{"as_of":"2026-08-08T18:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7a07023b2d043a390c3994c7567d4f2beda048ef6547f0d2bd631549476c3ac7","coverage":[{"denominator":15,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":15,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T10:41:43.354834Z","state":"measured"},{"denominator":18,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":18,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-26T21:05:49.893508Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-04T00:39:16.844047Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"cited_work":{"arxiv_id":"2507.23536","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.23536","snapshot_observed_at":"2026-07-04T00:39:16.844047Z","title":"From llms to edge: Parameter-efficient fine-tuning on edge devices","venue":null,"work_id":"ff337a2c-e750-4dd3-95fa-686a53d08d41","year":2025},"citing_paper":{"arxiv_id":"2511.11362","last_updated":"2026-05-05T10:40:45Z","snapshot_observed_at":"2026-07-06T22:35:51.341917Z","submitted_at":"2025-11-14T14:46:29Z","title":"On-Device Fine-Tuning via Backprop-Free Zeroth-Order Optimization","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-17T22:03:53.594703Z"},"links":{"cited_paper":"/paper/2507.23536","citing_paper":"/paper/2511.11362"},"observation_digest":"sha256:c26b29bee7302ff3d5db4ddfb347918d8f77ff63e690acb3f69abcf06f23072a","observation_id":"80ff85b3-15bb-468c-8b58-2e7b3b881f98","resolution":{"observed_at":"2026-05-17T22:05:21.441039Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"cited_work":{"arxiv_id":"2507.23536","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.23536","snapshot_observed_at":"2026-07-04T00:39:16.844047Z","title":"From llms to edge: Parameter-efficient fine-tuning on edge devices","venue":null,"work_id":"ff337a2c-e750-4dd3-95fa-686a53d08d41","year":2025},"citing_paper":{"arxiv_id":"2604.05375","last_updated":"2026-04-07T03:21:17Z","snapshot_observed_at":"2026-07-06T22:54:08.897942Z","submitted_at":"2026-04-07T03:21:17Z","title":"DAT: Dual-Aware Adaptive Transmission for Efficient Multimodal LLM Inference in Edge-Cloud Systems","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-10T19:18:27.764572Z"},"links":{"cited_paper":"/paper/2507.23536","citing_paper":"/paper/2604.05375"},"observation_digest":"sha256:f34e160178e280f403409f657dc0b84b3b526faed134159c028de9b535d345e1","observation_id":"cf8fc0b1-fc8d-4cf8-aaa4-74f0191a37aa","resolution":{"observed_at":"2026-05-10T23:10:51.693536Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"cited_work":{"arxiv_id":"2507.23536","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.23536","snapshot_observed_at":"2026-07-04T00:39:16.844047Z","title":"From llms to edge: Parameter-efficient fine-tuning on edge devices","venue":null,"work_id":"ff337a2c-e750-4dd3-95fa-686a53d08d41","year":2025},"citing_paper":{"arxiv_id":"2606.19528","last_updated":"2026-06-17T19:20:06Z","snapshot_observed_at":"2026-08-02T10:25:23.230319Z","submitted_at":"2026-06-17T19:20:06Z","title":"Techniques for Peak Memory Reduction for LoRA Fine-tuning of LLMs on Edge Devices","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T21:05:49.893508Z"},"links":{"cited_paper":"/paper/2507.23536","citing_paper":"/paper/2606.19528"},"observation_digest":"sha256:86700de1f013fbf764e5f107700d6d5559eb77e84a3400362515f8b5c7c97b27","observation_id":"827b0643-c07b-480f-a64f-13cfdbd925af","resolution":{"observed_at":"2026-07-04T00:39:16.845468Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.23536/citation-record","integrity":"/paper/2507.23536/integrity","json":"/paper/2507.23536/citation-record.json","paper":"/paper/2507.23536"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1907.02893","last_updated":"2020-03-27T19:07:58Z","snapshot_observed_at":"2026-07-06T08:05:24.076802Z","submitted_at":"2019-07-05T15:26:26Z","title":"Invariant Risk Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.02893","snapshot_observed_at":"2026-08-06T10:41:43.297208Z","title":"Arjovsky, L","venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.297208Z"},"links":{"cited_paper":"/paper/1907.02893","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:6a83d56740617da28f6ef9195e76ac9c976df1b0e583422e0d48d089faeb5e57","observation_id":"7abae34a-8e4c-49ff-8064-91fc7aca51ea","resolution":{"observed_at":"2026-08-06T10:41:43.297208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.12261","last_updated":"2019-03-28T20:56:37Z","snapshot_observed_at":"2026-08-02T09:01:28.869881Z","submitted_at":"2019-03-28T20:56:37Z","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.12261","snapshot_observed_at":"2026-08-06T10:41:43.322565Z","title":"Hendrycks and T","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.322565Z"},"links":{"cited_paper":"/paper/1903.12261","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:c59097ea03a6ffa46576a28a1d754eaa1b57e076d9e23d40037a9cf62859b93b","observation_id":"b8b41b39-d450-4b67-a865-e89732f1ceaf","resolution":{"observed_at":"2026-08-06T10:41:43.322565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1704.04861","last_updated":"2017-04-17T03:57:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-04-17T03:57:34Z","title":"MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.04861","snapshot_observed_at":"2026-08-06T10:41:43.326513Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.326513Z"},"links":{"cited_paper":"/paper/1704.04861","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:caee175267e980ccd1291d2c8f6281917a09e6f7a5a75d24017bbf694edf9d82","observation_id":"9f1d0a16-d0d3-4413-977a-8a7d549b74cc","resolution":{"observed_at":"2026-08-06T10:41:43.326513Z","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":"2026-08-07T07:43:16.294957Z","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":"2026-08-06T10:41:43.330438Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.330438Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:1d21822568fc58e39436fe1f4f778e585b1f2e1095078f70cf446d6c94ec6f97","observation_id":"18f15ff8-016f-42e5-b7c3-fa76ba51162a","resolution":{"observed_at":"2026-08-06T10:41:43.330438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.05012","last_updated":"2024-05-12T22:21:27Z","snapshot_observed_at":"2026-07-06T18:11:30.354072Z","submitted_at":"2024-05-08T12:26:15Z","title":"The Entropy Enigma: Success and Failure of Entropy Minimization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.05012","snapshot_observed_at":"2026-08-06T10:41:43.338435Z","title":"Press, R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.338435Z"},"links":{"cited_paper":"/paper/2405.05012","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:65163742e96f7ceaa7cc39ede0aacc5c691470c979c789401baed44e8069b567","observation_id":"54666b9c-e340-41d2-a94d-1114c778b4e5","resolution":{"observed_at":"2026-08-06T10:41:43.338435Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.10726","last_updated":"2021-03-18T17:58:01Z","snapshot_observed_at":"2026-07-06T09:30:32.320227Z","submitted_at":"2020-06-18T17:55:28Z","title":"Tent: Fully Test-time Adaptation by Entropy Minimization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.10726","snapshot_observed_at":"2026-08-06T10:41:43.346975Z","title":null,"venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.346975Z"},"links":{"cited_paper":"/paper/2006.10726","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:04ee29f245806b089b6ebdf98692762efe902744a0c90c418cd81cb692b52c8c","observation_id":"79f04153-0c0f-443c-82cf-a0507b492e91","resolution":{"observed_at":"2026-08-06T10:41:43.346975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.03507","last_updated":"2024-06-02T21:24:12Z","snapshot_observed_at":"2026-07-06T17:40:15.746482Z","submitted_at":"2024-03-06T07:29:57Z","title":"GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.03507","snapshot_observed_at":"2026-08-06T10:41:43.351113Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.351113Z"},"links":{"cited_paper":"/paper/2403.03507","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:cb909efd3b0f7686f1c70d5a40ea59309ecb0ba4dcb1f89ff8485eb1b2366a7f","observation_id":"ff35c07d-38ac-4c8c-99e8-ce245fbbd1eb","resolution":{"observed_at":"2026-08-06T10:41:43.351113Z","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":"2026-08-06T10:41:43.556649Z","title":"Baseline hyperparameters for the analyzed PEFT methods, consistent with Hu et al","venue":null,"work_id":"8344c514-8ab7-4669-91f0-16ca5ac0b810","year":2021},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.354834Z"},"links":{"citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:89db06759e83fbda257251ea869f5c1f7616eea879890f621538ae2704d60dce","observation_id":"79bb51d4-fd59-413b-acf1-bddcc9cc8385","resolution":{"observed_at":"2026-08-06T10:41:43.560736Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-06T10:41:43.318235Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.318235Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:1a2fc25425923956f063dcef146cdb395a771294f05bc62868cd40cfb46a1f2f","observation_id":"453e493e-63b1-4436-b3ab-1c15f72f6670","resolution":{"observed_at":"2026-08-06T10:41:43.318235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.05721","last_updated":"2019-06-12T17:47:21Z","snapshot_observed_at":"2026-08-02T06:04:05.801557Z","submitted_at":"2019-06-12T17:47:21Z","title":"Visual Wake Words Dataset","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.05721","snapshot_observed_at":"2026-08-06T10:41:43.305839Z","title":"Chowdhery, P","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.305839Z"},"links":{"cited_paper":"/paper/1906.05721","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:62b3e185443400b7ca82b16c12c762c8847f695e13d5f174b2a20abdc71c5349","observation_id":"0f378383-931c-455b-9621-2d740a904059","resolution":{"observed_at":"2026-08-06T10:41:43.305839Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13536","last_updated":"2024-05-28T09:28:53Z","snapshot_observed_at":"2026-07-06T15:31:01.106910Z","submitted_at":"2023-05-22T23:19:45Z","title":"Subspace-Configurable Networks","version":3},"cited_work":{"arxiv_id":"2305.13536","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.13536","snapshot_observed_at":"2026-08-06T10:41:43.411762Z","title":"Subspace-Configurable Networks","venue":"cs.LG","work_id":"3f53cc46-2545-49ad-abf4-0639fc6b3a0b","year":2023},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.342681Z"},"links":{"cited_paper":"/paper/2305.13536","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:e4da1245efdc0bdc084c47ac33236eb12370becdb54b117c48d91b918e62ec04","observation_id":"024397ce-6bc8-4476-9a4b-75194ab49aaa","resolution":{"observed_at":"2026-08-06T10:41:43.416886Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.13349","last_updated":"2025-07-28T14:11:53Z","snapshot_observed_at":"2026-07-31T05:34:54.063652Z","submitted_at":"2023-11-22T12:34:51Z","title":"REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints","version":3},"cited_work":{"arxiv_id":"2311.13349","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.13349","snapshot_observed_at":"2026-08-06T10:41:43.507470Z","title":"REDS: Resource-Efficient Deep Subnetworks for Dynamic Resource Constraints","venue":"cs.LG","work_id":"d85900dd-5692-4d1b-ba02-128443e3f091","year":2023},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.310034Z"},"links":{"cited_paper":"/paper/2311.13349","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:ce0056cd185c21b104ef2fefae54cb0c0cd0564b835bec77ae154c6e04617839","observation_id":"5606ddbe-56b9-47e0-9d94-50832f18b549","resolution":{"observed_at":"2026-08-06T10:41:43.512438Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.00152","last_updated":"2021-03-21T21:48:35Z","snapshot_observed_at":"2026-07-06T09:01:07.016780Z","submitted_at":"2020-02-29T01:57:37Z","title":"Training BatchNorm and Only BatchNorm: On the Expressive Power of Random Features in CNNs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.00152","snapshot_observed_at":"2026-08-06T10:41:43.313947Z","title":"Frankle andet al","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.313947Z"},"links":{"cited_paper":"/paper/2003.00152","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:27e52e621784c8583707e44decbbd8f6637730eea8b5428f9d84e74e6c04d53c","observation_id":"803712bd-e059-4807-8bc7-ec547d522980","resolution":{"observed_at":"2026-08-06T10:41:43.313947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.06522","last_updated":"2023-08-12T10:33:57Z","snapshot_observed_at":"2026-07-06T16:05:31.757410Z","submitted_at":"2023-08-12T10:33:57Z","title":"SLoRA: Federated Parameter Efficient Fine-Tuning of Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.06522","snapshot_observed_at":"2026-08-06T10:41:43.301828Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.301828Z"},"links":{"cited_paper":"/paper/2308.06522","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:bc112ec0dcc164322d8f2417a7f02c610feb4282777856c8196876f468aa0e7e","observation_id":"80d3ebaa-e6f4-4f1d-b043-9dd20af342c9","resolution":{"observed_at":"2026-08-06T10:41:43.301828Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01650","last_updated":"2024-05-29T06:24:55Z","snapshot_observed_at":"2026-08-04T05:18:10.467283Z","submitted_at":"2024-04-02T05:34:33Z","title":"Test-Time Model Adaptation with Only Forward Passes","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01650","snapshot_observed_at":"2026-08-06T10:41:43.334161Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T10:41:43.334161Z"},"links":{"cited_paper":"/paper/2404.01650","citing_paper":"/paper/2507.23536"},"observation_digest":"sha256:7f5e5a59d1e230277d1e7580a68495c48e86fee3c92426280972ae79f4ea5f74","observation_id":"18891047-926f-49bc-9f86-8eee15e20a6e","resolution":{"observed_at":"2026-08-06T10:41:43.334161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2507.23536","last_updated":"2025-07-31T13:23:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T10:41:41.943363Z","submitted_at":"2025-07-31T13:23:21Z","title":"From LLMs to Edge: Parameter-Efficient Fine-Tuning on Edge Devices"},"reference_resolution":{"displayed":15,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":15},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 15 of 15 outbound references and 3 inbound Pith citation observations for arXiv:2507.23536."}