{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UP3BPFM5KXH7HUM3AI3CHXUY35","short_pith_number":"pith:UP3BPFM5","canonical_record":{"source":{"id":"2505.07680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T15:46:28Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"398a373f19552f70f18212d9da986c7e5d64b42dfdf552b7181e2f6f1b185d97","abstract_canon_sha256":"fa382ecb8ea1b794a1347884033a7d9447a6e2678eea7f6253254678f9b1c61d"},"schema_version":"1.0"},"canonical_sha256":"a3f617959d55cff3d19b023623de98df49c28ebf6e869af51867bf42593097a8","source":{"kind":"arxiv","id":"2505.07680","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07680","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07680v1","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07680","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"UP3BPFM5KXH7","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"UP3BPFM5KXH7HUM3","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"UP3BPFM5","created_at":"2026-07-05T11:01:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UP3BPFM5KXH7HUM3AI3CHXUY35","target":"record","payload":{"canonical_record":{"source":{"id":"2505.07680","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T15:46:28Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"398a373f19552f70f18212d9da986c7e5d64b42dfdf552b7181e2f6f1b185d97","abstract_canon_sha256":"fa382ecb8ea1b794a1347884033a7d9447a6e2678eea7f6253254678f9b1c61d"},"schema_version":"1.0"},"canonical_sha256":"a3f617959d55cff3d19b023623de98df49c28ebf6e869af51867bf42593097a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:51.654168Z","signature_b64":"LFCxRCrB2Dg9PfVgHNsmNpFwb0qwuJxGq2DPeRHuUVq/25GGjxFAmFmQvWRuEytdLdt4XzVePJ1j9S2uHURLAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3f617959d55cff3d19b023623de98df49c28ebf6e869af51867bf42593097a8","last_reissued_at":"2026-07-05T11:01:51.653642Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:51.653642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.07680","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":"2026-07-05T11:01:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V+3jDCQX9zPoJC0l7SkpRJte3U0wx2XlczC4/73AtY4Dde1i5Y6kCxxxDXRnuw4n7Dk81aAkza2YDXc7sO14Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:26:01.655646Z"},"content_sha256":"7336f505bf09e8940cf95687b33768b14d97206bf720b1f921a1278d4b8407e6","schema_version":"1.0","event_id":"sha256:7336f505bf09e8940cf95687b33768b14d97206bf720b1f921a1278d4b8407e6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UP3BPFM5KXH7HUM3AI3CHXUY35","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Biao Hou, Hang Wu, Haojie Wang, Jianian Zhu, Jidong Zhai, Yinghui Li","submitted_at":"2025-05-12T15:46:28Z","abstract_excerpt":"Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing serving strategies often employ fixed model scales or static two-stage speculative decoding, failing to dynamically adapt to the varying complexities of user requests or fluctuations in system performance. This paper introduces \\systemname{}, a novel framework that reimagines LLM inference as an adaptive routing problem solved through multi-level speculativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07680","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.07680/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:01:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"APdCXlMYgklypI5K26zEBagJDdbtoNeSCswuVBxO/QYhHaQTOR7mdhBFy76d5rDSBqhZHQ66HFFRBMJ2RQROCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:26:01.656455Z"},"content_sha256":"ca710653cb8ac9f3f169e0b1d63a75556a2de7836e80cf29856ad343fb756762","schema_version":"1.0","event_id":"sha256:ca710653cb8ac9f3f169e0b1d63a75556a2de7836e80cf29856ad343fb756762"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UP3BPFM5KXH7HUM3AI3CHXUY35/bundle.json","state_url":"https://pith.science/pith/UP3BPFM5KXH7HUM3AI3CHXUY35/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UP3BPFM5KXH7HUM3AI3CHXUY35/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":"2026-08-17T23:26:01Z","links":{"resolver":"https://pith.science/pith/UP3BPFM5KXH7HUM3AI3CHXUY35","bundle":"https://pith.science/pith/UP3BPFM5KXH7HUM3AI3CHXUY35/bundle.json","state":"https://pith.science/pith/UP3BPFM5KXH7HUM3AI3CHXUY35/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UP3BPFM5KXH7HUM3AI3CHXUY35/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UP3BPFM5KXH7HUM3AI3CHXUY35","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":"fa382ecb8ea1b794a1347884033a7d9447a6e2678eea7f6253254678f9b1c61d","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T15:46:28Z","title_canon_sha256":"398a373f19552f70f18212d9da986c7e5d64b42dfdf552b7181e2f6f1b185d97"},"schema_version":"1.0","source":{"id":"2505.07680","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.07680","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"arxiv_version","alias_value":"2505.07680v1","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07680","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_12","alias_value":"UP3BPFM5KXH7","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_16","alias_value":"UP3BPFM5KXH7HUM3","created_at":"2026-07-05T11:01:51Z"},{"alias_kind":"pith_short_8","alias_value":"UP3BPFM5","created_at":"2026-07-05T11:01:51Z"}],"graph_snapshots":[{"event_id":"sha256:ca710653cb8ac9f3f169e0b1d63a75556a2de7836e80cf29856ad343fb756762","target":"graph","created_at":"2026-07-05T11:01:51Z","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/2505.07680/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) present a critical trade-off between inference quality and computational cost: larger models offer superior capabilities but incur significant latency, while smaller models are faster but less powerful. Existing serving strategies often employ fixed model scales or static two-stage speculative decoding, failing to dynamically adapt to the varying complexities of user requests or fluctuations in system performance. This paper introduces \\systemname{}, a novel framework that reimagines LLM inference as an adaptive routing problem solved through multi-level speculativ","authors_text":"Biao Hou, Hang Wu, Haojie Wang, Jianian Zhu, Jidong Zhai, Yinghui Li","cross_cats":["cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T15:46:28Z","title":"SpecRouter: Adaptive Routing for Multi-Level Speculative Decoding in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07680","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":"sha256:7336f505bf09e8940cf95687b33768b14d97206bf720b1f921a1278d4b8407e6","target":"record","created_at":"2026-07-05T11:01:51Z","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":"fa382ecb8ea1b794a1347884033a7d9447a6e2678eea7f6253254678f9b1c61d","cross_cats_sorted":["cs.DC"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-12T15:46:28Z","title_canon_sha256":"398a373f19552f70f18212d9da986c7e5d64b42dfdf552b7181e2f6f1b185d97"},"schema_version":"1.0","source":{"id":"2505.07680","kind":"arxiv","version":1}},"canonical_sha256":"a3f617959d55cff3d19b023623de98df49c28ebf6e869af51867bf42593097a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3f617959d55cff3d19b023623de98df49c28ebf6e869af51867bf42593097a8","first_computed_at":"2026-07-05T11:01:51.653642Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:01:51.653642Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LFCxRCrB2Dg9PfVgHNsmNpFwb0qwuJxGq2DPeRHuUVq/25GGjxFAmFmQvWRuEytdLdt4XzVePJ1j9S2uHURLAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:01:51.654168Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.07680","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7336f505bf09e8940cf95687b33768b14d97206bf720b1f921a1278d4b8407e6","sha256:ca710653cb8ac9f3f169e0b1d63a75556a2de7836e80cf29856ad343fb756762"],"state_sha256":"1a353c95a4c570a2dad51c28d035db95e9acf3fa65e1cd62da950a2a03f620e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ty+ULFi9Ic+DmKQKt5uKnJAbWRgNXZaVnDAXZ6GXkERFwJWKW0QzLOqIlHkgaDsSj80UkaPp46F1G8trKdquAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:26:01.663411Z","bundle_sha256":"3a0f1e0a1bd28a8b514e35e0b686c79edc114bec227c2fdb311e343196dd8857"}}