{"as_of":"2026-08-09T15:14:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5bb1e4b711d300dfdd41d204847aad227c8eecd21ff24a42e4ab64d320127a9c","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T20:15:49.289390Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-22T13:21:35.626449Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.01380","last_updated":"2025-04-03T13:28:51Z","snapshot_observed_at":"2026-07-06T20:00:05.118831Z","submitted_at":"2024-12-02T11:07:51Z","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","version":2},"cited_work":{"arxiv_id":"2412.01380","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.01380","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Efficient llm inference using dynamic input pruning and cache-aware masking","venue":null,"work_id":"92ed369a-abc4-4297-b716-9651a81b2fda","year":null},"citing_paper":{"arxiv_id":"2505.17138","last_updated":"2026-05-18T17:05:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-05-22T06:12:42Z","title":"RAP: Runtime Adaptive Pruning for LLM Inference","version":5},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-22T13:20:41.739571Z"},"links":{"cited_paper":"/paper/2412.01380","citing_paper":"/paper/2505.17138"},"observation_digest":"sha256:a2ab1cc7c69d9bb35aa25e854b319320269b8b29746648edb4839c005e9d43c4","observation_id":"57e8b28b-7346-4cbf-9aca-f48e6a169591","resolution":{"observed_at":"2026-05-22T13:21:35.629058Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01380","last_updated":"2025-04-03T13:28:51Z","snapshot_observed_at":"2026-07-06T20:00:05.118831Z","submitted_at":"2024-12-02T11:07:51Z","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.01380","snapshot_observed_at":"2026-08-05T20:15:49.289390Z","title":"Efficient llm inference using dynamic input pruning and cache-aware masking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2508.10824","last_updated":"2025-08-16T03:17:35Z","snapshot_observed_at":"2026-08-06T02:00:57.019893Z","submitted_at":"2025-08-14T16:48:38Z","title":"Memory-Augmented Transformers: A Systematic Review from Neuroscience Principles to Enhanced Model Architectures","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-05T20:15:49.289390Z"},"links":{"cited_paper":"/paper/2412.01380","citing_paper":"/paper/2508.10824"},"observation_digest":"sha256:edddc62fb539e4462c9209e52843b94d1fa86370742b6cb59e4b510f69cad155","observation_id":"244a3fa0-3f99-483d-b108-e6139357ad16","resolution":{"observed_at":"2026-08-05T20:15:49.289390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.01380","last_updated":"2025-04-03T13:28:51Z","snapshot_observed_at":"2026-07-06T20:00:05.118831Z","submitted_at":"2024-12-02T11:07:51Z","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.01380","snapshot_observed_at":"2026-08-03T18:56:59.496372Z","title":"Efficient llm inference using dynamic input pruning and cache-aware masking","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.02924","last_updated":"2026-07-20T02:01:50Z","snapshot_observed_at":"2026-08-06T15:38:52.220151Z","submitted_at":"2025-12-02T16:45:25Z","title":"AutoNeural: Co-Designing Vision-Language Models for NPU Inference","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T18:56:59.496372Z"},"links":{"cited_paper":"/paper/2412.01380","citing_paper":"/paper/2512.02924"},"observation_digest":"sha256:ef49a3e559bda6156ef5232b831c6aaabab6de1e97574808108960608e85a8f0","observation_id":"b1490825-f9dd-4591-a84c-a20a207d8aab","resolution":{"observed_at":"2026-08-03T18:56:59.496372Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.01380/citation-record","integrity":"/paper/2412.01380/integrity","json":"/paper/2412.01380/citation-record.json","paper":"/paper/2412.01380"},"outbound":[],"paper":{"arxiv_id":"2412.01380","last_updated":"2025-04-03T13:28:51Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T20:00:05.118831Z","submitted_at":"2024-12-02T11:07:51Z","title":"Efficient LLM Inference using Dynamic Input Pruning and Cache-Aware Masking"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2412.01380."}