{"as_of":"2026-08-09T20:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:00e82e16a7486285836797a4df98589b9ae49c216e7f2672ba071b1088d22e33","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T08:50:39.370097Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2607.29353/citation-record","integrity":"/paper/2607.29353/integrity","json":"/paper/2607.29353/citation-record.json","paper":"/paper/2607.29353"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T08:50:33.332233Z","title":"A survey on the convergence of edge computing and ai for uavs: Opportunities and challenges,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.332233Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:3d8eb3d19ce913e3b43f040d70f91f44645fffdea9cb3c630379c55f3664992b","observation_id":"d7c89886-c043-452d-9b29-556bc19bad96","resolution":{"observed_at":"2026-08-03T08:50:33.332233Z","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":"2026-08-03T08:50:33.436847Z","title":"V ocell: A 65-nm speech-triggered wake-up soc for 10- µ w keyword spotting and speaker verification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.436847Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:ea340c3c75439dc24fc26bfa9027417790f7a6098b7ad525f2dd4ca29375d1c3","observation_id":"6026e7fe-a284-400c-a784-557d94ed5779","resolution":{"observed_at":"2026-08-03T08:50:33.436847Z","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":"2026-08-03T08:50:33.549410Z","title":"A 23-uw keyword spotting ic with ring-oscillator-based time-domain feature extraction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.549410Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:cead1ec07340bff45af1932612d9177c3333616abc6f3b78ae07826ff7771c98","observation_id":"d776d96a-3690-46f0-b3c2-85652afe464f","resolution":{"observed_at":"2026-08-03T08:50:33.549410Z","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":"2026-08-03T08:50:33.670452Z","title":"Tan, W.-H","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.670452Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:b2f4b2574d50660cc73bcd82d6cff7fe334484862d7dc4ff741b2972f22b9340","observation_id":"2665fb5d-920e-4501-b15c-4e78d5f99665","resolution":{"observed_at":"2026-08-03T08:50:33.670452Z","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":"2026-08-03T08:50:33.781884Z","title":"A 5.6µw 10-keyword end-to-end keyword spotting system using passive-averaging sar adc and sign-exponent-only layer fusion with 92.7% accuracy,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.781884Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:8e0fe602b255dc9bcb991684a7fd2c379899d83f821e1d000ab7173c61fcd57b","observation_id":"3ed3f82c-b2d2-4738-a025-1797fb15f200","resolution":{"observed_at":"2026-08-03T08:50:33.781884Z","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":"2026-08-03T08:50:33.870735Z","title":"An ultra-low power reconfigurable biomedical ai processor with adaptive learning for versatile wearable intelligent health monitoring,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.870735Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:3ee4e16550c6e6cf7f4b86daab2efd1cc70f07578a0ef3533e6c769420c4abd2","observation_id":"ffdb84cd-fb40-4052-8e59-1c543bc36ddd","resolution":{"observed_at":"2026-08-03T08:50:33.870735Z","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":"2026-08-03T08:50:33.980966Z","title":"A 3.9 mw 25- electrode reconfigured sensor for wearable cardiac monitoring system,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:33.980966Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:facbe27a245183cf89e3b2d90cf93522b33ba75b95b0ef178f4f6341a2aec66d","observation_id":"31f52ba8-1a15-4cea-b2ba-1948de6ccd46","resolution":{"observed_at":"2026-08-03T08:50:33.980966Z","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":"2026-08-03T08:50:34.055924Z","title":"A 1.06- µ w smart ecg processor in 65-nm cmos for real-time biometric authentication and personal cardiac monitoring,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:34.055924Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:4bfb393fc4d7424dbfcb75adbd17a700482e75e6fee3e94f0e2f2dcf1420e655","observation_id":"f4379345-013c-440d-a432-c3cdd41c954c","resolution":{"observed_at":"2026-08-03T08:50:34.055924Z","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":"2026-08-03T08:50:34.134197Z","title":"A 2.89 µ w dry-electrode enabled clockless wireless ecg soc for wearable applications,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:34.134197Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:93175a15e2e02d2a6b3e774ad6910864cecc6e3a6acc500e5ccdf2c6546803b1","observation_id":"aca944a0-135e-4cb8-b28f-7f7ef74d075a","resolution":{"observed_at":"2026-08-03T08:50:34.134197Z","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":"2026-08-03T08:50:34.183295Z","title":"An Ultra- Low Power Reconfigurable Biomedical AI Processor With Adaptive Learning for Versatile Wearable Intelligent Health Monitoring,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:34.183295Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:6537949ff1362e6e8765266761c92cda40fdfef4ecdff0b8bab932d1e796f8b4","observation_id":"68f0f806-48e7-4368-af94-c34f9117eb1d","resolution":{"observed_at":"2026-08-03T08:50:34.183295Z","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":"2026-08-03T08:50:34.261359Z","title":"Reckon: A 28nm sub-mm2 task-agnostic spiking recurrent neural network processor enabling on-chip learning over second-long timescales,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:34.261359Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:bc221fe3ef5c5b80044637c03f89ec8479e0d2a085fb15601f3a23e56ced184c","observation_id":"097132a3-9cd4-453c-8321-4de3ac58dafe","resolution":{"observed_at":"2026-08-03T08:50:34.261359Z","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":"2026-08-03T08:50:34.339309Z","title":"Tinyvers: A tiny versatile system-on-chip with state-retentive emram for ml inference at the extreme edge,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:34.339309Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:27dedb4999f6bd4833acff4716e0ae227146efa3e19ee740c9832021c6762615","observation_id":"c8952cc8-3402-413f-a61e-60bd2c400ea8","resolution":{"observed_at":"2026-08-03T08:50:34.339309Z","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":"2026-08-03T08:50:35.087155Z","title":"Embedded deep neural network processing: Algorithmic and processor techniques bring deep learning to iot and edge devices,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.087155Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:e36080a18fb391c0dff0b0e61ec025926b28590539880690dd96a20ffdedc37e","observation_id":"2f32478a-c71e-4414-92a4-f27eac3c7a31","resolution":{"observed_at":"2026-08-03T08:50:35.087155Z","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":"2026-08-03T08:50:35.180231Z","title":"Efficient processing of deep neural networks: A tutorial and survey,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.180231Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:daba02ac61c776bdcc147977474704979d7f9614101d9e40928c2ae143ee74f6","observation_id":"0c5639ce-86cf-454a-937c-7b7a01d19453","resolution":{"observed_at":"2026-08-03T08:50:35.180231Z","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":"2026-08-03T08:50:35.252510Z","title":"A 640m pixel/s 3.65 mw sparse event-driven neuromorphic object recognition processor with on-chip learning,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.252510Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:c01161f337430d0d3443acc506d6802fe58801f74ffda33a8214543dcb6e7e00","observation_id":"989e9aff-647a-411e-871c-123763975110","resolution":{"observed_at":"2026-08-03T08:50:35.252510Z","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":"2026-08-03T08:50:35.312293Z","title":"A 42pj/decision 3.12 tops/w robust in-memory machine learning classifier with on-chip training,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.312293Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:c233bae0242a396ef237e0c11e03111517b4d9ca10f0e7cb5aa6b018726afc46","observation_id":"62a69148-0bcf-4526-af9a-9cb4fd9f4955","resolution":{"observed_at":"2026-08-03T08:50:35.312293Z","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":"2026-08-03T08:50:35.379395Z","title":"A 55nm time-domain mixed-signal neuromorphic accelerator with stochastic synapses and embedded reinforcement learning for autonomous micro-robots,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.379395Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:e0b1f82a86852931903947afb76cbd3facc891cd765cb80a16774caa381551cf","observation_id":"5bc34053-9955-43fd-9c84-a14b5969342c","resolution":{"observed_at":"2026-08-03T08:50:35.379395Z","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":"2026-08-03T08:50:35.457540Z","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":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.457540Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:7f0150fc53312288b24cf750aa3bef6681273c5652a4ee9dbb4898f5c2926d21","observation_id":"98bd8fe6-c2a5-4786-b351-b6af40f19c1e","resolution":{"observed_at":"2026-08-03T08:50:35.457540Z","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":"2026-08-03T08:50:35.515571Z","title":"Clo-hdnn: A 4.66 tflops/w and 3.78 tops/w continual on-device learning accelerator with energy-efficient hyperdimensional computing via progressive search,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.515571Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:21a7ac89ace0faab352658459a200bf8bd00f56f719bf62e821ece9b139a30ad","observation_id":"c62d43f1-837f-45fe-bb8b-e0a5f281865c","resolution":{"observed_at":"2026-08-03T08:50:35.515571Z","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":"2026-08-03T08:50:35.568765Z","title":"One-shot learning with memory- augmented neural networks using a 64-kbit, 118 gops/w rram-based non-volatile associative memory,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.568765Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:a15768348a47722aaa51777d6af60dcd21a215d8fcb844fd21869c56c31352a9","observation_id":"edb33532-91f4-4139-b998-62cab852e417","resolution":{"observed_at":"2026-08-03T08:50:35.568765Z","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":"2026-08-03T08:50:35.642889Z","title":"An in-memory computing sram macro for memory-augmented neural network,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.642889Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:65d47a4c7d75c52872031d2d3f0e2710a89bd80b256a1643a67ac725fdc2617e","observation_id":"28fc384d-7c3d-4c14-b835-ac1e68e32abe","resolution":{"observed_at":"2026-08-03T08:50:35.642889Z","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":"2026-08-03T08:50:35.700978Z","title":"A 4096-neuron 1m-synapse 3.8-pj/sop spiking neural network with on-chip stdp learning and sparse weights in 10-nm finfet cmos,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.700978Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:f9cf2d262cab8c9a37a87d53d03ca2968ede2a0bf951e9ffed7bf5e593371a29","observation_id":"0a9ea6a2-2606-4c3f-b153-6c20387c3ab6","resolution":{"observed_at":"2026-08-03T08:50:35.700978Z","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":"2026-08-03T08:50:35.772301Z","title":"Tess: A scalable temporally and spatially local learning rule for spiking neural networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.772301Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:2173acdb4d7709b50974cee745748159827927754b887f4180bb8dc42d6565c6","observation_id":"d2bff01e-7451-4a04-9da4-95fa67a58772","resolution":{"observed_at":"2026-08-03T08:50:35.772301Z","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":"2026-08-03T08:50:35.863655Z","title":"Online spatio-temporal learning in deep neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.863655Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:fdc09ad2803d2ed5cbc2879d32dc11b6382c717340ca726bdd5f51cb5e44c6f8","observation_id":"67ecec7c-62ee-4ac6-924f-8d966d9ef021","resolution":{"observed_at":"2026-08-03T08:50:35.863655Z","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":"2026-08-03T08:50:35.969483Z","title":"Chameleon: A multiplier-free temporal convolutional network accelerator for end-to-end few-shot and continual learning from sequential data,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:35.969483Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:82f218177b465a46fb4c031bd23b93e3cabf41b665ed8907bae7afc069e2f78b","observation_id":"054e3d67-514e-4b0a-9991-34d72d7f0566","resolution":{"observed_at":"2026-08-03T08:50:35.969483Z","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":"2026-08-03T08:50:36.059995Z","title":"Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences,","venue":null,"work_id":null,"year":1980},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.059995Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:511e3d24a1664a58eef4e22892aaf6345ca8e1ff5c8dd911eb6ac63ff4c019ed","observation_id":"b052a892-4762-4c1f-808e-c6da4c183ae5","resolution":{"observed_at":"2026-08-03T08:50:36.059995Z","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":"2026-08-03T08:50:36.160461Z","title":"Human-level concept learning through probabilistic program induction,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.160461Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:e660dc6b81afc119c6a5aa80dc543a2adcb6ef8e8aaf7dedfc587eabeaed6045","observation_id":"bb16e01c-2d16-45ea-8542-11aef4943cf1","resolution":{"observed_at":"2026-08-03T08:50:36.160461Z","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":"2026-08-03T08:50:36.225932Z","title":"Prototypical networks for few-shot learning,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.225932Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:0e03131f472025e4e4004b5f0c0528b5fa146afeb3dfb9c5664c5e9495e87c01","observation_id":"b5e4ac00-9ab1-4833-ac38-2f024c7265a8","resolution":{"observed_at":"2026-08-03T08:50:36.225932Z","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":"2026-08-03T08:50:36.308834Z","title":"Learning to compare: Relation network for few-shot learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.308834Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:40ff3e9135ea9f24b082a954bf3718b4c0434733c893b49d070a769836c3cf82","observation_id":"41a7dfba-2b89-404b-9115-c1c6eacaa1f0","resolution":{"observed_at":"2026-08-03T08:50:36.308834Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.01454","last_updated":"2021-09-09T20:36:28Z","snapshot_observed_at":"2026-07-06T10:56:16.595541Z","submitted_at":"2021-04-03T17:27:37Z","title":"Few-Shot Keyword Spotting in Any Language","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.01454","snapshot_observed_at":"2026-08-03T08:50:36.375877Z","title":"Few-shot keyword spotting in any language,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.375877Z"},"links":{"cited_paper":"/paper/2104.01454","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:8491a11fe006ee1900a276e27d7e1b65e3516b3ec591133c8f7ecf182bfc1af2","observation_id":"246026c2-7841-4f21-9e01-e2c5b085c8d3","resolution":{"observed_at":"2026-08-03T08:50:36.375877Z","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":"2026-08-03T08:50:36.456582Z","title":"Matching networks for one shot learning,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.456582Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:9872c57355164498864cc55214f92249d117e5e2afe0600dde38068354a5b73e","observation_id":"6abf80e5-2d50-449a-880c-ac551045c7d0","resolution":{"observed_at":"2026-08-03T08:50:36.456582Z","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":"2026-08-03T08:50:36.497975Z","title":"Domain-adaptive discriminative one-shot learning of gestures,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.497975Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:5f0bd5481e31360c809d13708c5e6e791cb02b2ac13ab9ad85778dcc09eee014","observation_id":"9a4d93d7-f4d4-4ecd-b79f-7205dc54b888","resolution":{"observed_at":"2026-08-03T08:50:36.497975Z","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":"2026-08-03T08:50:36.558336Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.558336Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:1cfb4e49310508520bde49a2f4d36d87741ab77354aaed81cfc15aae407e4b4d","observation_id":"513a05ab-0c3c-4192-b17f-3e3a2bd09411","resolution":{"observed_at":"2026-08-03T08:50:36.558336Z","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":"2026-08-03T08:50:36.642688Z","title":"One shot learning of simple visual concepts,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.642688Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:1015b61618f67053a80c3ecd796aca61712a3f7d13be135ca8d80c4948d4bc75","observation_id":"51723c2b-bb35-497f-bcf0-82db3a97720b","resolution":{"observed_at":"2026-08-03T08:50:36.642688Z","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":"2026-08-03T08:50:36.721777Z","title":"Siamese neural networks for one-shot image recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.721777Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:13979e64380836753cb90ee7d06fdf2aded25eac760132854a1250aaf0ec5450","observation_id":"38e0dc74-0918-41fc-bf2f-edbcb1ce65e7","resolution":{"observed_at":"2026-08-03T08:50:36.721777Z","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":"2026-08-03T08:50:36.807480Z","title":"One-shot learning of object categories,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.807480Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:efa7abd093ed7f5327d0df789edb993eb80943c079ab75d4a7f91f15168782c7","observation_id":"826252f6-a11a-4710-8e44-8c1ad17a375f","resolution":{"observed_at":"2026-08-03T08:50:36.807480Z","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":"2026-08-03T08:50:36.890733Z","title":"Few- shot class-incremental learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.890733Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:01a3dfa88cf09c0e3c632d66c6c5d165f83cfede659e6e935bf62e006034eda8","observation_id":"f6a3ac3b-5649-4fa7-89ea-dae6a32e47c9","resolution":{"observed_at":"2026-08-03T08:50:36.890733Z","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":"2026-08-03T08:50:36.947488Z","title":"The neurobench framework for benchmarking neuromorphic computing algorithms and systems,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:36.947488Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:0cddcf0b317fd067c42c00530ae221b9cb704a3c21974afa22cc4f507bec826c","observation_id":"73f9ef02-46c8-4582-aafc-b962d5325011","resolution":{"observed_at":"2026-08-03T08:50:36.947488Z","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":"2026-08-03T08:50:37.027873Z","title":"Overcoming catastrophic forgetting in neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.027873Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:d475969d57c4206afae44b1ff09c275fe7807e2b45d4b081180ae2ff3a024abc","observation_id":"be94ca2e-d410-4739-8ef0-e1dea6c3a4f8","resolution":{"observed_at":"2026-08-03T08:50:37.027873Z","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":"2026-08-03T08:50:37.087239Z","title":"Attribute-based classification for zero-shot visual object categorization,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.087239Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:dc3d5ced2d8056a39e1707f882043135995f6c718af149c1ab6ace7ad57ddc82","observation_id":"4b7468f2-d62a-4d5a-b116-5cc817c7b728","resolution":{"observed_at":"2026-08-03T08:50:37.087239Z","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":"2026-08-03T08:50:37.140858Z","title":"Trained transformers learn linear models in-context,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.140858Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:ad77c3a5013e0bdd0006afaecad8ab2ee24646491f98252332b5a441e7fc7a50","observation_id":"b258a1ad-f87c-4eb4-a5a5-46e846293cbc","resolution":{"observed_at":"2026-08-03T08:50:37.140858Z","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":"2026-08-03T08:50:37.201003Z","title":"What can transformers learn in-context? a case study of simple function classes,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.201003Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:683dc083d219bf05d1a4cd325a0bfab9692ee825e6dc1436402c9acde38023ef","observation_id":"3c0482b2-bd36-4464-9644-96280eaa4456","resolution":{"observed_at":"2026-08-03T08:50:37.201003Z","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":"2026-08-03T08:50:37.250140Z","title":"Language models are few-shot learners,","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.250140Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:4604c180bcd21deef59b942351ac743f97d22d561819697359437c968e823847","observation_id":"a40cf486-73a7-4784-b14d-aeb146924518","resolution":{"observed_at":"2026-08-03T08:50:37.250140Z","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":"2026-08-03T08:50:37.340570Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.340570Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:232cad29ade1f4b1603687d858fb78130c9766c2ddb4e6609a0bf4ea4cc414f3","observation_id":"4e11ce52-274b-4e9f-8c36-54df5bec101e","resolution":{"observed_at":"2026-08-03T08:50:37.340570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.15618","last_updated":"2025-02-25T16:27:38Z","snapshot_observed_at":"2026-07-06T18:19:25.869339Z","submitted_at":"2024-05-24T15:04:36Z","title":"MLPs Learn In-Context on Regression and Classification Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.15618","snapshot_observed_at":"2026-08-03T08:50:37.391440Z","title":"Mlps learn in-context on regression and classification tasks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.391440Z"},"links":{"cited_paper":"/paper/2405.15618","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:4bc05c3ea060f50e369117649bdfcd987103adf9988449a095316520aab0fcf6","observation_id":"3b43ba4e-1276-4c2a-9087-9b88a4948a54","resolution":{"observed_at":"2026-08-03T08:50:37.391440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1803.01271","last_updated":"2018-04-19T14:32:38Z","snapshot_observed_at":"2026-07-06T06:26:27.965096Z","submitted_at":"2018-03-04T00:20:29Z","title":"An Empirical Evaluation of Generic Convolutional and Recurrent Networks for Sequence Modeling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1803.01271","snapshot_observed_at":"2026-08-03T08:50:37.455637Z","title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.455637Z"},"links":{"cited_paper":"/paper/1803.01271","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:8c83d36082795affcb6179d2c596c9f4639148a4be2abfc89544a2bc7bac0da5","observation_id":"c5f3c437-970c-41ae-a235-16460a289f6a","resolution":{"observed_at":"2026-08-03T08:50:37.455637Z","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":"2026-08-03T08:50:37.464629Z","title":"Hyperdimensional computing: An introduction to comput- ing in distributed representation with high-dimensional random vectors,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.464629Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:9f6f4ae46fba374c5db1b3e54b63751421d6b6fdb9c4ca28f3d0599319070b9c","observation_id":"8f92447e-0273-4ca3-91e1-7e932248b633","resolution":{"observed_at":"2026-08-03T08:50:37.464629Z","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":"2026-08-03T08:50:37.545211Z","title":"Very deep convolutional neural networks for raw waveforms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.545211Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:466245fd0f9dbbefccd0008a1d7f5d104820ee1a523ffa379fd0229151ef4d5e","observation_id":"7316977f-f8ef-4660-bb3d-6922c9fe6b9b","resolution":{"observed_at":"2026-08-03T08:50:37.545211Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.03670","last_updated":"2019-07-25T17:56:23Z","snapshot_observed_at":"2026-07-06T07:44:28.011439Z","submitted_at":"2019-04-07T15:24:32Z","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.03670","snapshot_observed_at":"2026-08-03T08:50:37.709583Z","title":"Speech Model Pre-training for End-to-End Spoken Language Understanding","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.709583Z"},"links":{"cited_paper":"/paper/1904.03670","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:ef945048542cda015312fcd366c1e629fb6f5751fc0d80eab7dbe97ca1c1250a","observation_id":"f248c76e-2494-4794-a3f7-03a9e0cb401f","resolution":{"observed_at":"2026-08-03T08:50:37.709583Z","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":"2026-08-03T08:50:37.846227Z","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":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:37.846227Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:0f13597d3b67730d01bf9de621e85e904a9763fa154611c16f3bfc20eceb0d41","observation_id":"546ca876-5cf6-4e60-9290-c4a99b4a3d81","resolution":{"observed_at":"2026-08-03T08:50:37.846227Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.12973","last_updated":"2024-01-30T18:59:34Z","snapshot_observed_at":"2026-07-06T17:19:31.847730Z","submitted_at":"2024-01-23T18:59:21Z","title":"In-Context Language Learning: Architectures and Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12973","snapshot_observed_at":"2026-08-03T08:50:38.013907Z","title":"In-context language learning: Architectures and algorithms,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.013907Z"},"links":{"cited_paper":"/paper/2401.12973","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:2d6562333195175117953ab14748328ff44cf56086885969e03f97f074a553cc","observation_id":"ef486c4e-ca27-45d3-a0dc-7a42fe14ada8","resolution":{"observed_at":"2026-08-03T08:50:38.013907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00420","last_updated":"2019-01-09T11:11:47Z","snapshot_observed_at":"2026-07-06T07:18:30.039631Z","submitted_at":"2018-12-02T16:39:19Z","title":"Efficient Lifelong Learning with A-GEM","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00420","snapshot_observed_at":"2026-08-03T08:50:38.156737Z","title":"Efficient lifelong learning with a-gem,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.156737Z"},"links":{"cited_paper":"/paper/1812.00420","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:6413b8b71c3a7e56132f337817bfb146b086289f845423d64793fa36160a2dbd","observation_id":"74e6cc55-efb9-43df-84b0-cec8de714b0c","resolution":{"observed_at":"2026-08-03T08:50:38.156737Z","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":"2026-08-03T08:50:38.315179Z","title":"Normalization matters in zero-shot learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.315179Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:8977931c65a785006d1e405bc8291e58a8fa283e7778d8fb1e5cbfc873af9369","observation_id":"df28430a-33f9-4fce-bd6c-1a380c77a482","resolution":{"observed_at":"2026-08-03T08:50:38.315179Z","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":"2026-08-03T08:50:38.425114Z","title":"Tf- gczsl: Task-free generalized continual zero-shot learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.425114Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:2ffebe61200b06db39816fd93cf989310dc200a77b1309b56ff3ac11eb599289","observation_id":"212bbff8-62f3-4088-af40-24d12ebf78e3","resolution":{"observed_at":"2026-08-03T08:50:38.425114Z","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":"2026-08-03T08:50:38.589316Z","title":"Lifelong zero-shot learning.,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.589316Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:d03b368889d05fefcf70c2cc216e5044ecace7e1c1bb3c23884ec94490c90665","observation_id":"3e908950-7b97-4577-8b60-9c2ecd375d41","resolution":{"observed_at":"2026-08-03T08:50:38.589316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09988","last_updated":"2024-06-10T20:57:14Z","snapshot_observed_at":"2026-07-06T15:55:52.773367Z","submitted_at":"2023-07-19T13:49:12Z","title":"TinyTrain: Resource-Aware Task-Adaptive Sparse Training of DNNs at the Data-Scarce Edge","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09988","snapshot_observed_at":"2026-08-03T08:50:38.755927Z","title":"Tinytrain: Resource-aware task-adaptive sparse training of dnns at the data-scarce edge,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.755927Z"},"links":{"cited_paper":"/paper/2307.09988","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:50a32d7ce8ac647f9ac100d2f5796d974d6fa08f7545616bd0046519b3796ccf","observation_id":"c2c02d54-0503-43a7-819c-851022915b64","resolution":{"observed_at":"2026-08-03T08:50:38.755927Z","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":"2026-08-03T08:50:38.923956Z","title":"Decision transformer: Reinforcement learning via sequence modeling,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:38.923956Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:4e2315ac14eccc334cff98b6908bda3f4fc39f482cb21f196141743d23bb9caa","observation_id":"ad432ecf-b8b6-4226-8246-ff23f9128f4b","resolution":{"observed_at":"2026-08-03T08:50:38.923956Z","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":"2026-08-03T08:50:39.045787Z","title":"Offline reinforcement learning as one big sequence modeling problem,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:39.045787Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:7b2839c7c61d97ec831fdda01f64b9fd53b3ed392fa7377805f3b39094a5f9a6","observation_id":"563ef21f-18d5-49d8-b666-74ecd93d82e1","resolution":{"observed_at":"2026-08-03T08:50:39.045787Z","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":"2026-08-03T08:50:39.202344Z","title":"Learning without feedback: Fixed random learning signals allow for feedforward training of deep neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:39.202344Z"},"links":{"citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:0e769dcd6ca42166d49ade411264ffe0c29295f449f37f56f1e0cba636e7bc2b","observation_id":"d5c44b6d-9163-4979-aa85-e43b93e1ef3b","resolution":{"observed_at":"2026-08-03T08:50:39.202344Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.13345","last_updated":"2022-12-27T02:54:46Z","snapshot_observed_at":"2026-08-08T05:12:54.739479Z","submitted_at":"2022-12-27T02:54:46Z","title":"The Forward-Forward Algorithm: Some Preliminary Investigations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.13345","snapshot_observed_at":"2026-08-03T08:50:39.370097Z","title":"The forward-forward algorithm: Some preliminary investi- gations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T08:50:39.370097Z"},"links":{"cited_paper":"/paper/2212.13345","citing_paper":"/paper/2607.29353"},"observation_digest":"sha256:3076039fa0d08c913e95decea3ed379ef0ed1450776de242f3746f6d5a8b40f6","observation_id":"d24b62a8-aa0e-4035-870c-de597c0a4ead","resolution":{"observed_at":"2026-08-03T08:50:39.370097Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.29353","last_updated":"2026-07-31T12:37:48Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-05T23:13:16.167684Z","submitted_at":"2026-07-31T12:37:48Z","title":"Versatile On-device Adaptation at the Edge by Unifying Few-shot, Zero-shot, Continual, and In-context Learning"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":60,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":60},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2607.29353."}