{"as_of":"2026-08-23T21:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0e22b9d112fdb1d11ce13efdb5b1abe52cd20e15dffb12234d7e79aa15cd3299","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T19:06:09.743363Z","state":"measured"},{"denominator":41,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":41,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+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/2512.11826/citation-record","integrity":"/paper/2512.11826/integrity","json":"/paper/2512.11826/citation-record.json","paper":"/paper/2512.11826"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T19:06:07.450416Z","title":"A survey of on-device machine learning: An algorithms and learning theory perspective,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.450416Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:b36657ff86ebf487505bef8adf7f126920e3d46ea4200ed2fd6998d47b6b0382","observation_id":"a3dd591f-c079-4042-97c4-3ae8232e15ba","resolution":{"observed_at":"2026-08-03T19:06:07.450416Z","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":"2026-08-03T19:06:07.510205Z","title":"Df-lnpu: A pipelined direct feedback alignment-based deep neural network learning processor for fast online learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.510205Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:5d538f186fc317078501c3dd6a112ff3fd7c066744538811b3c5ca96cfd890cb","observation_id":"c3ac1636-5a82-4cba-849c-7cc6fe5a9e7d","resolution":{"observed_at":"2026-08-03T19:06:07.510205Z","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":"2026-08-03T19:06:07.567847Z","title":"A neural network training processor with 8-bit shared exponent bias floating point and multiple-way fused multiply-add trees,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.567847Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:08a5b8b79622de8cd5d90a0820129137a84d6c20dac16391b969c2858f6f7be4","observation_id":"21712cc3-6b3e-4c40-9e10-d2c2d0a0a0a5","resolution":{"observed_at":"2026-08-03T19:06:07.567847Z","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":"2026-08-03T19:06:07.648729Z","title":"CHIMERA: A 0.92-TOPS, 2.2-TOPS/W edge AI accelerator with 2-MByte on-chip foundry resistive RAM for efficient training and inference,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.648729Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:c5e94ed71dbccd2e8890a9907ea76f3639d6c33dca55659e82cd6dbedb1a8501","observation_id":"48d4b583-5050-419a-86e5-05abb6177c77","resolution":{"observed_at":"2026-08-03T19:06:07.648729Z","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":"2026-08-03T19:06:07.733276Z","title":"Trainer: An energy-efficient edge-device training processor supporting dynamic weight pruning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.733276Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:bb8f40d0b4378790bc258a7f17459b32fd0e81a8be0d54a7046d30b337e72311","observation_id":"e8943a7d-5e57-4566-bce2-229e370270c8","resolution":{"observed_at":"2026-08-03T19:06:07.733276Z","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":"2026-08-03T19:06:07.798109Z","title":"A 28-nm 8-bit floating- point tensor core-based programmable cnn training processor with dynamic structured sparsity,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.798109Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:3d538f56ef3ac1b6cc4b0e13d6ab4e97c1d51cebe6ab65d49ecf2f0205582e1b","observation_id":"4ab7f6a3-5e8f-46c3-aa6d-626c1e2537a9","resolution":{"observed_at":"2026-08-03T19:06:07.798109Z","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":"2026-08-03T19:06:07.874968Z","title":"A 4.69-TOPS/W Training, 2.34-µJ/Image Inference On-Chip Training Accelerator With Inference- Compatible Backpropagation and Design Space Exploration in 28-nm CMOS,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.874968Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:0058c1da1608532cf10e0ded7c5d9b9b3a00a9a34c8eeba8239a39ae5b01daa5","observation_id":"c408ff1b-67b0-420b-920e-42e4ba9bf6aa","resolution":{"observed_at":"2026-08-03T19:06:07.874968Z","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":"2026-08-03T19:06:07.931393Z","title":"An overview of energy-efficient hardware accelerators for on-device deep-neural-network training,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.931393Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:53a184c05b762a37631d174a7aef8ea5820da251c711b6c3f7fc2d43cbb155d6","observation_id":"ab4c7ff4-660a-43da-82e7-c1d3ad3bde30","resolution":{"observed_at":"2026-08-03T19:06:07.931393Z","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":"2026-08-03T19:06:07.994578Z","title":"Sp-pim: A super- pipelined processing-in-memory accelerator with local error prediction for area/energy-efficient on-device learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:07.994578Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:d7784c6cc9de0b578447aed8e69432eb0a8340e8850f73295f6fcbf5289262ac","observation_id":"91735ea5-3731-47f2-9107-454a63a24f36","resolution":{"observed_at":"2026-08-03T19:06:07.994578Z","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":"2026-08-03T19:06:08.050497Z","title":"Tinytl: Reduce memory, not parameters for efficient on-device learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.050497Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:b21817e0288a5532336bd2c751324401f0b0d95e61908d0eba24568525da5fc2","observation_id":"5b22fb24-2b14-4001-8223-a92b9f74bacb","resolution":{"observed_at":"2026-08-03T19:06:08.050497Z","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":"2026-08-03T19:06:08.108349Z","title":"T-pim: An energy- efficient processing-in-memory accelerator for end-to-end on-device training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.108349Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:962d2c5d0760559343dd1b54e7ea51600aa135b2b95d901e0b26e4183cf63be6","observation_id":"096c8102-1c00-4cc4-9703-f425bce8eedf","resolution":{"observed_at":"2026-08-03T19:06:08.108349Z","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":"2026-08-03T19:06:08.166306Z","title":"Scicnn: A 0-shot-retraining patient-independent epilepsy-tracking soc,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.166306Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:f0dfe65b2182c614637f8cee2b8619777bf2492eeea4b481e4efb9b7b32ecd0a","observation_id":"9c66d7e0-bde1-40ba-8aab-504d4c464b82","resolution":{"observed_at":"2026-08-03T19:06:08.166306Z","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":"2026-08-03T19:06:08.258423Z","title":"A high accuracy and ultra-energy-efficient zero- shot-retraining seizure detection processor,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.258423Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:a14d1584d977ce7e8ad39ac25cc302216f67e370c7def874286f9c26f76c4522","observation_id":"bcce2e15-2a43-4716-ab43-3b5f04b73a12","resolution":{"observed_at":"2026-08-03T19:06:08.258423Z","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":"2026-08-03T19:06:08.348145Z","title":"Energy-efficient reconfigurable xgboost inference accelerator with modular unit trees via selective node execution and data movement,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.348145Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:5042c424fea5f9fa1b90d6c7099c33a94e548fbe404eea3e6b42cb8c0f1d62e3","observation_id":"cc09c5b7-7efb-402d-affb-0e9cbd0f52ca","resolution":{"observed_at":"2026-08-03T19:06:08.348145Z","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":"2026-08-03T19:06:08.388078Z","title":"Hybrid slc-mlc rram mixed-signal processing-in-memory architecture for transformer acceleration via gradient redistribution,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.388078Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:3ffd07a35259e011aff90eb414f7dcacb539c0e8e0012af8cf0243212709ed81","observation_id":"d61202ca-3410-493d-99b2-374f7791c3f2","resolution":{"observed_at":"2026-08-03T19:06:08.388078Z","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":"2026-08-03T19:06:08.456322Z","title":"On- device learning systems for edge intelligence: A software and hardware synergy perspective,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.456322Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:ddc9385fe7ef3130ae7778b18bed8e18733efbed225733992bdbed26e7de96c3","observation_id":"70f97823-1122-487f-b1aa-247676c72e90","resolution":{"observed_at":"2026-08-03T19:06:08.456322Z","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":"2026-08-03T19:06:08.530803Z","title":"Experimentally validated memristive memory augmented neural network with efficient hashing and similarity search,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.530803Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:996841cedae1f07f35ee2f71a6900d047503f0283ee1e74955c304d66306c4ee","observation_id":"7738e5f0-9880-4385-8e3b-025ca028f416","resolution":{"observed_at":"2026-08-03T19:06:08.530803Z","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":"2026-08-03T19:06:08.610144Z","title":"Sapiens: A 64-kb rram-based non-volatile associative memory for one-shot learning and inference at the edge,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.610144Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:dd67374e3710ef2853657b08f56a37341bba9b17588e5025c2feabd8cee333cf","observation_id":"386084c8-f9b2-464c-8585-f88e62a79e04","resolution":{"observed_at":"2026-08-03T19:06:08.610144Z","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":"2026-08-03T19:06:08.723147Z","title":"In-memory realization of in-situ few-shot continual learning with a dynamically evolving explicit memory,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.723147Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:928adea1e554d90f9c8eabeff4aa313fd138838eeec64bd4245533d8b59bbbe2","observation_id":"1f4ae94d-2628-436b-9cda-630781764707","resolution":{"observed_at":"2026-08-03T19:06:08.723147Z","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":"2026-08-03T19:06:08.796045Z","title":"Understanding of object detection based on cnn family and yolo,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.796045Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:eb838793fc416dcdf51c3572ac8e36cdb354a31230463a076360ebed8ab08dd1","observation_id":"f924e68e-b24f-4797-8b19-6629106f4596","resolution":{"observed_at":"2026-08-03T19:06:08.796045Z","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":"2026-08-03T19:06:08.839386Z","title":"Optimization as a model for few-shot learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.839386Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:e8bbdeed1c14aeeeb4d12e517c0fc30ac887f504774392cdbb6d4314b6939903","observation_id":"9134fafa-3221-4207-bc1a-9485b8499305","resolution":{"observed_at":"2026-08-03T19:06:08.839386Z","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":"2026-08-03T19:06:08.900737Z","title":"Hyperdimensional computing: An introduction to computing in distributed representation with high-dimensional random vectors,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.900737Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:273d203c39e5f98fd1874868e5bb5217e77175400aab98c60343887be49bae3f","observation_id":"b73dc6f2-da7c-4b5f-a210-3a80035863e0","resolution":{"observed_at":"2026-08-03T19:06:08.900737Z","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":"2026-08-03T19:06:08.982910Z","title":"A theoretical perspective on hyperdimensional computing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:08.982910Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:8c969efdede5b99ee8547bcc9cbc6ae1080bbb0da79d12acc19fae7befe4783c","observation_id":"511a1213-38a9-4d8e-ba74-3826e5e73fdd","resolution":{"observed_at":"2026-08-03T19:06:08.982910Z","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":"2026-08-03T19:06:09.061752Z","title":"Fsl-hdnn: A 5.7 tops/w end-to- end few-shot learning classifier accelerator with feature extraction and hyperdimensional computing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.061752Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:75027c7b0b517ac111d949a4f409b96fb7243f936ac5c60e0af5513be48ac14b","observation_id":"5d8222f0-ff4f-4c59-868c-92252f62a211","resolution":{"observed_at":"2026-08-03T19:06:09.061752Z","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":"2026-08-03T19:06:09.145111Z","title":"Meta-transfer learning for few-shot learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.145111Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:69ef5f69450dbccd294c65984d0753d06e101cc1b5fd293b8845805f977d5604","observation_id":"2dabcce1-8e53-4640-b0ed-fdb554422e86","resolution":{"observed_at":"2026-08-03T19:06:09.145111Z","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":"2026-08-03T19:06:09.198792Z","title":"Rethinking few-shot image classification: A good embedding is all you need?,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.198792Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:300d95cf849379741b8c27e2a91219d0428497aa1271b799f786f6d6f0768ac1","observation_id":"657eb3bc-93c5-448c-acc2-f6e691f0c582","resolution":{"observed_at":"2026-08-03T19:06:09.198792Z","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":"2026-08-03T19:06:09.222234Z","title":"Few-shot image classification: Just use a library of pre-trained feature extractors and a simple classifier,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.222234Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:65270db7a4087eaf1e854ae87a392e38d712ded2638d6b50ea230a66a4a6c729","observation_id":"2c53dbeb-0d8f-4016-b3d7-9583ac6c0bbd","resolution":{"observed_at":"2026-08-03T19:06:09.222234Z","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":"2026-08-03T19:06:09.254812Z","title":"Patternet: explore and exploit filter patterns for efficient deep neural networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.254812Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:62b3607b842512c24adcb06e9618c80a1c8089a2b5957ad22095b38ebf12f692","observation_id":"400edaa0-c532-4e79-a2c4-c1b953a6bfbc","resolution":{"observed_at":"2026-08-03T19:06:09.254812Z","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":"2026-08-03T19:06:09.276024Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.276024Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:6ae101f414913f57473278a8f4758d3fbfaf4be43f4f36a805f2e67912608b4b","observation_id":"7392078e-22b8-4407-bd76-379891dfdd5f","resolution":{"observed_at":"2026-08-03T19:06:09.276024Z","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":"2026-08-03T19:06:09.318154Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.318154Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:f225214d1e85f5878f247b29fff14be4b3c315ee9b800568bc3029a5e089dd54","observation_id":"f3659d98-5a16-489e-b5f0-780fd76f847e","resolution":{"observed_at":"2026-08-03T19:06:09.318154Z","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":"2026-08-03T19:06:09.343203Z","title":"Locality-based encoder and model quantization for efficient hyper- dimensional computing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.343203Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:fe9056fa08a93a0ab28f02cd6ebb0598bb0d1cb2f5b6ca8fa8164f25852d4ef4","observation_id":"6572507a-eeeb-4d2f-b53f-1bcd2d62a740","resolution":{"observed_at":"2026-08-03T19:06:09.343203Z","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":"2026-08-03T19:06:09.379197Z","title":"Study and analysis of various lfsr architectures,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.379197Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:22399dc842e6b528286853d68b602f854f42b6d300f9edd4926ea89dbdb7bb18","observation_id":"a61aacd5-0831-4516-9715-02d8966d756b","resolution":{"observed_at":"2026-08-03T19:06:09.379197Z","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":"2026-08-03T19:06:09.415023Z","title":"Branchynet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.415023Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:3c23d54c43d2d7c3697db99741ab50f8e4c542120ef2b3912c93a3bed59e438d","observation_id":"9f5f9362-ee0f-4087-9e7c-fd2664388ae5","resolution":{"observed_at":"2026-08-03T19:06:09.415023Z","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":"2026-08-03T19:06:09.436967Z","title":"Locoexnet: Low-cost early exit network for energy efficient cnn accelerator design,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.436967Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:9e62bfe54f94521d5eca9156f73802a9988fc00fcbf9f2a08b37b0efe017cca2","observation_id":"abc26422-a97a-4233-a060-39eedde16ca2","resolution":{"observed_at":"2026-08-03T19:06:09.436967Z","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":"2026-08-03T19:06:09.474717Z","title":"Early-exit deep neural network-a comprehensive survey,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.474717Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:d2a0f4cab600f8c8cdb32a4bcc96e86fc50d2c05c00b9f92741657e475189df9","observation_id":"23d2fc4a-44d8-4da8-8485-87cb89aed6b5","resolution":{"observed_at":"2026-08-03T19:06:09.474717Z","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":"2026-08-03T19:06:09.507568Z","title":"Adaptive deep neural network inference optimization with eenet,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.507568Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:96bc4a9f9ae56771f9890abbd049feba0514a15e256af1283225a86421994a63","observation_id":"29ec8857-a01d-41d2-a80f-48a26c90ed4d","resolution":{"observed_at":"2026-08-03T19:06:09.507568Z","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":"2026-08-03T19:06:09.570247Z","title":"Tadam: Task dependent adaptive metric for improved few-shot learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.570247Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:b17a421c1fe000ade306a452e51b15309d9bdac83c938e0ca4b211768caf09c5","observation_id":"c43c6342-24ab-4f42-8746-25c181d36101","resolution":{"observed_at":"2026-08-03T19:06:09.570247Z","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":"2026-08-03T19:06:09.648157Z","title":"Automated flower classification over a large number of classes,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.648157Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:365f9b906a3c9b775f3668f9f9b7c01b7d32986d618cbd8fa8ba09f37315571d","observation_id":"9a64b7df-40d4-43c8-ad35-c1349c27dfc7","resolution":{"observed_at":"2026-08-03T19:06:09.648157Z","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":"2026-08-03T19:06:09.701997Z","title":"Detection of traffic signs in real-world images: The german traffic sign detection 10 benchmark,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.701997Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:37e25991ce6bae6f170989aacc337c9942b6cbefaef1a2bc9c2932a57997c521","observation_id":"1084d84c-3786-4f52-bb40-e1015fdff0fa","resolution":{"observed_at":"2026-08-03T19:06:09.701997Z","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":"2026-08-03T19:06:09.711792Z","title":"Imagenet: A large-scale hierarchical image database,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.711792Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:a5ca18f3ee8365986e25075025faf2cf66508133c45bd46caa6b72fcafc5178c","observation_id":"55eb8522-3fcf-483e-b254-09932fa0b960","resolution":{"observed_at":"2026-08-03T19:06:09.711792Z","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":"2026-08-03T19:06:09.743363Z","title":"Deepscaletool: A tool for the accurate estimation of technology scaling in the deep-submicron era,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T19:06:09.743363Z"},"links":{"citing_paper":"/paper/2512.11826"},"observation_digest":"sha256:1c2cf517ce4f9c9d0b5242401dc353ecf59961d1abd7358d1767404b5a5f94db","observation_id":"e2002b8e-e870-41e2-af57-e34d52bbbb65","resolution":{"observed_at":"2026-08-03T19:06:09.743363Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.11826","last_updated":"2025-12-02T02:36:19Z","latest_version":1,"primary_category":"cs.AR","snapshot_observed_at":"2026-08-19T06:06:19.943086Z","submitted_at":"2025-12-02T02:36:19Z","title":"FSL-HDnn: A 40 nm Few-shot On-Device Learning Accelerator with Integrated Feature Extraction and Hyperdimensional Computing"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":41,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":41},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 0 inbound Pith citation observations for arXiv:2512.11826."}