{"as_of":"2026-08-19T02:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e72da41f2dc0949279a12b678e2a9745267d6ac1de19c60a1afbeea418d9d55e","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T17:31:15.972423Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T04:51:16.312840Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-10T04:51:16.419521Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"cited_work":{"arxiv_id":"2607.02523","doi":null,"metadata_source":"pith","pith_arxiv_id":"2607.02523","snapshot_observed_at":"2026-08-10T04:51:16.419521Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","venue":"cs.DC","work_id":"597b23a6-a6c3-4c71-a9b9-834953cea6e5","year":2026},"citing_paper":{"arxiv_id":"2608.07427","last_updated":"2026-08-07T17:14:45Z","snapshot_observed_at":"2026-08-18T01:27:54.649075Z","submitted_at":"2026-08-07T17:14:45Z","title":"A Picture is Worth a Thousand Tokens: How Vision Language Models Cut AI Energy Costs While Improving Accuracy","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T04:51:16.312840Z"},"links":{"cited_paper":"/paper/2607.02523","citing_paper":"/paper/2608.07427"},"observation_digest":"sha256:24b42d20b92fa203c685d4669d3fbb30f578832496110f4f78fe58b1c94e5977","observation_id":"23f19057-c6ed-4369-8bdb-6a68b50353a2","resolution":{"observed_at":"2026-08-10T04:51:16.426717Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2607.02523/citation-record","integrity":"/paper/2607.02523/integrity","json":"/paper/2607.02523/citation-record.json","paper":"/paper/2607.02523"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"O-RAN.WG2.AIML-v01.03: AI/ML Workflow De- scription and Requirements,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:2048598ece26931d82b4eaa673a21acf778423d6a669fe077eca6a326b9be8ac","observation_id":"67670063-65f4-4d82-88db-b7b2a73e9733","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Multi-access Edge Computing (MEC); Framework and Refer- ence Architecture,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:0210b0de3c0d39c293dd22507da21b84ebeee5fefd528781b1c344ab9ab480e5","observation_id":"b110543c-0144-46cc-8b0e-b9a6fcca1ac0","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"NVIDIA EGX Platform: Enterprise AI at the Edge,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:e5e6599befb413f98131c7c58face7388c9d00c2d8f676304b31bcd5f3924bcc","observation_id":"55acd5f7-4403-435c-a7a2-ab2bec3fa0e6","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-17T18:04:53.578114Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"LoRA: Low-Rank Adaptation of Large Language Models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:55efddc18fc58b829888b1d3c9b4c817d403cdf529d2eed953295727860ae603","observation_id":"95754c4e-46a7-4af8-9ccd-ef7e7dffbc9f","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Fine-tuning LLMs Guide,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:cc5a81da50bb1785bbd624e776d72ca60130938a9b0d71ebd63bbd969fa88aca","observation_id":"631d17d6-53c8-491c-a359-7ca6b644d92d","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Language Models are Few-Shot Learners,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:8a6e67ddd8921b270f844d7a5f96ee906fafc8081633f867beea3005ee8841a1","observation_id":"edf0b74b-8d09-45f2-80e1-b7543e86525d","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14314","last_updated":"2023-05-23T17:50:33Z","snapshot_observed_at":"2026-08-13T23:56:42.354755Z","submitted_at":"2023-05-23T17:50:33Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14314","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:89619a9f943a8e11ba46da8960174f42e81686f3aedec7e38c33acb46a1e62d5","observation_id":"98286267-7d7d-4406-8b37-ad6c97d1613e","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Mastering LLM Techniques: Inference Optimization,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:8bf9e711931f33c93f09efb80652acb18ee7536db19d97beee1f163e0f39d822","observation_id":"d430f827-c1c0-44d1-8d73-dde4919457a2","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Available: https://developer.nvidia.com/blog/mastering- llm-techniques-inference-optimization/","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:90c6d342ad1a3a0ef2f7669c361b7d8428344d2ebb43c07db88cfd1d51366eb5","observation_id":"94b11f64-5e58-4c48-82b6-623e343d0b8c","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-07-12T17:31:15.972423Z","title":"Efficient Memory Management for LLM Serving with PagedAttention,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2309.06180","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:5c476f35c893f79e59cd11cd0fa4a9aea77ce8a46857ddb98cd90e23ca770aa5","observation_id":"36bbb660-1b89-4e5e-9f91-c03772605987","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.18079","last_updated":"2025-05-28T18:58:29Z","snapshot_observed_at":"2026-08-17T08:27:45.946180Z","submitted_at":"2024-01-31T18:58:14Z","title":"KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.18079","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"KVQuant: Towards 10M Context Length LLM Inference,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2401.18079","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:4adc4e9f9f99df15c6681697e5aa56a7f45a6e05fb56013e2ea0a55cb0778ef9","observation_id":"8e5f9032-d7cd-4df2-aa58-ef1b88649739","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.09670","last_updated":"2024-06-06T15:50:51Z","snapshot_observed_at":"2026-08-16T14:26:37.115667Z","submitted_at":"2024-01-18T01:03:38Z","title":"DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.09670","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"DistServe: Disaggregating Prefill and Decoding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2401.09670","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:d830c15d61663e93925956257f2b79b585a935a7002d2062624e3ffb852a4908","observation_id":"df274166-ffec-40af-9d3d-3978699cc3a4","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.16369","last_updated":"2023-08-31T00:03:02Z","snapshot_observed_at":"2026-08-15T04:42:28.752204Z","submitted_at":"2023-08-31T00:03:02Z","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes with Chunked Prefills","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.16369","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"SARATHI: Efficient LLM Inference by Piggybacking Decodes,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2308.16369","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:e92801dcb7ea1aa92a0a00bb97ee861b75bd451c5043916210a92cccccb928b4","observation_id":"db4971cb-75b1-46cc-a5bc-9efe313ef085","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:b09030349783301428fcf792cfef84365a29f58354f61d2ba570b81391b490c1","observation_id":"62930509-3921-44f0-9454-25bfe42e389b","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"TRL:Transformer Reinforcement Learning Library,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:3653348dfb988fd939433aa57f0b41fd78b2a59da3f41b51a9a26e4d0063533d","observation_id":"09a01829-d9fa-4475-8a7a-6e582925aeae","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Chat Templates Documentation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:c7cafa67c9165d77e80c6441a3b8947eff598f45ec5f898a9e4d6a172be9bded","observation_id":"6efd6013-4262-4cd2-a0b9-5e200e7455a6","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Qwen3 Quickstart and Thinking-Mode Controls,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:fae5594df00663fcb2a45755e74e01633b38770a13194f02000139cb90f27677","observation_id":"dc08ea07-ec20-457b-9f91-983d2ba02ec9","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Multi-access Edge Computing (MEC); MEC Support for Edge AI/ML,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:7a8fbfa40834160ca33b25c91615f680ebedfcb6581e3a6de73398ef8012c343","observation_id":"867ecd30-64be-441e-969c-8f3f44ae6591","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Edge Intelligence: Paving the Last Mile of Artificial Intelligence with Edge Computing,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:59c28854f92ad5ef6fceb7207663c26b3ccf047619e38c2a9d4d5c7474e13018","observation_id":"693a0a36-42ca-423f-b1b2-72e670168412","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"A Joint Learning and Communications Framework for Federated Learning over Wireless Networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:9b683ea84f476c280fd30893dc39270d9323247687fca3bf9d0587d17b7578ff","observation_id":"0ba44355-8e18-4273-80c7-03b737616d40","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.04693","last_updated":"2024-08-08T16:26:07Z","snapshot_observed_at":"2026-08-17T12:52:16.307088Z","submitted_at":"2024-08-08T16:26:07Z","title":"Understanding the Performance and Estimating the Cost of LLM Fine-Tuning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.04693","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"Understanding the Performance and Cost of LLM Fine-Tuning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2408.04693","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:65afdb878209b05fdf336b9b7110e29a62450f340e7e004324ff67fee32c15c0","observation_id":"5d93993a-d0e3-4def-a012-db8639f7f9a5","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Why Reinforcement Learning Beats Supervised Fine-Tuning When Data Is Scarce,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:0d3b403aefd2566f11186a47628ea95b24bfbfcb0153bd717ff7bb6d69ed4cdf","observation_id":"1629d081-15cb-4a7a-86da-5806c9710f1c","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15217","last_updated":"2025-04-28T05:09:12Z","snapshot_observed_at":"2026-08-13T16:22:14.977210Z","submitted_at":"2023-09-26T19:23:54Z","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.15217","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"Ragas: Automated Evaluation of Retrieval Augmented Generation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2309.15217","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:d868217b5fe33c1e38fd4aa6e6bda272852d78834c10611c1b4cbe8b0df5ffd8","observation_id":"6bf0498e-6520-49d3-abd9-c067f7a6c6f6","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Qwen2.5: A Party of Foundation Models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:40429ad89231c9dc260c34f6b9e37d00e580ff26fe31a78d80f81c3ed682971b","observation_id":"b612a67c-0f42-4112-91f1-12a67a9ec70e","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:3052d744ee31234bff74055b698d38b55362fe7c49d41942eb6e49cd5d6c4b0e","observation_id":"bf7c4aab-c497-423b-a99f-64631944c76e","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Think Less, Label Better: Multi-Stage Domain-Grounded Synthetic Data Generation for Fine-Tuning Large Language Models in Telecom- munications,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:9a569c7b5e2de30f7196257c6bcdd9f6df2ec6745a4de42c3e3905bb08c2ac57","observation_id":"844e192b-0706-4b0a-87e8-c5a129cc353d","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-07-12T17:31:15.972423Z","title":"The LLaMA 3 herd of models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:38c6749830179f2864f1bf636a65979d93f6ee6a341f5f65b5b89002b2d826c3","observation_id":"7aaa8487-1955-403d-840d-062db1f4d2f9","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","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":"2026-07-12T17:31:15.972423Z","title":"Leveraging Multi-Agent System (MAS) and Fine-Tuned Small Lan- guage Models (SLMs) for Automated Telecom Network Troubleshoot- ing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-07-12T17:31:15.972423Z"},"links":{"citing_paper":"/paper/2607.02523"},"observation_digest":"sha256:995fb403a51a8ce5a592de30300905555e3e099835c3abd6e675eeae72a39929","observation_id":"3fe4c21e-b431-40d0-bfc1-9affe5c1c163","resolution":{"observed_at":"2026-07-12T17:31:15.972423Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.02523","last_updated":"2026-05-06T17:03:24Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-14T01:39:54.079191Z","submitted_at":"2026-05-06T17:03:24Z","title":"Edge-Deployable LLM Fine-Tuning on a Single GPU for Telecom Network Troubleshooting"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 1 inbound Pith citation observation for arXiv:2607.02523."}