{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NSEOJZWUUYBNHIGRWTNPRKUXBM","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":"4b9b4606dd1c0b7bfc411db98f9eb68e8034d5c1fd503d27c69f730fc9dd5438","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:55:08Z","title_canon_sha256":"d8961ae18c05d9aeb7deb4cc1033e91cfa7b81d791f19c829b47e2e93930ff38"},"schema_version":"1.0","source":{"id":"2405.19261","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.19261","created_at":"2026-07-05T09:23:33Z"},{"alias_kind":"arxiv_version","alias_value":"2405.19261v2","created_at":"2026-07-05T09:23:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.19261","created_at":"2026-07-05T09:23:33Z"},{"alias_kind":"pith_short_12","alias_value":"NSEOJZWUUYBN","created_at":"2026-07-05T09:23:33Z"},{"alias_kind":"pith_short_16","alias_value":"NSEOJZWUUYBNHIGR","created_at":"2026-07-05T09:23:33Z"},{"alias_kind":"pith_short_8","alias_value":"NSEOJZWU","created_at":"2026-07-05T09:23:33Z"}],"graph_snapshots":[{"event_id":"sha256:ed0016af6e00c640b5bdd91bda754299df84648b496f3ac08c41ebf3980af471","target":"graph","created_at":"2026-07-05T09:23:33Z","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/2405.19261/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cascades and speculative decoding are two common approaches to improving language models' inference efficiency. Both approaches involve interleaving models of different sizes, but via fundamentally distinct mechanisms: cascades employ a deferral rule that invokes the larger model only for \"hard\" inputs, while speculative decoding uses speculative execution to primarily invoke the larger model in parallel verification mode. These mechanisms offer different benefits: empirically, cascades offer better cost-quality trade-offs, often even outperforming the large model, while theoretically, specula","authors_text":"Aditya Krishna Menon, Ankit Singh Rawat, Harikrishna Narasimhan, Neha Gupta, Sanjiv Kumar, Seungyeon Kim, Wittawat Jitkrittum","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:55:08Z","title":"Faster Cascades via Speculative Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.19261","kind":"arxiv","version":2},"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":"sha256:65d625448072b7f64ed48785db11e042da1a859370cbae082b3c3b68303d43c0","target":"record","created_at":"2026-07-05T09:23:33Z","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":"4b9b4606dd1c0b7bfc411db98f9eb68e8034d5c1fd503d27c69f730fc9dd5438","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-29T16:55:08Z","title_canon_sha256":"d8961ae18c05d9aeb7deb4cc1033e91cfa7b81d791f19c829b47e2e93930ff38"},"schema_version":"1.0","source":{"id":"2405.19261","kind":"arxiv","version":2}},"canonical_sha256":"6c88e4e6d4a602d3a0d1b4daf8aa970b07117f6516506d0c43a0e6501641f775","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6c88e4e6d4a602d3a0d1b4daf8aa970b07117f6516506d0c43a0e6501641f775","first_computed_at":"2026-07-05T09:23:33.275861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:33.275861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Gl8ltS/0HkNjG7dYOXvIhQFCbqyV1tRhWAmuxxFO8lGBDWDA663DW6Js2NB/2vyG0uwQwP9wH+skKKTakYmDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:33.276284Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.19261","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:65d625448072b7f64ed48785db11e042da1a859370cbae082b3c3b68303d43c0","sha256:ed0016af6e00c640b5bdd91bda754299df84648b496f3ac08c41ebf3980af471"],"state_sha256":"0abaddcc8f6524dc403c16b21446163f23c5f6afdedf77c70b49335783034f19"}