{"as_of":"2026-08-08T04:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4cc556328da43558c9d8db1c53fedfc7e8745076519e3d586e4664a46324c455","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:19:37.845139Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.24852/citation-record","integrity":"/paper/2505.24852/integrity","json":"/paper/2505.24852/citation-record.json","paper":"/paper/2505.24852"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:44.746683Z","title":"Learn to learn on chip: Hardware-aware meta-learning for quantized few-shot learning at the edge,","venue":null,"work_id":"fb896447-0cc7-43dd-a9e8-29ac90238dad","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.491265Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:9898bc1e6b658f6e1e2dda75574f1b0c3316dd3fdc48d685100c2485b23503ff","observation_id":"1c857ee4-30a1-451c-a23e-e0bdb6371e56","resolution":{"observed_at":"2026-08-07T12:19:44.887456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:44.536463Z","title":"A tinyml platform for on-device continual learning with quantized latent replays,","venue":null,"work_id":"8c58b88d-29b0-457f-9452-e30db71d7423","year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.542384Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:a0a69a82815a3c7fb0097a0791374a904df122fb279d11a28e8efabffdd60acf","observation_id":"df03fb6c-78c2-4dc9-8cc3-515ea54beb77","resolution":{"observed_at":"2026-08-07T12:19:44.644633Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1606.06565","last_updated":"2016-07-25T17:23:29Z","snapshot_observed_at":"2026-07-06T05:00:46.434335Z","submitted_at":"2016-06-21T13:37:05Z","title":"Concrete Problems in AI Safety","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.06565","snapshot_observed_at":"2026-08-07T12:19:33.618139Z","title":"Concrete problems in ai safety","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.618139Z"},"links":{"cited_paper":"/paper/1606.06565","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:250581429fe6c5353ee06443df6e331a3750a71df6605e7e131c27d63cdacd93","observation_id":"56366507-3d25-4686-a2ac-1dfe4805d5ed","resolution":{"observed_at":"2026-08-07T12:19:33.618139Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:44.345765Z","title":"Latent replay for real-time continual learning,","venue":null,"work_id":"ff96dda4-d557-46b4-9165-67d9bce66355","year":2020},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.724272Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:e0251a35820f60dd42ed9376501a57c95fb3d6124bd8a59d5cc805964b616fa7","observation_id":"70bfc458-81aa-4534-9570-6ae347afcf29","resolution":{"observed_at":"2026-08-07T12:19:44.368429Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:44.241191Z","title":"A quantization framework for neural network adaption at the edge,","venue":null,"work_id":"8249e602-da7b-43f6-846b-ecf214856ffb","year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.786201Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:df534d8ee6c34c7e909ca2d5ed62ac704066a4764f2d3053c66d4ccb916a2cb9","observation_id":"e37e1108-7e23-48e9-bcb1-b6ccade64470","resolution":{"observed_at":"2026-08-07T12:19:44.312526Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:44.070795Z","title":"Exploring quantization in few-shot learning,","venue":null,"work_id":"5fbf3ab6-5045-4c35-80c1-7f2439759b6a","year":2020},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.840395Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:0742b3c543c84d2bea0ecbdee1f42474dc767832f0081f04f00d1bfa06f861a9","observation_id":"f50a347f-e39b-4076-8338-474c3866929a","resolution":{"observed_at":"2026-08-07T12:19:44.153755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:43.902353Z","title":"An in-memory computing sram macro for memory-augmented neural network,","venue":null,"work_id":"2e1b71cd-b2b3-4d9b-8474-015b4155718f","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.928353Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:153671971f047af8d2a873141fda61b3d47e8368371b2af5bedee5e029b5a92d","observation_id":"e5045f60-a812-49a7-af99-be355362107b","resolution":{"observed_at":"2026-08-07T12:19:43.982582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:43.766461Z","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":"b5718932-b701-489d-a954-2fa92b135a1b","year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:33.989162Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:bf2e7edbaa88b51a8c7d63cac40f17bbc241b8dce4b5fabd17e164b10f2312c7","observation_id":"9dab63a9-cb6a-4a8b-af84-9cf13fb0d19e","resolution":{"observed_at":"2026-08-07T12:19:43.824930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:43.604527Z","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":"993485ab-5ccd-45d4-86d1-e247c00c5b3d","year":2024},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.065022Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:0b23442d74540b78f226fdcb848b52676ecc781a23b241e16a05c1bc9dda5c13","observation_id":"c1b9afd2-a076-4362-8c9b-d1255346dbf7","resolution":{"observed_at":"2026-08-07T12:19:43.672749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:43.461949Z","title":"V ocell: A 65-nm speech-triggered wake-up soc for 10- µ w keyword spotting and speaker verification,","venue":null,"work_id":"38dd1fbf-530e-4065-9188-a67cbf8f5aa0","year":2020},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.163440Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:76d53e6168a0b711b2bb779a1bfa053df48948b0f00567144a2f3b2fddc6f761","observation_id":"a18edd7d-2763-44b8-b348-88110fc881ea","resolution":{"observed_at":"2026-08-07T12:19:43.542396Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:43.331207Z","title":"Efficient execution of temporal convolutional networks for embedded keyword spotting,","venue":null,"work_id":"51d6d5a1-f3b4-4dd5-846a-08eae78995fa","year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.229510Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:8a921867dea50eeac4d05e0771f542e017ee91f74b5672e7ece267debd8e4ee4","observation_id":"11c04190-1c28-4c01-82ef-ffffd320ee4c","resolution":{"observed_at":"2026-08-07T12:19:43.401047Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:43.195155Z","title":"Tinyvers: A tiny versatile system-on-chip with state-retentive emram for ml inference at the extreme edge,","venue":null,"work_id":"d93cd46c-f429-4440-b20f-f9959379c648","year":2023},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.289490Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:cca088985d64963c2058635fa17bb32733756bdf38ac87ea0bf700575401787d","observation_id":"0f9a6a00-7ba4-4d66-b41e-6e566e24fd6e","resolution":{"observed_at":"2026-08-07T12:19:43.250353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:42.973834Z","title":"Ultratrail: A configurable ultralow-power tc-resnet ai accelerator for efficient keyword spotting,","venue":null,"work_id":"c010adfe-340c-4359-8e85-51c9deb5f560","year":2020},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.347514Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:36c1e4bcea8dcb7f14959b210094e05e0a650a5847a325e925f99c12759481f0","observation_id":"23813bbc-25fd-4795-a002-d8a66aea9ef7","resolution":{"observed_at":"2026-08-07T12:19:43.082803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:42.837331Z","title":"A 23-uw keyword spotting ic with ring-oscillator-based time-domain feature extraction,","venue":null,"work_id":"c37c2ee1-8e2d-463a-99ca-7c8b01eb23aa","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.405115Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:1a5b2737c129468152ffbbd56a8a8fea170cc4679d0f12790dc3c205188e08c0","observation_id":"ca4fe88c-8898-4822-a0bf-1589ea490aff","resolution":{"observed_at":"2026-08-07T12:19:42.896022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:42.703130Z","title":"In-memory realization of in-situ few-shot continual learning with a dynamically evolving explicit memory,","venue":null,"work_id":"94c84169-8c57-45f8-ae24-c935d83d65df","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.493655Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:e6c6fae10cee409592ae98cc5188e917c9ad334f3dc44df05064db09aa362987","observation_id":"e94a1224-6b38-409f-9612-92340b9f3134","resolution":{"observed_at":"2026-08-07T12:19:42.775708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:42.491229Z","title":"Prototypical networks for few- shot learning,","venue":null,"work_id":"1453deaa-802a-4ee7-9928-ac82baa49f5b","year":2017},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.573364Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:2d9a8412388991801a2ae4da1837c1f5697d9178e3c9f34a64caea8017316ed1","observation_id":"5f2f6c15-fef4-46a0-9c87-647ad1e71223","resolution":{"observed_at":"2026-08-07T12:19:42.571835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:42.202375Z","title":"Human-level concept learning through probabilistic program induction,","venue":null,"work_id":"8d25651c-36e0-4c9c-867d-aa6955d91c58","year":2015},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.663219Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:61d5c4e00dd0edef8c1dcfdde95d85348c0e0ad45fc9a0fd9ebd823eae518328","observation_id":"69deb566-5cf5-4861-849b-05466d9e02d6","resolution":{"observed_at":"2026-08-07T12:19:42.331836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"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":"2026-08-07T12:19:34.716102Z","title":"An empirical evaluation of generic convolutional and recurrent networks for sequence modeling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.716102Z"},"links":{"cited_paper":"/paper/1803.01271","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:06fe6bfc2219c330e8659bf56709780ef9bd262901522d3372d3ad171877bd61","observation_id":"1ebce5f9-3bab-4ab1-90d2-b4f578303cac","resolution":{"observed_at":"2026-08-07T12:19:34.716102Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:41.918506Z","title":"Tcn-cutie: A 1,036-top/s/w, 2.72-µj/inference, 12.2-mw all-digital ternary accelerator in 22-nm fdx technology,","venue":null,"work_id":"b9ad2954-8c9a-4ea1-a88e-0c1cf929d399","year":2023},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.769031Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:a2f28bc82136836a1ff477ca2eecfc87854210c13d172003cdf536748713f061","observation_id":"2abbc65a-b38a-4b8e-968c-f2ab37a023e0","resolution":{"observed_at":"2026-08-07T12:19:42.064912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:41.652957Z","title":"Model-agnostic meta-learning for fast adaptation of deep networks,","venue":null,"work_id":"568e0a35-e300-41cc-baec-943e5827c3f1","year":2017},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.831601Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:1e2335c831349db83d6d6ebf4ef515e8a9ec808ecf70f61f2f5c3a76ad6f5968","observation_id":"afbd1501-f4a5-4980-8a85-2adbb7410e7c","resolution":{"observed_at":"2026-08-07T12:19:41.787217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:41.336807Z","title":"Meta- learning in neural networks: A survey,","venue":null,"work_id":"21bdbf69-167d-4653-9e30-14f34a50ec61","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:34.910431Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:5e8c455770507752fc8fe6a8144e38df402a8fcce7c92d46eecd4ef864d70d53","observation_id":"4ce8914a-b538-4077-b60e-17483ab94cbf","resolution":{"observed_at":"2026-08-07T12:19:41.522250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:40.994253Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":"db8cac04-9114-4b2e-a823-46f989ef3a85","year":null},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.000072Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:bf0d7426b4563e5eea2610f1c08ef3ea6f1449e39008d0921cce68d8fe811cdc","observation_id":"f7dfb8c1-f262-4801-b2bd-99ca69748de7","resolution":{"observed_at":"2026-08-07T12:19:41.139888Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.03141","last_updated":"2018-02-25T04:55:20Z","snapshot_observed_at":"2026-07-06T05:50:35.749193Z","submitted_at":"2017-07-11T06:21:31Z","title":"A Simple Neural Attentive Meta-Learner","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.03141","snapshot_observed_at":"2026-08-07T12:19:35.089788Z","title":"A Simple Neural Attentive Meta-Learner","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.089788Z"},"links":{"cited_paper":"/paper/1707.03141","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:e7713f03c887434f47a73ab4b7ca6804ad7ebb2a96151d41067c368d7d8b41fc","observation_id":"6d16b3d6-ae48-44c7-9046-25fab751f06c","resolution":{"observed_at":"2026-08-07T12:19:35.089788Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:40.706595Z","title":"Meta-learning with memory-augmented neural networks,","venue":null,"work_id":"0677a28d-6568-44a4-9c6b-04b683b31d47","year":2016},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.163237Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:2c39e364b60661a08324c3ee18cb2123bafae3dd121cbb991ae87bf64f5ea735","observation_id":"987daeff-1344-4d3e-97df-8872c0f51418","resolution":{"observed_at":"2026-08-07T12:19:40.830232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:40.342438Z","title":"Locality-based encoder and model quantization for efficient hyper- dimensional computing,","venue":null,"work_id":"86823a98-adad-4698-9649-749076ef1826","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.262058Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:df7927f1a12008e6cc0e7ceaa61591d8eac7a9e9a8a0e19e6dcf0ec76a16b8ae","observation_id":"28c6b9c5-f1ae-40c6-bc78-9c9fc780a9ae","resolution":{"observed_at":"2026-08-07T12:19:40.535720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:40.191981Z","title":"Anp-g: A 28-nm 1.04-pj/sop sub-mm2 asynchronous hybrid neural network olfactory processor enabling few-shot class-incremental on- chip learning,","venue":null,"work_id":"18fa6bee-a7c6-4031-8ca9-1d950cf2c379","year":2025},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.341773Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:e837344ca493a100d8b05e3c525425bb8aa5be3356c728510ebccd951de883d9","observation_id":"01ec8ab5-047c-44ef-8ff1-ab441dad9bbf","resolution":{"observed_at":"2026-08-07T12:19:40.259827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:35.424388Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.424388Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:d70021834b6c650e8710cfe3eb65c753322a55150244178d8e1b1ef9921c2ced","observation_id":"e4feb59e-1512-4098-8604-5d4e78964132","resolution":{"observed_at":"2026-08-07T12:19:35.424388Z","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":"2026-08-07T12:19:35.501009Z","title":"Long short-term memory,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.501009Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:17808412a2cb60cf0c89ecfa44b785c45fc18d74613e154d2d459e02774cba67","observation_id":"4957e28c-0d57-4ae3-b7a0-72fc8ebfc5cf","resolution":{"observed_at":"2026-08-07T12:19:35.501009Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1907.05572","last_updated":"2019-07-12T04:01:57Z","snapshot_observed_at":"2026-08-02T01:42:45.538014Z","submitted_at":"2019-07-12T04:01:57Z","title":"R-Transformer: Recurrent Neural Network Enhanced Transformer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.05572","snapshot_observed_at":"2026-08-07T12:19:35.595074Z","title":"R-transformer: Recurrent neural network enhanced transformer","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.595074Z"},"links":{"cited_paper":"/paper/1907.05572","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:12a96c06635dea6f153a18f43961f9ee8c9e56359e43dda0eaceacae62506740","observation_id":"83b322e0-62da-47f4-8afa-3b2a0e284105","resolution":{"observed_at":"2026-08-07T12:19:35.595074Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-08-07T12:19:35.696922Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.696922Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:4dd883a583c227feb669a68125d141cd5a50ac18b931dc25f70e5f8fa6836551","observation_id":"31820cc1-501d-42c5-968b-af6e2c5b2700","resolution":{"observed_at":"2026-08-07T12:19:35.696922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.01025","last_updated":"2016-03-17T03:32:30Z","snapshot_observed_at":"2026-07-06T04:48:11.215166Z","submitted_at":"2016-03-03T08:51:52Z","title":"Convolutional Neural Networks using Logarithmic Data Representation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1603.01025","snapshot_observed_at":"2026-08-07T12:19:35.769092Z","title":"Convolutional neural net- works using logarithmic data representation","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.769092Z"},"links":{"cited_paper":"/paper/1603.01025","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:8b84a244c87291ad863b50a2c5200007f989b9e66660a4ea63609e811831824c","observation_id":"e3ddaa35-4952-4be9-81cb-8cff9a1fa557","resolution":{"observed_at":"2026-08-07T12:19:35.769092Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.05025","last_updated":"2022-03-09T19:57:14Z","snapshot_observed_at":"2026-07-06T12:46:12.270140Z","submitted_at":"2022-03-09T19:57:14Z","title":"Power-of-Two Quantization for Low Bitwidth and Hardware Compliant Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.05025","snapshot_observed_at":"2026-08-07T12:19:35.866132Z","title":"Power-of-two quantization for low bitwidth and hardware compliant neural networks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.866132Z"},"links":{"cited_paper":"/paper/2203.05025","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:65982cfe403ea5a98ced0ff0eea883aea0eca00ce3382fa83a6d838146506df8","observation_id":"a0f24342-db3b-4382-9cef-3d8ef37ec080","resolution":{"observed_at":"2026-08-07T12:19:35.866132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1502.03167","last_updated":"2015-03-02T20:44:12Z","snapshot_observed_at":"2026-07-06T04:08:54.419941Z","submitted_at":"2015-02-11T01:44:18Z","title":"Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1502.03167","snapshot_observed_at":"2026-08-07T12:19:35.957370Z","title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:35.957370Z"},"links":{"cited_paper":"/paper/1502.03167","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:930fe0032085ecd60b706230c3ba957b58530c12a09f783145ec37a776105ff1","observation_id":"92a31021-6b9e-4d89-b9ac-49a87063e9af","resolution":{"observed_at":"2026-08-07T12:19:35.957370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:40.046523Z","title":"Accurate, large minibatch sgd: Training imagenet in 1 hour","venue":null,"work_id":"ee8d33f1-19f5-4ff5-a478-93bb06fba1f9","year":null},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.051700Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:97ad6bd9592cb0880946c6fd1291d795bacc0da713928bfcaeaf9c4ffbc6f352","observation_id":"f69cde1d-7d21-4b81-931f-4cad51f45446","resolution":{"observed_at":"2026-08-07T12:19:40.093525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.903486Z","title":"Delving deep into rectifiers: Sur- passing human-level performance on imagenet classification,","venue":null,"work_id":"71d58bc9-b70e-404c-ba9f-fb0d2b34fa89","year":2015},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.109844Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:649a056081ca08f4d5c410eae1b021e78b1f401df112752edf42aa0eb89caf5c","observation_id":"29aa772c-acc0-4842-835b-d6c44656cc3e","resolution":{"observed_at":"2026-08-07T12:19:39.967609Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.759916Z","title":"Pappalardo","venue":null,"work_id":"15ba35d1-6ef4-4d65-9e96-bd30c3d44d0e","year":2023},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.166370Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:9b505b62db3b106dad43224db44b5ae6609cce7655cfb308edf555ca451f45a8","observation_id":"d16916b8-cc5f-40b7-90e1-e25fdcc32bbe","resolution":{"observed_at":"2026-08-07T12:19:39.812682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1806.08342","last_updated":"2018-06-21T17:32:46Z","snapshot_observed_at":"2026-07-06T06:46:08.396066Z","submitted_at":"2018-06-21T17:32:46Z","title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.08342","snapshot_observed_at":"2026-08-07T12:19:36.267470Z","title":"Quantizing deep convolutional networks for effi- cient inference: A whitepaper","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.267470Z"},"links":{"cited_paper":"/paper/1806.08342","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:e9a854ae4166e56bfbc400d14808d7b0a6279f3e24a4555ed6c1e1fa9b612c9a","observation_id":"eff2edb7-76a6-4050-bda3-3b5bc9e576db","resolution":{"observed_at":"2026-08-07T12:19:36.267470Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.624347Z","title":"Quantization and training of neural networks for efficient integer-arithmetic-only inference,","venue":null,"work_id":"64573e42-75ec-47d0-85a8-5f9b11e33736","year":2018},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.382096Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:e408e001b47591cab0bd9c69a6f3ef361116856759473917ea64fa431256eeb4","observation_id":"75740e46-c17e-48ed-a417-9251e95b84bd","resolution":{"observed_at":"2026-08-07T12:19:39.661893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.08295","last_updated":"2021-06-15T17:12:42Z","snapshot_observed_at":"2026-08-02T11:19:40.664702Z","submitted_at":"2021-06-15T17:12:42Z","title":"A White Paper on Neural Network Quantization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.08295","snapshot_observed_at":"2026-08-07T12:19:36.494989Z","title":"A white paper on neural network quan- tization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.494989Z"},"links":{"cited_paper":"/paper/2106.08295","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:a387120777b7d443861bb412740f95939c28da4ee70fd612d9a20f3800792a76","observation_id":"c47d9990-4fa3-4256-91a2-f765408d85a0","resolution":{"observed_at":"2026-08-07T12:19:36.494989Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.481935Z","title":"Matching networks for one shot learning,","venue":null,"work_id":"eae4703f-cbcb-454b-96a3-2539ec6f658c","year":2016},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.562708Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:2aa754085c1be70e7f4b3083bd1c3102cc7199c9d0e1a0fcd8ae1ade74db4131","observation_id":"97b2d6fd-c647-44ca-8c50-d15922ce4727","resolution":{"observed_at":"2026-08-07T12:19:39.542623Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.362010Z","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":"d815ff48-ed21-4457-9114-d5cd106f36d6","year":2022},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.653125Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:16a3c14e1ee28b59622bacfe51a64b78e4cb954d9f7a4bd45a2901161a951a9f","observation_id":"0f545c93-5ea0-4914-a8ae-184b82c58348","resolution":{"observed_at":"2026-08-07T12:19:39.417841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.273104Z","title":"9.3 a 40nm 4.81tflops/w 8b floating- point training processor for non-sparse neural networks using shared exponent bias and 24-way fused multiply-add tree,","venue":null,"work_id":"51dea1a7-3565-4cc5-bc85-5fd79a05c8be","year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.717163Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:2f0b78dcb1aacbb31f1b8b32b6c27066ed9a916b452fb2f70850001ba6dfd402","observation_id":"061c1790-e3f0-4b47-8d0d-cdd018ca6b96","resolution":{"observed_at":"2026-08-07T12:19:39.321871Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.07802","last_updated":"2024-03-12T16:41:31Z","snapshot_observed_at":"2026-08-06T02:48:09.333288Z","submitted_at":"2024-03-12T16:41:31Z","title":"Boosting keyword spotting through on-device learnable user speech characteristics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.07802","snapshot_observed_at":"2026-08-07T12:19:36.818186Z","title":"Boosting keyword spot- ting through on-device learnable user speech characteristics","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.818186Z"},"links":{"cited_paper":"/paper/2403.07802","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:c4659aa658c03aeb1320d580e80402a6cf2c9b962cd35282141287b3fcff71f6","observation_id":"c7a8242d-c406-4708-8df2-95f125021bc5","resolution":{"observed_at":"2026-08-07T12:19:36.818186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.141958Z","title":"Few- shot class-incremental learning,","venue":null,"work_id":"1ae1e402-3756-4520-9d76-7c29576eef8e","year":2020},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.898341Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:8b75cb9796ad4530cca42d928f964f5896948d28ad071608fc73dacb5883e50c","observation_id":"a2980144-cb72-4c84-b7cc-7be298074472","resolution":{"observed_at":"2026-08-07T12:19:39.192734Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:39.026281Z","title":"12 mj per class on-device online few-shot class-incremental learning,","venue":null,"work_id":"1f86cd01-ab0f-42a5-88f7-5bf1a86f4130","year":2024},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:36.992198Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:0f49ac57ae79551d17fa452fc2286f8856464f8d04d9e84021c093394fc245e7","observation_id":"8720425a-54ba-4cf9-a70d-3ff602d53ccc","resolution":{"observed_at":"2026-08-07T12:19:39.079056Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-07-06T06:32:32.083176Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-07T12:19:37.067992Z","title":"Speech commands: A dataset for limited-vocabulary speech recognition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.067992Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:5aa9df7cfcb184defd064b21c8da93b2278349415de0fb68a08bf3727a044f8a","observation_id":"f885428e-03fa-4912-ad77-59fbe17cfd88","resolution":{"observed_at":"2026-08-07T12:19:37.067992Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2005.06720","last_updated":"2020-07-29T01:53:16Z","snapshot_observed_at":"2026-08-07T13:50:20.304437Z","submitted_at":"2020-05-14T05:05:22Z","title":"Streaming keyword spotting on mobile devices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.06720","snapshot_observed_at":"2026-08-07T12:19:37.163917Z","title":"Streaming keyword spotting on mobile devices","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.163917Z"},"links":{"cited_paper":"/paper/2005.06720","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:7afb3ec4084f60c51ddff608a99a8651e16b5a25338f555d42adc7320241a45b","observation_id":"58a57763-fa72-4be4-b299-6f936abbeef3","resolution":{"observed_at":"2026-08-07T12:19:37.163917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.07128","last_updated":"2018-02-14T19:24:55Z","snapshot_observed_at":"2026-07-06T06:10:16.792443Z","submitted_at":"2017-11-20T03:19:03Z","title":"Hello Edge: Keyword Spotting on Microcontrollers","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.07128","snapshot_observed_at":"2026-08-07T12:19:37.275917Z","title":"Hello edge: Keyword spotting on microcontrollers","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.275917Z"},"links":{"cited_paper":"/paper/1711.07128","citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:40cc18ead89c8607ea7fbb682902d06303888ae9987afb5f275cb9853927c5d1","observation_id":"e867b4f9-de64-4fa3-a12f-34bc17fb7020","resolution":{"observed_at":"2026-08-07T12:19:37.275917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:38.911500Z","title":"Comparison of parametric represen- tations for monosyllabic word recognition in continuously spoken sentences,","venue":null,"work_id":"9d43603f-3612-408d-9c21-61f4b41c679c","year":1980},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.397707Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:cb6bd6a4e670896311d46f07d1cfb310f9b713cb2749ed4974e99f9b03ceb55d","observation_id":"adcebaeb-b794-45d8-9630-badafec98c4a","resolution":{"observed_at":"2026-08-07T12:19:38.950318Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:38.770514Z","title":"A 510-nw wake-up keyword-spotting chip using serial-fft-based mfcc and binarized depthwise separable cnn in 28-nm cmos,","venue":null,"work_id":"7ae6b974-89ad-433b-a66c-5e289d74ff44","year":2021},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.508775Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:855bdb52cb6b8840df683452f7041da316bcbcaadeeb4dd53632eaa870d092a1","observation_id":"b6722017-655d-4f81-a641-28fb730ae387","resolution":{"observed_at":"2026-08-07T12:19:38.838997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:38.665376Z","title":"A 22nm, 10.8 uw/15.1 uw dual computing modes high power-performance-area efficiency domained background noise aware keyword- spotting processor,","venue":null,"work_id":"cd4d2e0b-65ec-4af3-bcf7-a3323bc20bd2","year":null},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.605741Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:b293ee1b4a1d46a26251a4f5d70aa4391c3a3425fef702c91444636f27b8ebd9","observation_id":"3d4d99f8-e747-4826-b875-248a3894ed17","resolution":{"observed_at":"2026-08-07T12:19:38.717614Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:38.473378Z","title":"Tan, W.-H","venue":null,"work_id":"c366a186-9db1-4cc7-83a6-cc4316a98f23","year":2025},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.684501Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:cdacc537a69f2ec2d35124591faaa840fa948de06103b1badef62dfddb1a5035","observation_id":"358736b8-8fc2-4249-b5e0-a35358e30667","resolution":{"observed_at":"2026-08-07T12:19:38.568070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:38.079483Z","title":null,"venue":null,"work_id":"ee85e627-14d7-4717-86ba-46b2c9b8349d","year":2023},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.845139Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:181a8b430c45fe9d2e612a0c0e311222e343152dc048db9bad9a9cd2020d4378","observation_id":"f4051205-4388-4362-8713-44502289638b","resolution":{"observed_at":"2026-08-07T12:19:38.156730Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:19:38.257830Z","title":"She presented several invited talks, including keynotes at the tinyML EMEA technical forum 2021 and at the Neuro-Inspired Computational Elements (NICE) neuromorphic conference","venue":null,"work_id":"03fc8b10-7675-4e65-bb99-8905940d9b65","year":2023},"citing_paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data","version":3},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T12:19:37.777550Z"},"links":{"citing_paper":"/paper/2505.24852"},"observation_digest":"sha256:d27b0ca6ace5652091078033925ba89db750d32637790ca12fce1c3a5e32198d","observation_id":"437b14bb-8a1f-435e-9689-4d5ee658f9eb","resolution":{"observed_at":"2026-08-07T12:19:38.363141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.24852","last_updated":"2026-07-19T08:09:35Z","latest_version":3,"primary_category":"cs.AR","snapshot_observed_at":"2026-08-07T19:00:11.575070Z","submitted_at":"2025-05-30T17:49:30Z","title":"Chameleon: A Multiplier-Free Temporal Convolutional Network Accelerator for End-to-End Few-Shot and Continual Learning from Sequential Data"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":0,"verified_fuzzy":36},"total_outbound_references":54},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2505.24852."}