{"as_of":"2026-08-20T17:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9c0f71f65a30a84b4bf2ff5614e4dd596669bf037ed1f5557ea310bfad794909","coverage":[{"denominator":27,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":27,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:50:41.023247Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2505.18166/citation-record","integrity":"/paper/2505.18166/integrity","json":"/paper/2505.18166/citation-record.json","paper":"/paper/2505.18166"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:50:41.465614Z","title":"Large-scale artificial intelligence models.Computer, 55(5):76–80, May 2022","venue":null,"work_id":"71693704-b647-4446-aa31-3a33525230af","year":2022},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.879479Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:e83850ac96f594e05d7f895c98cb76e2696622060e053198e52a174976ae7ac1","observation_id":"af31ce55-65e2-443c-ae76-4c9ade11c37d","resolution":{"observed_at":"2026-08-15T21:50:41.469394Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.08727","last_updated":"2023-01-25T08:01:55Z","snapshot_observed_at":"2026-08-16T20:50:52.110799Z","submitted_at":"2023-01-20T18:47:24Z","title":"Neural Architecture Search: Insights from 1000 Papers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.08727","snapshot_observed_at":"2026-08-15T21:50:40.886372Z","title":"Neural architecture search: Insights from 1000 papers.arXiv preprint arXiv:2301.08727, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.886372Z"},"links":{"cited_paper":"/paper/2301.08727","citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:865f45c84b8141197c8ee54de38687ed8ebae8d09ffe81529a03a6ff1ba11f9e","observation_id":"b01d0492-c744-44c8-aab2-edf20b03c3ce","resolution":{"observed_at":"2026-08-15T21:50:40.886372Z","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":"2026-08-15T21:50:41.452616Z","title":"Edgeshard: Efficient llm inference via collaborative edge computing.IEEE Internet of Things Journal, pages 1–1, 2024","venue":null,"work_id":"514f1484-beba-40e9-9da7-75a4c75a572a","year":2024},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.891897Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:d6c7884e514631c048205996f9a2512c97790c0c50d9b3c0800e8efb694843eb","observation_id":"90c44106-39dd-4cae-a827-a39f1dc63d89","resolution":{"observed_at":"2026-08-15T21:50:41.457392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.15014","last_updated":"2025-01-28T20:29:44Z","snapshot_observed_at":"2026-08-15T08:26:57.013948Z","submitted_at":"2025-01-25T01:37:03Z","title":"On Accelerating Edge AI: Optimizing Resource-Constrained Environments","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.15014","snapshot_observed_at":"2026-08-15T21:50:40.897187Z","title":"On accelerating edge ai: Optimizing resource-constrained environments.arXiv preprint arXiv:2501.15014, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.897187Z"},"links":{"cited_paper":"/paper/2501.15014","citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:c68701722d60fa14fa89f8d4ef05b6cab8830b7b9a9fcdad1ebff676e6e0b7a5","observation_id":"8d2b6581-e70a-405c-8eea-6e60f48ad64f","resolution":{"observed_at":"2026-08-15T21:50:40.897187Z","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":"2026-08-15T21:50:41.435326Z","title":"Edge AI: A survey.Internet of Things and Cyber-Physical Systems, 2023","venue":null,"work_id":"92532057-b02a-4782-ad3a-9eec4a3f415a","year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.903221Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:1d05658b03c1e3d3ad5cd53f9ee402d20603d863513f2897906fb58529104e21","observation_id":"e93ba845-7a1a-4aae-9648-def7bb4a0851","resolution":{"observed_at":"2026-08-15T21:50:41.442597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:40.907709Z","title":"Distilling the knowledge in a neural network, 2015","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.907709Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:4a07831251989447939fe1d994aa2a9a42ff04ee04b3bea797f2b7b366056ffa","observation_id":"a0d5d358-f6b3-416c-822a-07fb51a544c2","resolution":{"observed_at":"2026-08-15T21:50:40.907709Z","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":"2026-08-15T21:50:41.396049Z","title":"EPSD: Early pruning with self-distillation for efficient model compression, 2024","venue":null,"work_id":"2f9d482e-e8d4-4442-8279-2c4531e29f5b","year":2024},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.913773Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:9fb962d15069da9fa31473cf72a0fbd3ca3b3608056c737b78a1e615b22c3718","observation_id":"82fd839f-e266-45c0-93ed-1e85306256d5","resolution":{"observed_at":"2026-08-15T21:50:41.401073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:41.381050Z","title":"Springer International Publishing, 2023","venue":null,"work_id":"0747cfee-50e8-4c3d-b0ec-96199f1c92a4","year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.918095Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:8734e90308072acb751ebbde8721750f46588249f46bf2b471e56a10c0716cd9","observation_id":"e74b4020-8d93-45c2-bf9d-9a66a429bfc2","resolution":{"observed_at":"2026-08-15T21:50:41.385925Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:41.367653Z","title":"Self-data distillation for recovering quality in pruned large language models, 2024","venue":null,"work_id":"82db0b4f-9654-43e2-9ff4-229c1cac4e02","year":2024},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.925165Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:9f7b8da29f12edc85519a71c8996e6b3177f6951a655cc7ff055daa132336086","observation_id":"a1a2bd59-576e-4b10-97b0-8a77fd9fd8e0","resolution":{"observed_at":"2026-08-15T21:50:41.372917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:41.353850Z","title":"Llm Pruning and Distillation in Practice: The Minitron Approach.arXiv.org, 2024","venue":null,"work_id":"d6aa1027-866b-472b-826f-987645dd3060","year":2024},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.931138Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:99b98e1d980da27d6aa89ed73f79f485736acf9bcb88461a12b4fed2d95c06d8","observation_id":"eb31a221-690e-44ba-80ad-41ae27beac54","resolution":{"observed_at":"2026-08-15T21:50:41.357881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:41.337917Z","title":"Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks.IEEE International Conference on Decision and Control (CDC), 2018","venue":null,"work_id":"b1e95d2d-ed51-460b-8436-8b1346b13608","year":2018},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.938350Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:6791983bf2bc57bbac9627d4ed9117457be163c7eb82e2523f14a7cfd717f5f1","observation_id":"5dd70124-6fa6-4c68-b42c-081b876fa145","resolution":{"observed_at":"2026-08-15T21:50:41.343025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:41.316179Z","title":"Ugur Guney, Yann Dauphin, and Leon Bottou","venue":null,"work_id":"f10fa71f-65cb-4361-9e9a-796151082ebc","year":2017},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.942768Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:a03a59f794cb0ca21f3ddaf8683b5e861b51a867c5640bcd6ca87ec097097309","observation_id":"e76b1024-06ab-4521-a256-8d35f24225eb","resolution":{"observed_at":"2026-08-15T21:50:41.323267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:40.948953Z","title":"Revisiting self-distillation, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.948953Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:3f870a1d3f4558e2b1d2c90773b750e96d62e17e29277cc6c78b2890263e8996","observation_id":"917df378-6303-4e66-8774-7db4f4592ba4","resolution":{"observed_at":"2026-08-15T21:50:40.948953Z","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":"2026-08-15T21:50:41.274005Z","title":"Random teachers are good teachers","venue":null,"work_id":"7d22c632-245c-48b8-8ed4-e185ae65651d","year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.953958Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:a7d935f97512cd552575dfabc1189e2c3bec55596da1d8f70ab6032ba6e0a452","observation_id":"1d0cd805-89b0-4eda-80f5-b2872f819299","resolution":{"observed_at":"2026-08-15T21:50:41.282302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:41.250622Z","title":"Comparing kullback-leibler divergence and mean squared error loss in knowledge distillation","venue":null,"work_id":"7e39496c-0abc-4eaf-9bbf-f9c3148ae2ca","year":2021},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.958300Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:cfacdaad7299983c04322cd8029215f800d0206b8653115e385d859c05a5e940","observation_id":"9fdb6086-16da-4701-83e0-1e4b778988de","resolution":{"observed_at":"2026-08-15T21:50:41.257362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:40.962957Z","title":"Self-distillation amplifies regularization in hilbert space","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.962957Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:05188bf23722a4104b277fabb8697e64c8ffb7a5bfef8f9027d318389ced2659","observation_id":"bcd4a412-3a5d-4c6a-94e8-6b679d90d6f1","resolution":{"observed_at":"2026-08-15T21:50:40.962957Z","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":"2026-08-15T21:50:40.967618Z","title":"Optimal brain damage.Advances in neural information processing systems, 2, 1989","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.967618Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:7814cc747245bccc66b502cee16187ffa713bcd20789b72c522a830f1b01c7d7","observation_id":"70865389-668d-43d8-ac38-8feea5345df5","resolution":{"observed_at":"2026-08-15T21:50:40.967618Z","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":"2026-08-15T21:50:41.213600Z","title":"Gomez, Łukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":"d7a92060-78be-4ffb-bf13-aa6d939ecf67","year":2017},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.971451Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:6c32921f8e122e383bbe8442dbd081310007e4cdfe12b5c704b3461efb705052","observation_id":"ddb9e323-27b1-4165-9e79-53f46ef09d02","resolution":{"observed_at":"2026-08-15T21:50:41.217885Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-15T21:50:40.975500Z","title":"Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, et al","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.975500Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:5de844a8baf292762a459f1fdcac7524f5070b986bd8657cc042309cd72d1fc0","observation_id":"10b69f36-6d4e-435f-9f38-f01ba78bbf92","resolution":{"observed_at":"2026-08-15T21:50:40.975500Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-15T21:50:40.980875Z","title":"Gpt-4 technical report.arXiv preprint arXiv:2303.08774, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.980875Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:2f4d15dd3365474d4af263b5ac4af2d0ac975d72e5b4a3cb630c7b3ae200e12f","observation_id":"af58ced1-7aa3-4c0c-accd-247287b2cbec","resolution":{"observed_at":"2026-08-15T21:50:40.980875Z","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":"2026-08-15T21:50:40.984990Z","title":"Llama: Open and efficient foundation language models.arXiv preprint arXiv:2302.13971, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.984990Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:1c738ba3bab3e4f700b59d0a49cf4f7a9b47f5d3af7f3f3d7eb7f75f514b293a","observation_id":"af5f7739-5968-4166-8e44-1e5f6790566c","resolution":{"observed_at":"2026-08-15T21:50:40.984990Z","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":"2026-08-15T21:50:40.989135Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.989135Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:e9d753c1e6fa0d9695bfb98bbb4b12bfdff5c38bf23bcde1f2e786089bb01fc0","observation_id":"827f0b82-ae47-4829-887d-17b4c810c1c4","resolution":{"observed_at":"2026-08-15T21:50:40.989135Z","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":"2026-08-15T21:50:40.993090Z","title":"CommonsenseQA: A question answering challenge targeting commonsense knowledge","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.993090Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:e9254654d7f43e598b8fd855205f29008311f988446deccd72c3bf5bddbab8a7","observation_id":"39c2ffe3-554f-4ddb-9272-64d294fea444","resolution":{"observed_at":"2026-08-15T21:50:40.993090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-15T21:50:40.998467Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:40.998467Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:6fd123e8e09b21e77dd41847fe3923c32d2cf50703a486e199a95bd983baeb67","observation_id":"6a5aed0d-4a02-4845-8b54-8cce62b05d78","resolution":{"observed_at":"2026-08-15T21:50:40.998467Z","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":"2026-08-15T21:50:41.177169Z","title":"ptflops: a flops counting tool for neural networks in pytorch framework, 2024","venue":null,"work_id":"7209ec1a-4d24-4d20-abd9-28c87743c6e6","year":2024},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:41.004625Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:f056e4568ce3d698392f015274ce0a0b742258b524398c10c780919a7aad3c56","observation_id":"8dd1354b-bb01-47d3-8daf-30f5b0f610c2","resolution":{"observed_at":"2026-08-15T21:50:41.181569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00774","last_updated":"2023-03-22T12:33:46Z","snapshot_observed_at":"2026-08-19T20:16:07.393402Z","submitted_at":"2023-01-02T17:48:56Z","title":"SparseGPT: Massive Language Models Can Be Accurately Pruned in One-Shot","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00774","snapshot_observed_at":"2026-08-15T21:50:41.013629Z","title":"Sparsegpt: Massive language models can be accurately pruned in one-shot","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:41.013629Z"},"links":{"cited_paper":"/paper/2301.00774","citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:395b10f73526e129bab8b4eb299402678bf50fdba0a5ca5d09772a254cc1695f","observation_id":"b42d6c7f-ef15-4667-8160-2b9e57a8bb29","resolution":{"observed_at":"2026-08-15T21:50:41.013629Z","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":"2026-08-15T21:50:41.161602Z","title":"A survey on uncertainty quantification methods for deep learning, 2025","venue":null,"work_id":"1c6d6e17-492e-4161-b882-c8e68b16ebdc","year":2025},"citing_paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T21:50:41.023247Z"},"links":{"citing_paper":"/paper/2505.18166"},"observation_digest":"sha256:026abd09af81ac2262335fce69d503480909e4b171dcf0937da6010e8017df8b","observation_id":"e8539ca2-cc99-46c4-820b-64b19e1d00ca","resolution":{"observed_at":"2026-08-15T21:50:41.168587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.18166","last_updated":"2025-05-13T19:06:32Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T08:52:02.075557Z","submitted_at":"2025-05-13T19:06:32Z","title":"Constrained Edge AI Deployment: Fine-Tuning vs Distillation for LLM Compression"},"reference_resolution":{"displayed":27,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":0,"verified_fuzzy":14},"total_outbound_references":27},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 27 of 27 outbound references and 0 inbound Pith citation observations for arXiv:2505.18166."}