf0M4jmQ5LV7HlHx5/Q6Q3I+n72BhYm0fBwrogripKi9CsaIoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-21T10:25:28.955866Z","bundle_sha256":"f14de95c431fa3284119245353543627f0f058143eba061cd8efafbcd3a810bc"}}