{"as_of":"2026-08-08T10:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:df9b9d45a391230706e5f51eb6184536d5e5fc2b110779c969b45ce060536561","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T12:37:17.291925Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2607.22568/citation-record","integrity":"/paper/2607.22568/integrity","json":"/paper/2607.22568/citation-record.json","paper":"/paper/2607.22568"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.06180","last_updated":"2023-09-12T12:50:04Z","snapshot_observed_at":"2026-08-02T09:51:08.145755Z","submitted_at":"2023-09-12T12:50:04Z","title":"Efficient Memory Management for Large Language Model Serving with PagedAttention","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.06180","snapshot_observed_at":"2026-08-02T12:37:16.449904Z","title":"Yaniv Leviathan, Matan Kalman, and Yossi Matias","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.449904Z"},"links":{"cited_paper":"/paper/2309.06180","citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:341e942641ea24daf6bc96d7c9c71b4c2d0184afed2b80b5ded6d9d5eaecccd6","observation_id":"48429db2-feac-49a7-a626-ad75f9877fc7","resolution":{"observed_at":"2026-08-02T12:37:16.449904Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:37:16.580769Z","title":"InProceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 2511–2522, Singapore","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.580769Z"},"links":{"citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:2e8ff48f86d457e80deca401c3a9fe272ec3ea8d052a094be170858f3bbc4b25","observation_id":"a383f0f7-8c5a-46b9-a699-9d4fb217e1bf","resolution":{"observed_at":"2026-08-02T12:37:16.580769Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:37:16.648197Z","title":"https: //ai.meta.com/research/publications/the-l lama-3-herd-of-models/","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.648197Z"},"links":{"citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:134602bc84b4434dd6af30649c62d0ae40a6e1a9789e7c05d293bacce00e5f0d","observation_id":"ebdd4da8-e202-44f9-a867-ed678b1f55a6","resolution":{"observed_at":"2026-08-02T12:37:16.648197Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:37:16.687157Z","title":"https://github.com/mlc- ai/mlc- llm","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.687157Z"},"links":{"citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:f0ee19bc8ac49e9f866413631f58cdfc0323b1c39b05d3098efbcd88fc649b3e","observation_id":"e4096334-4b22-4090-9078-46e289559268","resolution":{"observed_at":"2026-08-02T12:37:16.687157Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:37:16.786832Z","title":"https://github.com /NVIDIA/TensorRT-LLM","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.786832Z"},"links":{"citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:74b2aaa6bba60c7654609e8a0fcfa23403fc9fc532682e4fd6f313952ca8dde9","observation_id":"956d658c-2e88-4ebf-bd9f-3ee2d8ee99a2","resolution":{"observed_at":"2026-08-02T12:37:16.786832Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:37:16.911184Z","title":"https://github.com/tatsu-lab /stanford_alpaca","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.911184Z"},"links":{"citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:6a53588176bcec1d11873db9697ebc08012bc1a8d9e1f9727854b8bc5f213676","observation_id":"4d8993ea-a3fc-4965-a412-14f8b52c6580","resolution":{"observed_at":"2026-08-02T12:37:16.911184Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T12:37:17.163584Z","title":"https://busine ss.yelp.com/data/resources/open-dataset/","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:17.163584Z"},"links":{"citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:68edd0ddabcb4f227fb29b1f8996a9e9a8e0f849dbc840a8ac209439b28f95b2","observation_id":"3a5fbe97-0626-4325-88b0-98fbd653379e","resolution":{"observed_at":"2026-08-02T12:37:17.163584Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.01910","last_updated":"2023-03-10T17:20:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-11-03T15:43:03Z","title":"Large Language Models Are Human-Level Prompt Engineers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.01910","snapshot_observed_at":"2026-08-02T12:37:17.291925Z","title":"Relevance","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:17.291925Z"},"links":{"cited_paper":"/paper/2211.01910","citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:e982be320eb00f247eec4db719df126a8f533fac718f132a5b1ba6dace3567e8","observation_id":"663dc144-b379-45bd-80b0-0467f7879f59","resolution":{"observed_at":"2026-08-02T12:37:17.291925Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2007.03051","last_updated":"2020-07-06T20:24:31Z","snapshot_observed_at":"2026-07-06T09:35:54.026093Z","submitted_at":"2020-07-06T20:24:31Z","title":"Carbontracker: Tracking and Predicting the Carbon Footprint of Training Deep Learning Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.03051","snapshot_observed_at":"2026-08-02T12:37:16.293093Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.293093Z"},"links":{"cited_paper":"/paper/2007.03051","citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:d97f346f45d16a6903cd2fba43ca822430a14c660bd08c2b122a8d14caf8c4af","observation_id":"178af1ac-c2a3-42f9-96c5-b38c5b027e9a","resolution":{"observed_at":"2026-08-02T12:37:16.293093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.11903","last_updated":"2023-01-10T23:07:57Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-01-28T02:33:07Z","title":"Chain-of-Thought Prompting Elicits Reasoning in Large Language Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.11903","snapshot_observed_at":"2026-08-02T12:37:17.042022Z","title":"Yelp, Inc","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:17.042022Z"},"links":{"cited_paper":"/paper/2201.11903","citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:82003ee1dc2e2914d900e5a9d3fed1bd2a9092c53d2bbd99b3306f67b2ab51e2","observation_id":"93af7e13-a114-4135-89cb-5923ae512070","resolution":{"observed_at":"2026-08-02T12:37:17.042022Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.12246","last_updated":"2024-07-21T08:01:00Z","snapshot_observed_at":"2026-08-06T00:07:59.786773Z","submitted_at":"2023-02-23T18:58:59Z","title":"Active Prompting with Chain-of-Thought for Large Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.12246","snapshot_observed_at":"2026-08-02T12:37:16.379427Z","title":"arXiv preprint arXiv:2302.12246","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.379427Z"},"links":{"cited_paper":"/paper/2302.12246","citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:1300302789078c0a1e36ce87a7b633b207d6fb579190bd483d6babf20e7e164b","observation_id":"fc77ecf9-1083-4ac9-aae9-c72572a57d35","resolution":{"observed_at":"2026-08-02T12:37:16.379427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14905","last_updated":"2024-06-27T03:53:46Z","snapshot_observed_at":"2026-08-07T05:13:11.135540Z","submitted_at":"2024-02-22T18:58:55Z","title":"MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14905","snapshot_observed_at":"2026-08-02T12:37:16.511857Z","title":"Yang Liu, Dan Iter, Yichong Xu, Shuohang Wang, Ruochen Xu, and Chenguang Zhu","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T12:37:16.511857Z"},"links":{"cited_paper":"/paper/2402.14905","citing_paper":"/paper/2607.22568"},"observation_digest":"sha256:647f512d478c108354edd935534c00bdebe5c88b0396b0527953942ed246fb62","observation_id":"c38036c8-6617-4fa2-abb6-0c6715b6b375","resolution":{"observed_at":"2026-08-02T12:37:16.511857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.22568","last_updated":"2026-05-31T18:29:16Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T09:50:32.922452Z","submitted_at":"2026-05-31T18:29:16Z","title":"Keyword Matters: Unveiling the Energy Sensitivity of On-Device LLM Prompting"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":12},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2607.22568."}