{"work":{"id":"06043450-dbd9-4e7f-92b5-07811314b835","openalex_id":"https://openalex.org/W7084400772","doi":"10.48550/arxiv.2510.00636","arxiv_id":"2510.00636","raw_key":null,"title":"Expected attention: Kv cache compres- sion by estimating attention from future queries distribution.arXiv preprint arXiv:2510.00636, 2025","authors":null,"authors_text":"Alessio Devoto, Maximilian Jeblick, and Simon Jégou","year":2025,"venue":"arXiv (Cornell University)","abstract":null,"external_url":"https://arxiv.org/abs/2510.00636","cited_by_count":0,"metadata_source":"arxiv_reference","metadata_fetched_at":"2026-08-05T02:28:24.338817+00:00","pith_arxiv_id":null,"created_at":"2026-05-09T22:54:16.693955+00:00","updated_at":"2026-08-05T02:28:24.338817+00:00","title_quality_ok":true,"display_title":"Expected attention: KV cache compression by estimating attention from future queries distribution","render_title":"Expected attention: KV cache compression by estimating attention from future queries distribution"},"hub":{"state":{"work_id":"06043450-dbd9-4e7f-92b5-07811314b835","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":26,"external_cited_by_count":0,"distinct_field_count":7,"first_pith_cited_at":"2024-07-16T09:53:32+00:00","last_pith_cited_at":"2026-06-09T14:48:56+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-08-22T19:19:45.287410+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":3}],"polarity_counts":[{"context_polarity":"background","n":3}],"runs":{},"summary":{},"graph":{},"authors":[]}}