{"as_of":"2026-08-21T07:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c88c46c883f8dad9e6518f136aed6137163a0b02e48e53c1440cde17563af37e","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T22:32:20.824316Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.03621/citation-record","integrity":"/paper/2412.03621/integrity","json":"/paper/2412.03621/citation-record.json","paper":"/paper/2412.03621"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.092195Z","title":"JPPO: Joint power and prompt optimization for accelerated large language model services,","venue":null,"work_id":"3f07486b-3ed3-400e-9022-70088feea50b","year":2025},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.734050Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:4d2e155106afb237d73b1deea6e17de445fc36967b3d68a85b51c81dee13a20f","observation_id":"b04d268d-0a8c-4ba5-9ca3-7ff036145108","resolution":{"observed_at":"2026-08-11T22:32:21.094944Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.084275Z","title":"Large language models (LLMs) inference offloading and resource allocation in cloud-edge computing: An active inference approach,","venue":null,"work_id":"e082f1d7-cf30-487e-8a84-4e904bfa473c","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.737639Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:55e6000476e1650fa15947d097bda3c6ef8f2b37f42cc105ba1434eced260d19","observation_id":"eb40f94d-e554-4ac1-9270-e9b4414665c4","resolution":{"observed_at":"2026-08-11T22:32:21.087491Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.740124Z","title":"A survey on large language models for communication, network, and service management: Application insights, challenges, and future directions,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.740124Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:78f9288ecdb179a0f7ba7442a5556346055cfa0c6eb7c0c5d9cd2c50c2dda119","observation_id":"5a6e0143-94ba-4eb2-ad2c-b6707ab0a9ff","resolution":{"observed_at":"2026-08-11T22:32:20.740124Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.073309Z","title":"EdgeMoE: Empowering sparse large language models on mobile devices,","venue":null,"work_id":"09a54d5d-7333-4323-8b12-f0860d61032e","year":2025},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.742989Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:fd97e553aa60c149ee28f7b4b9ed0f0a835ade6d4501fe2d858ffbfd0725e1d6","observation_id":"3839ae91-21b5-4a19-a885-7d68dcff2690","resolution":{"observed_at":"2026-08-11T22:32:21.076096Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.745618Z","title":"Mobile edge intelligence for large language models: A contemporary survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.745618Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:90525760d93dcf88d29aa40ad1492d294e107b854ae5270f8066b3ec61e49ef6","observation_id":"81520502-beae-4e73-a125-b79cadc01f66","resolution":{"observed_at":"2026-08-11T22:32:20.745618Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.062214Z","title":"Indus- trial internet of things with large language models (LLMs): an intelligence-based reinforcement learning approach,","venue":null,"work_id":"9174023c-926a-43d5-98ca-7c22920fcf29","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.748275Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:47f6379d7ccc19bf047bdfbbce6919a2a029e9ab3cf180c2a7c31016623f1824","observation_id":"9b899b35-c79f-4185-aec4-1605b0c4664a","resolution":{"observed_at":"2026-08-11T22:32:21.065017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.055001Z","title":"LLM-based edge intelligence: A com- prehensive survey on architectures, applications, security and trustworthiness,","venue":null,"work_id":"c8bf44f0-562b-4300-b5cd-eab4f53fad7f","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.751010Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:a40cd92af66321c85f4f9f80e5d6e27f81a4960d3037e2a598fbbf68db1219e4","observation_id":"bbb71eb0-f25c-4bf5-a2a1-90f400ece007","resolution":{"observed_at":"2026-08-11T22:32:21.057816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.047598Z","title":"Recent advances in natural language processing via large pre-trained language models: A survey,","venue":null,"work_id":"ef1144cd-625c-40ea-a15c-2542e3aee080","year":2023},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.753485Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:8ed0713d32166d5b4e06f2c46e7eeb1dd511d3356e4ac35bcd36dd4cc379bdb5","observation_id":"436f2d5f-6787-40a5-b359-720ad60aa271","resolution":{"observed_at":"2026-08-11T22:32:21.050440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.040481Z","title":"Large language model enhanced multi-agent systems for 6G communications,","venue":null,"work_id":"cb3b5dbc-bbda-441f-bda2-5ad51a7b95ae","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.755926Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:8f4c0ef4347e69423a7d7fa03a3f5cf602530ffaa5273327e095a6a7ea80bf0c","observation_id":"73c123b9-5f1a-46e3-b1bd-d17d191a120c","resolution":{"observed_at":"2026-08-11T22:32:21.043188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.033166Z","title":"A review of current trends, techniques, and challenges in large language models (LLMs),","venue":null,"work_id":"9c8d9f50-9796-430f-9a81-f1a64d2a5c9d","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.758370Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:db5ffe7496c8ad686e8095f09b9c82777fce8eca66b24b4acff1333ca7c18709","observation_id":"246639d3-823c-4c67-99a6-fe4e5d3c6769","resolution":{"observed_at":"2026-08-11T22:32:21.036120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.025538Z","title":"What makes for good tokenizers in vision transformer?","venue":null,"work_id":"a73dc1a6-e8fb-4d87-aaa7-1032662ee3ba","year":2023},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.760743Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:1da26c707ee6f3c2ada11e9b596eb4ab97a8f72e75c68100aa6e4370b4a35b3d","observation_id":"86bcfbbb-c603-446a-a08d-f0bd87b8ec7c","resolution":{"observed_at":"2026-08-11T22:32:21.028372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.02060","last_updated":"2024-06-12T02:46:16Z","snapshot_observed_at":"2026-08-18T10:06:55.154937Z","submitted_at":"2024-04-02T15:59:11Z","title":"Long-context LLMs Struggle with Long In-context Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.02060","snapshot_observed_at":"2026-08-11T22:32:20.763197Z","title":"Long-context LLMs struggle with long in-context learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.763197Z"},"links":{"cited_paper":"/paper/2404.02060","citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:174ca0befcb630ae1d6f1052253f755d4e49cb5f6d6764249c45b207f640643f","observation_id":"06bfaab0-543a-49d1-a055-663c3d5339b4","resolution":{"observed_at":"2026-08-11T22:32:20.763197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.017932Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":"97a5727f-37c9-4cfc-8df2-9750987547a7","year":2022},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.766463Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:b0a5b5e650d54e343e85efc61da2f162c127311c2a5bee06f4e67858aa0b00f6","observation_id":"797619b7-34b8-4c6a-a35e-2be1b8a86acd","resolution":{"observed_at":"2026-08-11T22:32:21.020769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.010569Z","title":"Efficient prompting for LLM-based generative internet of things,","venue":null,"work_id":"bbb90d13-03ed-48cd-a4d9-3965d68a03e1","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.768799Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:2dbf38e80d31e85efcc63d05b278c176cec2973dd5f7aeb123a1912e5725502c","observation_id":"83cc6ca7-016f-4d90-a645-a1dd1d9af0b0","resolution":{"observed_at":"2026-08-11T22:32:21.013429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:21.003181Z","title":"To repeat or not to repeat: Insights from scaling LLM under token-crisis,","venue":null,"work_id":"ed765576-1e6d-43e6-99ee-d1a4702c3a3a","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.771089Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:661df216f9f086ca6b66bc9b97683be318c55c25032ae84d0602f00ad94f84fe","observation_id":"b607f92f-b588-4621-b494-95256dc716ba","resolution":{"observed_at":"2026-08-11T22:32:21.005920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05736","last_updated":"2023-12-06T17:02:25Z","snapshot_observed_at":"2026-08-16T14:53:48.767514Z","submitted_at":"2023-10-09T14:10:21Z","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05736","snapshot_observed_at":"2026-08-11T22:32:20.773340Z","title":"LLMLingua: Compressing prompts for accelerated inference of large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.773340Z"},"links":{"cited_paper":"/paper/2310.05736","citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:a1e9d98bf09954cef08c701a08b74b7f0053dbfe0bb32122cec28532772cbf35","observation_id":"451bc9a2-8be9-46c1-a39b-5fa59b2ba18a","resolution":{"observed_at":"2026-08-11T22:32:20.773340Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.995966Z","title":"LLM-Slice: Dedicated wireless network slicing for large language models,","venue":null,"work_id":"a5f9cd3e-78ba-461d-9afc-e93052035bb0","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.776181Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:334f1439bfc967d6f8d9820592888bec0e21a77a2c05b9402a92e6c6116b9117","observation_id":"fafd3145-8a47-4bef-9cbd-59044a61e353","resolution":{"observed_at":"2026-08-11T22:32:20.998732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.988133Z","title":"Deeploy: Enabling energy- efficient deployment of small language models on heterogeneous microcontrollers,","venue":null,"work_id":"14c26206-d738-4bc8-84ae-022b6064b1d2","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.778498Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:817d95115de53071d61b4145afc9e591559b99311e6e2e8bc3d0ab33b9ee1128","observation_id":"6b7f6183-aba2-480d-b7c2-095711299a20","resolution":{"observed_at":"2026-08-11T22:32:20.991152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.780844Z","title":"Denoising diffusion probabilistic models,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.780844Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:9aa64190709282ef915f4887623c4e9b29b69a5797c354496df1d99a9c77c05d","observation_id":"cc66ff15-b223-474b-a00e-4b925acc2d6b","resolution":{"observed_at":"2026-08-11T22:32:20.780844Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.977424Z","title":"Wire- lessLLM: Empowering large language models towards wireless intelligence,","venue":null,"work_id":"522d967e-89e7-4d59-8b6b-5024c255ba94","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.783259Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:b8595d94d52c34cea5bccde11ec5e681812c0c2d1c404008e3d40639568ce0df","observation_id":"600a4bff-5760-421a-a73b-db7d1546154c","resolution":{"observed_at":"2026-08-11T22:32:20.980116Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.970422Z","title":"Edge intelligence optimization for large language model inference with batching and quantization,","venue":null,"work_id":"4511b408-3cab-40c5-8ba2-e2713d4fa21d","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.785712Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:9eb3afc489bebd67748e27a56c716b8cf984a9fac166e236482a682c84d33cc7","observation_id":"8bde7fc6-a6b7-4bd5-9a4d-6c2039919702","resolution":{"observed_at":"2026-08-11T22:32:20.973215Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.963422Z","title":"Beyond the cloud: Edge inference for generative large language models in wireless networks,","venue":null,"work_id":"8fb4b7bf-d30b-4e62-8078-40193512ac05","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.788284Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:0e94e0128c8073bca3117428de9feec6683697f1c12a88d3d8c481a0191fc882","observation_id":"b8fd5ac5-6949-45e0-b850-6e35b0082e44","resolution":{"observed_at":"2026-08-11T22:32:20.966218Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.956230Z","title":"Large multi-modal models (LMMs) as universal foundation models for AI-native wireless systems,","venue":null,"work_id":"f338899a-07bd-4206-b1dd-5b770138bb5a","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.790597Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:c22ed15f2bc3f94746d90c94ed068c9c1a33fe11fd84e6b576cdcdcef42a987f","observation_id":"ae538a7e-3057-45c5-9635-9e35d3385e52","resolution":{"observed_at":"2026-08-11T22:32:20.959075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.949061Z","title":"Adapting LLMs for efficient context processing through soft prompt compression,","venue":null,"work_id":"3e18b897-f73c-4fd8-9ccd-2a94a623666f","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.792957Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:fd0341aa3bcd63048bb27b868838b1a78c607d26da88f3dc0ce025fda1c96334","observation_id":"bb17ef0f-8616-4b15-97ab-5f7c949948cf","resolution":{"observed_at":"2026-08-11T22:32:20.951744Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.941907Z","title":"Prompt-assisted semantic interference cancelation on moderate interference chan- nels,","venue":null,"work_id":"6ff31d16-3f1f-4c8c-8d35-6209d0de66a8","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.795257Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:0dac6111710ea4aa4fd14d25ecb222f2765cc014eb5f102978af413c9c9ed18c","observation_id":"7643b011-894b-4752-942e-37bce2cb04df","resolution":{"observed_at":"2026-08-11T22:32:20.944681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.934631Z","title":"Cross modal compression with variable rate prompt,","venue":null,"work_id":"467596c7-71c5-462d-adf9-9455eab52ea8","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.797785Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:c280f9231b89814e094cd59e77cc6db5b11b555d850d943e82af3b66b7237178","observation_id":"4cc9a607-1c5a-427e-abd3-af2a0bdfbad4","resolution":{"observed_at":"2026-08-11T22:32:20.937469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.927072Z","title":"Discrete prompt compression with rein- forcement learning,","venue":null,"work_id":"b63b346a-8c99-4330-ac12-3790dd182b46","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.800209Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:0a13c1fc9787620b47b04fd822d06f3f412c385193cf3eccd1d6ca512eb1834c","observation_id":"67448533-5779-412e-aeeb-199d1076b55c","resolution":{"observed_at":"2026-08-11T22:32:20.929942Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.919256Z","title":"Intelligent cloud-edge collaborations for energy-efficient user association and power allocation in space-air-ground integrated networks,","venue":null,"work_id":"79f14249-75cf-46b1-92e0-c613eada7d20","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.802518Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:112028f66b6e399b93aad315837e38f24162681f79bc9e59ba52d4b187a132fa","observation_id":"5b5500a8-70de-4193-88e0-fda914260452","resolution":{"observed_at":"2026-08-11T22:32:20.922172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.911517Z","title":"Joint resource allocations for energy consumption optimization in HAPS-aided MEC-NOMA systems,","venue":null,"work_id":"853cf56d-bc8e-454b-a2d7-46fb0527093f","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.805005Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:41736ccaf69bcd2ea611075e8c4f26b609c9597c8360436a3a4a47904eec3b20","observation_id":"d8ecf47e-f24e-4070-b9ac-7e7c1d5cbb53","resolution":{"observed_at":"2026-08-11T22:32:20.914369Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.903694Z","title":"Graph neural networks approach for joint wireless power control and spectrum allocation,","venue":null,"work_id":"dee951df-d3a7-4b2d-bfe6-49015c29e106","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.807289Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:9bd398672258807c09ce4719668327edaf85ee2fe26f2d43130f833328b326b3","observation_id":"6d6ae3d9-edc9-42dc-8a1e-ff16b51cdb74","resolution":{"observed_at":"2026-08-11T22:32:20.906617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.895355Z","title":"LLMCarbon: Modeling the end-to-end carbon footprint of large language models,","venue":null,"work_id":"30c7216b-5c7d-409a-9d51-cda5c6f6c618","year":2024},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.809750Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:a6dc82050e68461dc9be901340d3fb925d29456c49c2bfd764f8f30fc8446d4f","observation_id":"4b9f70a3-2eb5-4f73-9b6c-279a70d3c600","resolution":{"observed_at":"2026-08-11T22:32:20.898733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.887834Z","title":"Tse and P","venue":null,"work_id":"65f1cb54-3cdd-41d5-90c1-f594a48ea9d9","year":2005},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.812250Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:ae4db55356603a5584038fc774acde1d6cee26062b28c11b3d752e00bb990288","observation_id":"61a1fba7-34b7-4e4c-82be-f4ae2d44ff3f","resolution":{"observed_at":"2026-08-11T22:32:20.890611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.814634Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.814634Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:e70936806218ff245b0f6b5d9f4afbb7145952814fd92e503dfa561398738646","observation_id":"2d425dfb-d471-48eb-81fe-d13b98c811a8","resolution":{"observed_at":"2026-08-11T22:32:20.814634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.876509Z","title":"Deep reinforcement learn- ing with double q-learning,","venue":null,"work_id":"a0399a20-3958-4049-ba67-2353312541d9","year":2016},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.817107Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:629bab93bbc36efa183351275087e2527e7c9402015a3605f48fabead828ca07","observation_id":"9ed71506-8d56-4178-bb84-029ae9713d5c","resolution":{"observed_at":"2026-08-11T22:32:20.879283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.869126Z","title":null,"venue":null,"work_id":"aa801edd-3612-46e3-a2dd-9ce3d73e9ec5","year":2022},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.819449Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:1c391dff63b2d35750f3645ed9866cb4da193dac846f7890ef00860d60a7a100","observation_id":"6b5707ee-d05b-44d6-9a79-cb6a283ed499","resolution":{"observed_at":"2026-08-11T22:32:20.871804Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T22:32:20.859736Z","title":"Meetingbank: A benchmark dataset for meeting summarization,","venue":null,"work_id":"33d78b88-6e07-4cbb-90a4-d96249d85525","year":2023},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.821792Z"},"links":{"citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:513a9a89368183f2fad00fc4ac038528d0ad42e9637458ab4dab9f260b27aef2","observation_id":"39c02c51-2435-478e-850f-638579cbe7ad","resolution":{"observed_at":"2026-08-11T22:32:20.864182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.14508","last_updated":"2024-06-19T04:00:32Z","snapshot_observed_at":"2026-08-08T03:49:18.086396Z","submitted_at":"2023-08-28T11:53:40Z","title":"LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.14508","snapshot_observed_at":"2026-08-11T22:32:20.824316Z","title":"Longbench: A bilingual, multi- task benchmark for long context understanding,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-11T22:32:20.824316Z"},"links":{"cited_paper":"/paper/2308.14508","citing_paper":"/paper/2412.03621"},"observation_digest":"sha256:8e956a023701f81c96de744686b3b6f61df832db469b1c15aaee5f0a80d4712d","observation_id":"5cb6d87a-a4b1-496d-8204-f2f8ae8171d8","resolution":{"observed_at":"2026-08-11T22:32:20.824316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.03621","last_updated":"2025-05-30T15:19:44Z","latest_version":4,"primary_category":"cs.NI","snapshot_observed_at":"2026-08-14T08:27:16.891751Z","submitted_at":"2024-12-04T15:26:10Z","title":"JPPO++: Joint Power and Denoising-inspired Prompt Optimization for Mobile LLM Services"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":29},"total_outbound_references":37},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2412.03621."}