{"as_of":"2026-08-15T02:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8d0c299d087739d42f6077f918e9c9a8d67a3bb82035c588a5292d14cec7e4fd","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T09:23:42.381010Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+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/2607.20806/citation-record","integrity":"/paper/2607.20806/integrity","json":"/paper/2607.20806/citation-record.json","paper":"/paper/2607.20806"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T09:23:39.181072Z","title":"Energy and Policy Consid- erations for Deep Learning in NLP,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.181072Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:1fb4ad7eadd288415b1bce15f1edcd407653b5ac31b025f82a2b1cc9332044c9","observation_id":"4ce27c9c-e1c4-4b21-b3a5-9a087de10f8e","resolution":{"observed_at":"2026-08-01T09:23:39.181072Z","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":"2026-08-01T09:23:39.287348Z","title":"Green AI,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.287348Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:3ebf731f44d7a8a6c1d6bb443fecf4e62761a9b62022284617fd9c3f76db1ce4","observation_id":"9c0686ea-f937-4d41-8d77-4ff3c82a364b","resolution":{"observed_at":"2026-08-01T09:23:39.287348Z","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":"2026-08-01T09:23:39.400310Z","title":"A Comprehensive Survey on TinyML,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.400310Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:cd4a7c941b4e4075ff1d1c347a658988a18fb6657384bcc1edc2620f4691df44","observation_id":"dc799f71-5680-4df6-ab1b-411ab8169dc6","resolution":{"observed_at":"2026-08-01T09:23:39.400310Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.00088","last_updated":"2024-09-14T04:01:09Z","snapshot_observed_at":"2026-08-12T22:57:42.454673Z","submitted_at":"2024-08-26T03:33:36Z","title":"On-Device Language Models: A Comprehensive Review","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.00088","snapshot_observed_at":"2026-08-01T09:23:39.488916Z","title":"On-Device Language Models: A Comprehensive Review,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.488916Z"},"links":{"cited_paper":"/paper/2409.00088","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:fb53c2bbdcd51a276d646b79fce59b8c1f7d357953d586fe555ea4eb65557e90","observation_id":"39cf0452-bb57-4ec2-ba09-5fee27a122f2","resolution":{"observed_at":"2026-08-01T09:23:39.488916Z","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":"2026-08-01T09:23:39.593062Z","title":"Privacy issues in Large Language Models: A survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.593062Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:cb2c472d2db9fd38713e6c15240664ea63faf8e3ee1d05478071eec1e631dbe9","observation_id":"bf974530-5a73-4566-9c8d-48fa17fdffed","resolution":{"observed_at":"2026-08-01T09:23:39.593062Z","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":"2026-08-01T09:23:39.674038Z","title":"Edge Computing: Vision and Challenges,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.674038Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:46d78805bc94b273176487ed24401e39634c5dc13a201fb5cf2090c5936fb6b4","observation_id":"ecc4429a-53ca-4b8d-9c27-d7b76249b71c","resolution":{"observed_at":"2026-08-01T09:23:39.674038Z","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":"2026-08-01T09:23:39.801238Z","title":"The Emergence of Edge Computing,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.801238Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:012a6b14abb91c35191bfc57a10c69c021fddf13c4ee6cb1bb3e102cafbb2972","observation_id":"6f4278e1-418e-4cdd-9f09-208323dbb198","resolution":{"observed_at":"2026-08-01T09:23:39.801238Z","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":"2026-08-01T09:23:39.918275Z","title":"LLM.int8(): 8-bit Matrix Multiplication for Transformers at Scale,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:39.918275Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:3ab3e834e4fa44ca882ed4e029813ffbedd5719053dd9b6c63bd3ba56a3f1fb0","observation_id":"aa17519f-ea10-492d-8650-3a96aa932d1d","resolution":{"observed_at":"2026-08-01T09:23:39.918275Z","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":"2026-08-01T09:23:40.043115Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.043115Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:7898607a21b5fd88ef361f1d373489e5afe45ec3c28cf57a617026dd90a327e5","observation_id":"cfd23771-0cf9-4978-a238-069e5dbbc6c0","resolution":{"observed_at":"2026-08-01T09:23:40.043115Z","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":"2026-08-01T09:23:40.190292Z","title":"LLM-Pruner: On the Structural Pruning of Large Language Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.190292Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:7a19bdf9d793ae877488629366bb1fc144cff4ab4147bb13ab58fe7b1ff7f2f5","observation_id":"ec26b72c-c720-4360-8177-916ef54cf57f","resolution":{"observed_at":"2026-08-01T09:23:40.190292Z","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":"2026-08-01T09:23:40.310084Z","title":"A Review on Edge Large Language Models: Design, Execution, and Applications,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.310084Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:9a57c5393ab0d2746697d4f0519cc00f82eb84f0e65bf8e8e5d4b0afd1f6ac49","observation_id":"e319cc9e-99c4-4428-89e0-f03b8a7e64bf","resolution":{"observed_at":"2026-08-01T09:23:40.310084Z","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":"2026-08-01T09:23:40.394013Z","title":"1.1 Computing’s energy problem (and what we can do about it),","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.394013Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:94f55a97f3582109ed99ccff85c40489e9a18e433981576bfaa013255b689eab","observation_id":"ed8413f8-a6af-42fe-bfbd-2fab07e4a2ef","resolution":{"observed_at":"2026-08-01T09:23:40.394013Z","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":"2026-08-01T09:23:40.470986Z","title":"Energy-aware metaheuristics,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.470986Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:c4b35016a41369cd15d8d13bd8dedb2bbdbc7c4db9399f8422b4fe491fb7d96a","observation_id":"3b846143-a7ff-4e90-a942-05407142c857","resolution":{"observed_at":"2026-08-01T09:23:40.470986Z","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":"2026-08-01T09:23:40.567736Z","title":"Green optimization: Energy-aware design of metaheuristics by using machine learning surrogates to cope with real problems,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.567736Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:4bd4309f3d12adb156c6f4e0367066d0ffad3b21b89fa8672b0e5844ca330329","observation_id":"87e88f19-0df9-4367-8231-fd75ac1042e6","resolution":{"observed_at":"2026-08-01T09:23:40.567736Z","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":"2026-08-01T09:23:40.677448Z","title":"White-box execution refactoring of transformers for lower energy,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.677448Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:150785b15cc1361dc5a1dc7da1c19d86430141ebec0cef937148553239727579","observation_id":"bcd8d9bd-d44d-4ba2-a1c8-e351bb9bb5d8","resolution":{"observed_at":"2026-08-01T09:23:40.677448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-01T09:23:40.784563Z","title":"LLaMA: Open and Efficient Foundation Language Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.784563Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:0c16281018fbc3b090472899469d3c51d92be898d2db12e35e952c0669fba3b6","observation_id":"f3c94add-8ecb-4f79-8c7c-47d17a12455d","resolution":{"observed_at":"2026-08-01T09:23:40.784563Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-01T09:23:40.935045Z","title":"Mistral 7B,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.935045Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:edc079e6770e98e99a15db48785f7a0e3e7392d1a77e748eda0b402fdedd5b12","observation_id":"4a55202f-cfc4-47df-a0f2-cf8bc23fb327","resolution":{"observed_at":"2026-08-01T09:23:40.935045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.02385","last_updated":"2024-06-04T02:05:30Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-04T17:54:59Z","title":"TinyLlama: An Open-Source Small Language Model","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.02385","snapshot_observed_at":"2026-08-01T09:23:41.007689Z","title":"TinyLlama: An Open-Source Small Language Model,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.007689Z"},"links":{"cited_paper":"/paper/2401.02385","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:9320f5fd32d986943e7ec2731570790e11dc8f8bb67c78ab410f5cafb7d7d2cb","observation_id":"b07029ab-eb29-4c55-b042-cfb8b6e56b39","resolution":{"observed_at":"2026-08-01T09:23:41.007689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-01T09:23:41.114930Z","title":"Qwen2.5 Technical Report,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.114930Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:d912f370c99674b86f754e5584306a339bdf50bc91d033ccd33a9d25be13c176","observation_id":"ec215d32-32cf-4d7c-9cf4-9cfc83fe10c0","resolution":{"observed_at":"2026-08-01T09:23:41.114930Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08295","last_updated":"2024-04-16T12:52:47Z","snapshot_observed_at":"2026-08-03T03:29:01.959523Z","submitted_at":"2024-03-13T06:59:16Z","title":"Gemma: Open Models Based on Gemini Research and Technology","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08295","snapshot_observed_at":"2026-08-01T09:23:41.210439Z","title":"Gemma: Open models based on gemini research and technology,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.210439Z"},"links":{"cited_paper":"/paper/2403.08295","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:deb2263ac32bebf5d6a2144d8a71c4f68b676e133820ff9f07495827eecd4109","observation_id":"5c04f705-3ca3-4b6b-86c4-378bf932b5be","resolution":{"observed_at":"2026-08-01T09:23:41.210439Z","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":"2026-08-01T09:23:41.276892Z","title":"Phi-2: The Surprising Power of Small Language Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.276892Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:21ecd5c8301539b649f4048e117926823714c59ff297531e197390e20cb3b42c","observation_id":"8ade16ce-5e15-4ea8-91aa-245f2143dbb9","resolution":{"observed_at":"2026-08-01T09:23:41.276892Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-08-10T14:07:02.234322Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-01T09:23:41.394884Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.394884Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:f592a954c342d18fcb410031c28f7b1b6ddff3939bb10aa213edf9f8e2fc7e68","observation_id":"5b93593a-efe8-4fbc-ae49-ff9c270b4ea3","resolution":{"observed_at":"2026-08-01T09:23:41.394884Z","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":"2026-08-01T09:23:41.495973Z","title":"Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.495973Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:968f2bcc02821f5c9793c79fcd6e140b3bf33751bacdd0b06e42475b301eada0","observation_id":"73070ab2-5fbe-462f-8ec6-70533d73ed66","resolution":{"observed_at":"2026-08-01T09:23:41.495973Z","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":"2026-08-01T09:23:41.586996Z","title":"Evaluating Large Language Models Trained on Code,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.586996Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:3ec0541ba197a5c88dc508c9f8d56f5460930de3625770842b4318e7bc267651","observation_id":"414e3ec8-e1d0-41d7-b89f-9527c16db861","resolution":{"observed_at":"2026-08-01T09:23:41.586996Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-01T09:23:41.674980Z","title":"Training Verifiers to Solve Math Word Problems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.674980Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:217693eaf324c7a92c00805594fa59d84c2672ce58e62a724b60b09673972261","observation_id":"d3820b28-7d62-4573-9ab6-9e3ca640a184","resolution":{"observed_at":"2026-08-01T09:23:41.674980Z","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":"2026-08-01T09:23:41.795669Z","title":"MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.795669Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:bda5e71102aa62a3daf4c850629f1b9b4e5a9aa686993e3fad8376fbacf6503e","observation_id":"b4c2d04a-0ad0-4d22-82a3-02d81d6edef5","resolution":{"observed_at":"2026-08-01T09:23:41.795669Z","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":"2026-08-01T09:23:41.932239Z","title":"Measuring Massive Multitask Language Understanding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:41.932239Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:27680aecb007bb06d86b1117a44305a13a36538f5a1b05d2d949b28406991ab0","observation_id":"a682c2cd-1856-48ae-9ec9-28faa55e543c","resolution":{"observed_at":"2026-08-01T09:23:41.932239Z","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":"2026-08-01T09:23:42.066982Z","title":"A Survey on Edge Performance Benchmarking,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:42.066982Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:cebadff7ccbce3e044acad43cf85d2dfac37e2d5d4222a657eb62062229ae9ad","observation_id":"ba1bee03-4950-4680-a13e-8565d3becbc6","resolution":{"observed_at":"2026-08-01T09:23:42.066982Z","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":"2026-08-01T09:23:42.144508Z","title":"Intelligent Edge Computing and Machine Learning: A Survey of Optimization and Applications,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:42.144508Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:72d72e218663c426ed807a45cfecceaf0c50538158e926aae4b4f03ac9d334d6","observation_id":"5f47a7d5-3cc8-4455-8835-ea4372125a0f","resolution":{"observed_at":"2026-08-01T09:23:42.144508Z","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":"2026-08-01T09:23:42.265206Z","title":"tinybenchmarks: evaluating LLMs with fewer examples,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:42.265206Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:dcba488a4be726caaedddb04e86a1fb3d83f434602f7d5b74aaaf71db9233301","observation_id":"f616e81b-9816-454c-84fd-ad93c6503de8","resolution":{"observed_at":"2026-08-01T09:23:42.265206Z","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":"2026-08-01T09:23:42.381010Z","title":"THOP: PyTorch-OpCounter,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:42.381010Z"},"links":{"citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:5f859000c680f874c1ead745ff6487fba5f340ca02aa5116816200e53c8d5753","observation_id":"2d7bac58-3aa4-4f61-85ec-51e4cb9ab218","resolution":{"observed_at":"2026-08-01T09:23:42.381010Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.17323","last_updated":"2023-03-22T13:10:47Z","snapshot_observed_at":"2026-08-11T21:19:33.078277Z","submitted_at":"2022-10-31T13:42:40Z","title":"GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.17323","snapshot_observed_at":"2026-08-01T09:23:40.129068Z","title":"Available: https://arxiv.org/abs/2210.17323","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-01T09:23:40.129068Z"},"links":{"cited_paper":"/paper/2210.17323","citing_paper":"/paper/2607.20806"},"observation_digest":"sha256:e43062ef5d1a84e1b7928d26c05873561f22be797b454d74c88d5990fcefb7f4","observation_id":"093516f6-33f5-4f74-831d-345fc2626f43","resolution":{"observed_at":"2026-08-01T09:23:40.129068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.20806","last_updated":"2026-07-23T00:24:22Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-07T01:03:30.442425Z","submitted_at":"2026-07-23T00:24:22Z","title":"Profiling Lightweight Large Language Models"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":32},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2607.20806."}