{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NIBS3E7F4CT4724FDR2733K4W4","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":"4d5acbab0758b886684fa5a5270509be78fbc7cf342dc914019920efdc34d165","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:59:28Z","title_canon_sha256":"864e4b16d410a3b306704dfaa93071d3a0a60ae2538ad409a3276f7baca57088"},"schema_version":"1.0","source":{"id":"2402.16844","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.16844","created_at":"2026-07-05T08:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2402.16844v3","created_at":"2026-07-05T08:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16844","created_at":"2026-07-05T08:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"NIBS3E7F4CT4","created_at":"2026-07-05T08:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"NIBS3E7F4CT4724F","created_at":"2026-07-05T08:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"NIBS3E7F","created_at":"2026-07-05T08:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:ccff59eff5f2339a1d512e46da4def3571dd9157ee5c724f464db1962bbefcee","target":"graph","created_at":"2026-07-05T08:44:51Z","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/2402.16844/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have become ubiquitous in practice and are widely used for generation tasks such as translation, summarization and instruction following. However, their enormous size and reliance on autoregressive decoding increase deployment costs and complicate their use in latency-critical applications. In this work, we propose a hybrid approach that combines language models of different sizes to increase the efficiency of autoregressive decoding while maintaining high performance. Our method utilizes a pretrained frozen LLM that encodes all prompt tokens once in parallel, and ","authors_text":"Amelie Royer, Andrii Skliar, Babak Ehteshami Bejnordi, Benjamin Bergner, Tijmen Blankevoort, Yuki Asano","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:59:28Z","title":"Think Big, Generate Quick: LLM-to-SLM for Fast Autoregressive Decoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16844","kind":"arxiv","version":3},"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:ac87ef37a9f019eb2898346398ae4fd0d211bf554c2d94ef9510d562fe808718","target":"record","created_at":"2026-07-05T08:44:51Z","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":"4d5acbab0758b886684fa5a5270509be78fbc7cf342dc914019920efdc34d165","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-26T18:59:28Z","title_canon_sha256":"864e4b16d410a3b306704dfaa93071d3a0a60ae2538ad409a3276f7baca57088"},"schema_version":"1.0","source":{"id":"2402.16844","kind":"arxiv","version":3}},"canonical_sha256":"6a032d93e5e0a7cfeb851c75fded5cb70c5829b3ee46eec21bfaaac9c49e65cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a032d93e5e0a7cfeb851c75fded5cb70c5829b3ee46eec21bfaaac9c49e65cb","first_computed_at":"2026-07-05T08:44:51.369624Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:44:51.369624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5JNdBGuDftak4Ly1lZbJembyUh9LrjvL6uatwWK8Jqq300r9UJrXTHZxeGxC2d5lKIs0j4tYAqMr5eJ+EiqXAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:44:51.370155Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.16844","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac87ef37a9f019eb2898346398ae4fd0d211bf554c2d94ef9510d562fe808718","sha256:ccff59eff5f2339a1d512e46da4def3571dd9157ee5c724f464db1962bbefcee"],"state_sha256":"9d33b731ad094021c888fe9415d9767dccb3336ebbf4abee98ad00ce87edabff"}