{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WY4QHQCPB6MJVRMUXF27M32NUI","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":"f10678623c92e53d952c70dedf4068715602c67982eb03ccb21f2743dfb61849","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T22:12:29Z","title_canon_sha256":"f144d6fb133a864b238c5f5c59042cae5faf0fc83186d16032dc5a3557f41d66"},"schema_version":"1.0","source":{"id":"2506.01986","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.01986","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.01986v1","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.01986","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_12","alias_value":"WY4QHQCPB6MJ","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_16","alias_value":"WY4QHQCPB6MJVRMU","created_at":"2026-07-05T11:14:30Z"},{"alias_kind":"pith_short_8","alias_value":"WY4QHQCP","created_at":"2026-07-05T11:14:30Z"}],"graph_snapshots":[{"event_id":"sha256:297fa8c55a6118a01e6649fdf8de44d06fcfb3a35ac74c9ebff4eaf40b8a74ee","target":"graph","created_at":"2026-07-05T11:14:30Z","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/2506.01986/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in speculative decoding have demonstrated considerable speedup across a wide array of large language model (LLM) tasks. Speculative decoding inherently relies on sacrificing extra memory allocations to generate several candidate tokens, of which acceptance rate drives the speedup. However, deploying speculative decoding on memory-constrained devices, such as mobile GPUs, remains as a significant challenge in real-world scenarios. In this work, we present a device-aware inference engine named SpecMemo that can smartly control memory allocations at finer levels to enable mult","authors_text":"Deming Chen, Selin Yildirim","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T22:12:29Z","title":"SpecMemo: Speculative Decoding is in Your Pocket"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.01986","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:eb9928d59bd61c02714cb862dbcc15a11316553a26558d676b1879fb97eeee62","target":"record","created_at":"2026-07-05T11:14:30Z","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":"f10678623c92e53d952c70dedf4068715602c67982eb03ccb21f2743dfb61849","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-16T22:12:29Z","title_canon_sha256":"f144d6fb133a864b238c5f5c59042cae5faf0fc83186d16032dc5a3557f41d66"},"schema_version":"1.0","source":{"id":"2506.01986","kind":"arxiv","version":1}},"canonical_sha256":"b63903c04f0f989ac594b975f66f4da2095fc0423fcb98fc47f9ec1569eeb801","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b63903c04f0f989ac594b975f66f4da2095fc0423fcb98fc47f9ec1569eeb801","first_computed_at":"2026-07-05T11:14:30.570862Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:30.570862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9C9eXdkV6KMmXgawNwggLMSb4OkXuFrIu2dFA4VP/nQarybqH/0ktSCz7nBHnqc7sNpyFBCBd8iMN11sUNMHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:30.571378Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.01986","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb9928d59bd61c02714cb862dbcc15a11316553a26558d676b1879fb97eeee62","sha256:297fa8c55a6118a01e6649fdf8de44d06fcfb3a35ac74c9ebff4eaf40b8a74ee"],"state_sha256":"c24d6d38bf5650e1f8cb62d187e7bda3bc5341da06711c66c9b9e8bd936fcaf8"}