{"as_of":"2026-08-13T01:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:699f793696ed3fe3c83a3108a31d28a0c7be90b1ea36f0228c3b087b87b544ab","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T18:15:09.084823Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.17371/citation-record","integrity":"/paper/2607.17371/integrity","json":"/paper/2607.17371/citation-record.json","paper":"/paper/2607.17371"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T18:15:03.535634Z","title":"A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:03.535634Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:6dbacc1e5895a5b2812eabc8db4f8cfe14ee04fb5185a1bd002d571284d4ef91","observation_id":"7a6fd6a8-8ae0-44f3-a810-2f9786bdb8e0","resolution":{"observed_at":"2026-08-01T18:15:03.535634Z","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":"2026-08-01T18:15:03.628144Z","title":"Review of deep learning: concepts, CNN architectures, challenges, applications, future directions,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:03.628144Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:8276037541a5e36c9988b1ba222250eef2a7a74da912eda798adde5db450d32e","observation_id":"83d6e03a-6c14-437e-9038-e87a33029977","resolution":{"observed_at":"2026-08-01T18:15:03.628144Z","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":"2026-08-01T18:15:03.742579Z","title":"Are vision transformers more data hungry than newborn visual systems?,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:03.742579Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:39a5f82447877e2f0d6a0746c0787c5cbbeb0bfee7f2756776ecdd767bd7eeb7","observation_id":"177f2b18-9667-43cf-adf7-7f19de3091ba","resolution":{"observed_at":"2026-08-01T18:15:03.742579Z","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":"2026-08-01T18:15:03.865451Z","title":"Edge Intelligence: Empowering Intelligence to the Edge of Network,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:03.865451Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:2bf8dcfecabfd972321fc8b54ee1e65f3b5082b6c8c1cc46216dd651434ba43b","observation_id":"d272821d-555a-45e4-96fe-9a70d61d5799","resolution":{"observed_at":"2026-08-01T18:15:03.865451Z","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":"2026-08-01T18:15:03.988409Z","title":"Parameter-efficient fine-tuning of large-scale pre-trained language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:03.988409Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:c0d4bd9c557e16dfea66dbb538fbee12e364fb7cfe801cc1d5d2cbf6f9a6c5bf","observation_id":"7ce49a4f-fff6-4301-b4df-aa130220d4de","resolution":{"observed_at":"2026-08-01T18:15:03.988409Z","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":"2026-08-01T18:15:04.113587Z","title":"Survey: federated learning data security and privacy-preserving in edge-Internet of Things,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.113587Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:ec651daf641809d99c793a13b4ac0b76634f13cc12d7b811b6cc01525b02f38d","observation_id":"523706dc-219a-4541-afca-0bf69c9882e1","resolution":{"observed_at":"2026-08-01T18:15:04.113587Z","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":"2026-08-01T18:15:04.271600Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.271600Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:12ab57a688355ab9ecd592cff97c38520a15b20f81c2f34e4c990a372971c0be","observation_id":"07d6ef90-a12e-412e-823a-c9f4993b1aab","resolution":{"observed_at":"2026-08-01T18:15:04.271600Z","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":"2026-08-01T18:15:04.396867Z","title":"A Comprehensive Survey of Continual Learning: Theory, Method and Application,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.396867Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:536489692a8ece14efe80ba76ed0798c77e3a7558a36cae2369a43dc1db04ca2","observation_id":"c3057731-2719-4c2b-a8eb-ebe66214c4b0","resolution":{"observed_at":"2026-08-01T18:15:04.396867Z","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":"2026-08-01T18:15:04.503905Z","title":"PANTHER: A Programmable Architecture for Neural Network Training Harnessing Energy -Efficient ReRAM,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.503905Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:55b6ab3f281be7eaa023321a7f83683a2ed170c0de04a2a4c1bac6fec4640909","observation_id":"cda7ccbd-d6f3-44ba-9be9-54043dd54f38","resolution":{"observed_at":"2026-08-01T18:15:04.503905Z","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":"2026-08-01T18:15:04.586550Z","title":"Compute -in-Memory Chips for Deep Learning: Recent Trends and Prospects,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.586550Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:bdb81f9943410f1c04287230a60b1a76b75d1789b1c2cf4111f862236ef26bb3","observation_id":"7a073ddf-fe86-4a53-ad81-fb640e32b39a","resolution":{"observed_at":"2026-08-01T18:15:04.586550Z","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":"2026-08-01T18:15:04.645268Z","title":"Architectures and Circuits for Analog -memory-based Hardware Accelerators for Deep Neural Networks (Invited),","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.645268Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:78256c0c06d647f32d9a39aa882cd6625311ae34fa768a6f0dad704bb884cdec","observation_id":"fec27c97-60e2-4c03-bc9e-bae4912efd16","resolution":{"observed_at":"2026-08-01T18:15:04.645268Z","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":"2026-08-01T18:15:04.651421Z","title":"MobileNetV2: Inverted Residuals and Linear Bottlenecks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.651421Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:91b56b0ed8f5197ee360035f31346367779938729c0a2f0a8e63be402b11c515","observation_id":"2751ab52-92c0-434f-9f2d-4877d756a2d9","resolution":{"observed_at":"2026-08-01T18:15:04.651421Z","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":"2026-08-01T18:15:04.737523Z","title":"DNN+NeuroSim V2.0: An End -to-End Benchmarking Framework for Compute -in-Memory Accelerators for On -Chip Training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.737523Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:6feab26db3b26b00ac0a8bc194bb6b6141f65e25f09bc34cd7c72de8ad7655ea","observation_id":"069d05f7-8794-46a1-9b62-1fa16837bfc7","resolution":{"observed_at":"2026-08-01T18:15:04.737523Z","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":"2026-08-01T18:15:04.839853Z","title":"Efficient On -Device Training via Gradient Filtering,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:04.839853Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:158156af531939c091c73c92a51cbb951195254d29b216dd044002e89071a6d4","observation_id":"48f7d714-6f90-4d8e-ba2e-9515b78a9bfe","resolution":{"observed_at":"2026-08-01T18:15:04.839853Z","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":"2026-08-01T18:15:05.006899Z","title":"Universal language model fine -tuning for text classification,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.006899Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:de967e75d7cc30ddc47e62a58d4ded465bec37971b670ed989bb44e0933f382b","observation_id":"5449bf73-7d18-45cd-8907-3fdd799bdf0f","resolution":{"observed_at":"2026-08-01T18:15:05.006899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1910.01769","last_updated":"2020-07-23T01:44:14Z","snapshot_observed_at":"2026-07-06T08:26:50.559259Z","submitted_at":"2019-10-04T01:01:26Z","title":"Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data","version":2},"cited_work":{"arxiv_id":"1910.01769","doi":"10.48550/arxiv.1910.01769","metadata_source":"pith","pith_arxiv_id":"1910.01769","snapshot_observed_at":"2026-08-05T02:49:54.815029Z","title":"Distilling BERT into Simple Neural Networks with Unlabeled Transfer Data","venue":"cs.CL","work_id":"ff33f9fa-8e7b-4254-b786-375ebd81a5e1","year":2019},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.139153Z"},"links":{"cited_paper":"/paper/1910.01769","citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:fc64ff9f808e1d38f6fadca380a1fbc3f2ee47c36141c40345e7d5a1f8378795","observation_id":"a22d36e5-eee2-4e63-af2a-2eb8d0e8c3ba","resolution":{"observed_at":"2026-08-01T18:18:48.310863Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-01T18:15:05.257996Z","title":"What is being transferred in transfer learning?,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.257996Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:61fb4dacedd0de5dd71415a7da4bc8a4e91376e3ed820629f58775d8aeb1ac63","observation_id":"02203f92-021e-44b9-aa2d-4e9c2b2ebb25","resolution":{"observed_at":"2026-08-01T18:15:05.257996Z","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":"2026-08-01T18:15:05.373239Z","title":"Deep Residual Learning for Image Recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.373239Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:02bafddf8f9aa894c921b8f3577c963ca15a5eb429ed1f6dc7ed288a430136d8","observation_id":"7ed8c521-a6fc-4130-b4b8-621712c3b89c","resolution":{"observed_at":"2026-08-01T18:15:05.373239Z","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":"2026-08-01T18:15:05.488446Z","title":"In -Memory Computing in Emerging Memory Technologies for Machine Learning: An Overview,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.488446Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:641da1e0470d761f2295d979d503e173426fbe317a6820ec59e2af40a2aefd19","observation_id":"9769f94b-e7c4-45fc-b232-836173e99140","resolution":{"observed_at":"2026-08-01T18:15:05.488446Z","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":"2026-08-01T18:15:05.655648Z","title":"ISAAC: A Convolutional Neural Network Accelerator with In-Situ Analog Arithmetic in Crossbars,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.655648Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:22fac2f0c9ff37082650f505aaa3165d3304724d9b122193349b621ba4ad09c8","observation_id":"85468797-e4d5-4e22-9aaf-a2f997c85700","resolution":{"observed_at":"2026-08-01T18:15:05.655648Z","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":"2026-08-01T18:15:05.773303Z","title":"HuNT: Exploiting Heterogeneous PIM Devices to Design a 3 -D Manycore Architecture for DNN Training,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.773303Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:d066b27a9621b7b17b8e5db7673301ef6061441bc6d8a8fae4841b79f3f4c418","observation_id":"c69ff88c-0042-4c67-bb97-c64e95d26dc2","resolution":{"observed_at":"2026-08-01T18:15:05.773303Z","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":"2026-08-01T18:15:05.923306Z","title":"Hybrid RRAM/SRAM in -Memory Computing for Robust DNN Acceleration,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:05.923306Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:44884eeaa096c98324fe2afdf3b833e85be1b3c105f76917189d4036d682b9bf","observation_id":"098172f6-9301-4e3d-88e9-d13ca12d8cf5","resolution":{"observed_at":"2026-08-01T18:15:05.923306Z","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":"2026-08-01T18:15:06.069741Z","title":"Surgical fine -tuning improves adaptation to distribution shifts,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.069741Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:54fa85afea3e47ca56192f01bc9afddd5142536857dc7917b7fd874eedcbae31","observation_id":"8a9b96b1-3a35-4762-8453-36560de0ab02","resolution":{"observed_at":"2026-08-01T18:15:06.069741Z","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":"2026-08-01T18:15:06.228445Z","title":"Deep residual learning for image recognition: A survey,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.228445Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:9fef7ebc0cdf2ba86904d5d06fa5aa95d67da698976c4ca28ce13bad6a62762f","observation_id":"591288dc-2435-4750-8cf5-65b8c3a352ac","resolution":{"observed_at":"2026-08-01T18:15:06.228445Z","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":"2026-08-01T18:15:06.354492Z","title":"SpotTune: Transfer Learning Through Adaptive Fine - Tuning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.354492Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:9319d7b89217d07099b4cfdf8cb6a5e3be0ef20e77ec59f411439b74a83abc7c","observation_id":"bc3e5799-9f2a-49d8-8c66-9bd5be9646a7","resolution":{"observed_at":"2026-08-01T18:15:06.354492Z","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":"2026-08-01T18:15:06.541125Z","title":"Automatic layer selection for transfer learning and quantitative evaluation of layer effectiveness,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.541125Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:7d3853184cdf5f9346c24b9967ff71d94b42f3baa04204932b89adc4192a90d4","observation_id":"e40497ef-670d-49c6-aa4b-9f7841134afa","resolution":{"observed_at":"2026-08-01T18:15:06.541125Z","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":"2026-08-01T18:15:06.712495Z","title":"Lora: Low-rank adaptation of large language models.,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.712495Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:4aa7bd117884eae19726c82f5e2b915a28cb71d6d8acd1b5744a226b2552d192","observation_id":"72f57257-9060-413e-a6ad-4b5d28fff8cf","resolution":{"observed_at":"2026-08-01T18:15:06.712495Z","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":"2026-08-01T18:15:06.848730Z","title":"Few -shot parameter -efficient fine -tuning is better and cheaper than in-context learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.848730Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:8b1cef6f40e5366091ab8e5d809eddae2f2db4f3d921420ef4717762c5ea952c","observation_id":"8e6c632c-1a86-4617-8061-a023105339a7","resolution":{"observed_at":"2026-08-01T18:15:06.848730Z","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":"2026-08-01T18:15:06.938401Z","title":"Language models are few -shot learners,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:06.938401Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:9a26c1e27281a45802fd49489ce9393cd3d2fb93ff6828a8ca88ef2f431eeb75","observation_id":"f11dd851-79fa-47eb-a3b3-2995b780cf29","resolution":{"observed_at":"2026-08-01T18:15:06.938401Z","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":"2026-08-01T18:15:07.017478Z","title":"Lora-c: Parameter-efficient fine-tuning of robust cnn for iot devices,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.017478Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:09b1cf44206b3fa2b77b0cf62c4f839587a7b9930c29ae0de8c85e7dcabf0b54","observation_id":"886874e9-ef49-4fa1-b1be-e168bbd264cd","resolution":{"observed_at":"2026-08-01T18:15:07.017478Z","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":"2026-08-01T18:15:07.095306Z","title":"PipeLayer: A Pipelined ReRAM -Based Accelerator for Deep Learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.095306Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:1b3b952cfbf0e4005800870c6ae0d18acf010a50e47ec62726742544973987f7","observation_id":"fa222c81-8ecf-4583-886d-e4b2e0aa23d8","resolution":{"observed_at":"2026-08-01T18:15:07.095306Z","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":"2026-08-01T18:15:07.247299Z","title":"FARe: Fault-Aware GNN Training on ReRAM-Based PIM Accelerators,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.247299Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:54b54840fb0c12346b91c431cf9407a1ffad88dae281bcaa7f197257b5344906","observation_id":"c97cdc2d-22d3-463b-b3a1-d4ee466928ed","resolution":{"observed_at":"2026-08-01T18:15:07.247299Z","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":"2026-08-01T18:15:07.414703Z","title":"Improving neural networks by preventing co - adaptation of feature detectors,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.414703Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:0ae91192a098c26c1a4a59c5f7d661507e6df503eb90ee247b85c7042fcbf10f","observation_id":"3062cbd9-61c5-40ea-9e08-638ba1defc7e","resolution":{"observed_at":"2026-08-01T18:15:07.414703Z","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":"2026-08-01T18:15:07.504019Z","title":"Deep networks with stochastic depth,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.504019Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:69d5888593c2c3411917d28ccf1f49f1cdb9d269b213a10375a4f8ab27d21eb1","observation_id":"33137e6e-aee9-4e9c-b913-8c2e0c444a45","resolution":{"observed_at":"2026-08-01T18:15:07.504019Z","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":"2026-08-01T18:15:07.691633Z","title":"DyLoRA: Parameter-efficient tuning of pre -trained models using dynamic search-free low-rank adaptation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.691633Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:72266d4e69db18b37e251b9150abefb8f52add51ad2340c1758174611bdaea55","observation_id":"07bb7b0c-7c43-4a76-94fb-0dca145f694b","resolution":{"observed_at":"2026-08-01T18:15:07.691633Z","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":"2026-08-01T18:15:07.867912Z","title":"Learning ordered representations with nested dropout,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.867912Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:0ae4ebc07c0f98028a1b712b604b53760fff58234e3cdfd215dc9fa96b10f3e8","observation_id":"ee6baaca-bb5d-4849-847c-3925f82d4d79","resolution":{"observed_at":"2026-08-01T18:15:07.867912Z","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":"2026-08-01T18:15:07.959044Z","title":"CIMAT: A Compute -In-Memory Architecture for On - chip Training Based on Transpose SRAM Arrays,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:07.959044Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:d7d014de50e550c73890019f869f75bf00580848a65b23044e5b8ad5a7915aa5","observation_id":"4bc69649-008e-40c6-95fc-9c6a4e3eb0bf","resolution":{"observed_at":"2026-08-01T18:15:07.959044Z","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":"2026-08-01T18:15:08.158295Z","title":"PUMA: A Programmable Ultra -efficient Memristor - based Accelerator for Machine Learning Inference,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:08.158295Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:d095bc02544a0a0612abaa4d4ebdbe3ad17b19a1b0841dd0019d3fc1ae8ce59f","observation_id":"5b107c6d-5b86-42a7-a8a4-0386de99444b","resolution":{"observed_at":"2026-08-01T18:15:08.158295Z","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":"2026-08-01T18:15:08.285065Z","title":"ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:08.285065Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:bf64c41eeda5f1c185198fc584aa8824bb52c87d384a82366ccf43ccca92fd5b","observation_id":"bd0f68bd-b4df-4fcd-bd3a-85db5961fd22","resolution":{"observed_at":"2026-08-01T18:15:08.285065Z","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":"2026-08-01T18:15:08.443824Z","title":"ImageNet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:08.443824Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:4fb1a5e9e4ef6c60754205a32c6d9ee2bdaad75cd7e4b070ff37b47434588fab","observation_id":"cbae6f06-6f56-4014-9042-a89de1605acb","resolution":{"observed_at":"2026-08-01T18:15:08.443824Z","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":"2026-08-01T18:15:08.586864Z","title":"JESD235D JEDEC Standard, High Bandwidth Memory DRAM (HBM1, HBM2)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:08.586864Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:4169827235c191200bbc1b93bec7fc5e3530792f5291f7589322da6e0bf0199b","observation_id":"da686439-27b3-4adb-8e86-92a54aed2086","resolution":{"observed_at":"2026-08-01T18:15:08.586864Z","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":"2026-08-01T18:15:08.712240Z","title":"TPU v4: An Optically Reconfigurable Supercomputer for Machine Learning with Hardware Support for Embeddings,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:08.712240Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:a7ec73c487013c3c96fd6f74c56e80c276e35e4072c81ce082d885302b9b65b7","observation_id":"2f5755ff-98c6-43c1-a279-8a180bd870b2","resolution":{"observed_at":"2026-08-01T18:15:08.712240Z","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":"2026-08-01T18:15:08.882133Z","title":"JESD209 - 5C, Low Power Double Data Rate (LPDDR) 5/5X","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:08.882133Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:65a3b5871c8805ddb99807fb5ed67537f4707614994eacb7e709f996470325b6","observation_id":"c54e1c77-31e4-4b0d-993b-4fb4505d12f4","resolution":{"observed_at":"2026-08-01T18:15:08.882133Z","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":"2026-08-01T18:15:09.084823Z","title":"Atleus: Accelerating Transformers on the Edge Enabled by 3D Heterogeneous Manycore Architectures,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T18:15:09.084823Z"},"links":{"citing_paper":"/paper/2607.17371"},"observation_digest":"sha256:028f8edd2f986c6b11e4b88e522e054429ccb2f91e085223f95834791500c335","observation_id":"79b22016-40a9-4c08-9af1-04261c0cb70b","resolution":{"observed_at":"2026-08-01T18:15:09.084823Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.17371","last_updated":"2026-07-19T18:19:46Z","latest_version":1,"primary_category":"cs.AR","snapshot_observed_at":"2026-08-10T13:15:16.522332Z","submitted_at":"2026-07-19T18:19:46Z","title":"ADEPT: Architecture-Driven Energy-Efficient CNN Fine-Tuning on PIM Accelerators"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":43,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":44},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2607.17371."}