{"as_of":"2026-08-20T14:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:265404023dbc8f8411d5160c6349577e1677a6f665366d137ca00b6a3cca3b37","coverage":[{"denominator":28,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":28,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T16:07:54.254144Z","state":"measured"},{"denominator":28,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":28,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2607.18101/citation-record","integrity":"/paper/2607.18101/integrity","json":"/paper/2607.18101/citation-record.json","paper":"/paper/2607.18101"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T16:07:54.192519Z","title":"et al.: Fastvit: A fast hybrid vision trans- former using structural reparameterization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.192519Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:882474724da970f5e42519c6068794ac0fc633da64abbd52c41601617e640678","observation_id":"fc70e575-a139-440b-a1d1-8230d34eaaa7","resolution":{"observed_at":"2026-08-01T16:07:54.192519Z","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":"2026-08-01T16:07:54.195740Z","title":"et al.: Enabling on-device smartphone gpu based training: Lessons learned","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.195740Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:d373593cab1bc35ceee5912ddf07bf6709819e6398f034ae7cb308d76f93b4ef","observation_id":"2a96c89f-f09b-4f65-94d6-931131dac257","resolution":{"observed_at":"2026-08-01T16:07:54.195740Z","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":"2026-08-01T16:07:54.198020Z","title":"et al.: Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.198020Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:944232d4616047a6792fed62a6c2e33b8d06da13fb78e7dea034140dd13f90a3","observation_id":"d49e57dd-a2a9-40af-bf84-5014ab420765","resolution":{"observed_at":"2026-08-01T16:07:54.198020Z","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":"10.1007/978-3-031-25082-8_8","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"et al.: Qft: Post-training quantization via fast joint finetuning of all degrees of freedom","venue":"Lecture notes in computer science","work_id":"00cdbb80-c862-4b00-b6a1-ca9eca65f0e0","year":2022},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.200210Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:58eb42a211cfd3a3c1f6fa198d31830004ec53b8fd9d1ec3f5f44e4b7093c5f2","observation_id":"3ce33609-d7c6-405b-afc6-fdde4ddf60b6","resolution":{"observed_at":"2026-08-01T16:09:09.932487Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.03193","last_updated":"2019-06-07T16:00:35Z","snapshot_observed_at":"2026-08-14T16:19:08.012868Z","submitted_at":"2019-06-07T16:00:35Z","title":"Fighting Quantization Bias With Bias","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.03193","snapshot_observed_at":"2026-08-01T16:07:54.202817Z","title":"arXiv preprint arXiv:1906.03193 (2019)","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.202817Z"},"links":{"cited_paper":"/paper/1906.03193","citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:5a316afd874000b8bb31f6211dd68e14b77f59ed32116ec45bb9b6bdca46a41c","observation_id":"5635df39-5f23-4baa-83a0-03e553d8b4cf","resolution":{"observed_at":"2026-08-01T16:07:54.202817Z","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":"2026-08-01T16:07:54.208233Z","title":"Accessed: 31-05-2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.208233Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:5b8abff86d442131c48944a0ed59503bbd20494c1dc19be69a5b87a72e5db81e","observation_id":"92c8f4c3-19af-4726-9f47-fe6da5860f24","resolution":{"observed_at":"2026-08-01T16:07:54.208233Z","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":"2026-08-01T16:07:54.210231Z","title":"4.23.0,https://hailo.ai, [Online]","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.210231Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:55b7bfb51bb78c563272bd75bf48e8dcda68900d05de798ca18334ab2224223d","observation_id":"ad4964b0-3b7d-4c72-9d97-cfa3157f28f8","resolution":{"observed_at":"2026-08-01T16:07:54.210231Z","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":"2026-08-01T16:07:54.212216Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.212216Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:06fbe6d76f856fcece1f2217c5cceb60a3ed1edf71ee4a5ee4d94680f7bbe419","observation_id":"9b2c1486-7cae-4211-bcd5-c69c4ab048a5","resolution":{"observed_at":"2026-08-01T16:07:54.212216Z","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":"2026-08-01T16:07:54.214090Z","title":"et al.: Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.214090Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:75faf736c0e8766b4df7d73d1fd77881d49dd55cb1f409e00955189135cd7890","observation_id":"8ee23467-aafe-4944-95d0-1d9f61a70815","resolution":{"observed_at":"2026-08-01T16:07:54.214090Z","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":"2026-08-01T16:07:54.216562Z","title":"et al.: Searching for mobilenetv3","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.216562Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:71651509220d1abc2ea7d78fbee64dc7357406ef99ccb45c226b41b8762378a1","observation_id":"1b1053fb-2afc-4cfd-b218-1b50b7a0dc46","resolution":{"observed_at":"2026-08-01T16:07:54.216562Z","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":"10.1007/978-3-032-19099-4_11","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"et al.: On-device learning for human activity recogni- tion on low-power microcontrollers","venue":"Communications in computer and information science","work_id":"5f1bffb9-0131-4cbf-ba7e-14782e03306b","year":2026},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.218954Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:f55e5f2b8a93c5b435351f81a7cbc904dfdafa9de454c95b2262edb4ffa3ac27","observation_id":"0a0dc78f-a5e9-4999-92e3-a89bb5c60bc6","resolution":{"observed_at":"2026-08-01T16:09:09.894110Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-01T16:07:54.221322Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.221322Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:807d655cbd3a4008bd826639fdc88f5f3fc1bf9fab77b99bc79c4d6d2a63567f","observation_id":"be1c418e-ad08-4dd9-b6bf-e62ea779fd2b","resolution":{"observed_at":"2026-08-01T16:07:54.221322Z","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":"2026-08-01T16:07:54.223119Z","title":"et al.: On-device training under 256kb memory","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.223119Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:0cd5da3c109fba0f3bea0484badb0c571933285127d252ad36c517633605b6e4","observation_id":"f148a37a-d497-40a4-8c8b-c77d38a2106f","resolution":{"observed_at":"2026-08-01T16:07:54.223119Z","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":"2026-08-01T16:07:54.225139Z","title":"et al.: Same, same but different: Recovering neural network quantiza- tion error through weight factorization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.225139Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:6a1fc6f5b0e4dccfafaa7541c4fd2b993f0b7513f5395d5070bec9fc8ba54632","observation_id":"6c94f586-3ca2-4452-ad37-d1f4cdaa8afc","resolution":{"observed_at":"2026-08-01T16:07:54.225139Z","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":"2026-08-01T16:07:54.227240Z","title":"1.22.1-hailo,https://github.com/MatPiech/onnxruntime, [Online]","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.227240Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:eae5f4b9694db149f4edb9e3fa123458a7bffa7f43df9845cac493fd7ba351c0","observation_id":"b77d8957-e3c8-455d-b337-6d6d6da16966","resolution":{"observed_at":"2026-08-01T16:07:54.227240Z","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":"2026-08-01T16:07:54.229443Z","title":"et al.: Up or down? adaptive rounding for post-training quantization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.229443Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:e6f61254f804cfc839e71fe0a5e5716578cd18a930f96052bb30c3636762f2af","observation_id":"6964e717-2311-4104-aacc-ab7f16984235","resolution":{"observed_at":"2026-08-01T16:07:54.229443Z","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":"2026-08-01T16:07:54.231354Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.231354Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:a4f93c63ea1a6065e10a19fad34cef263de13de52eb91e8942d7de0cd05477cc","observation_id":"f816a82d-39d2-4313-a674-600149d8d3ee","resolution":{"observed_at":"2026-08-01T16:07:54.231354Z","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":"2026-08-01T16:07:54.233236Z","title":"et al.: Cats and dogs","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.233236Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:fedbdf6633f53657df92d5664ef3aaecf4dbda26f6629f467e096d4e81e6a229","observation_id":"b1823284-e28b-4497-94d3-9c9ed4ebe9ce","resolution":{"observed_at":"2026-08-01T16:07:54.233236Z","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":"10.1007/978-3-032-07343-3_28","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"In: Advanced Concepts for Intelligent Vision Systems","venue":"Lecture notes in computer science","work_id":"11e83191-c071-4f30-98ea-04a8b55f9cf5","year":2026},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.235502Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:4c8f760ea08c8bdb494c198d2f217c03b02058a892f0937217e729ac36632baa","observation_id":"2ab3174f-6e62-46c9-82dd-1eabf8d18dfe","resolution":{"observed_at":"2026-08-01T16:09:02.580519Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-01T16:07:54.238179Z","title":"et al.: Computationally budgeted continual learning: What does mat- ter? In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.238179Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:fa89a0528311e375a4c09660fc71dede81ba087ada5c892f43597700720fc6b8","observation_id":"cac4397a-b1bd-4747-bf63-fa7fc83fed86","resolution":{"observed_at":"2026-08-01T16:07:54.238179Z","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":"2026-08-01T16:07:54.240088Z","title":"Journal of King Saud University - Computer and Information Sciences34(4), 1595–1623 (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.240088Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:c8c414bdb4c7b96b6694b3228031db474c8cd1b35d137fd745e7a8b6313cb776","observation_id":"aa4de020-45e4-476b-b46f-3a1f7a289d92","resolution":{"observed_at":"2026-08-01T16:07:54.240088Z","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":"2026-08-01T16:07:54.242096Z","title":"In: Chaudhuri, K., Salakhutdinov, R","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.242096Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:5eb12f222fa1baca1b82239a1ad3235675af56bae97f57822969423c6483b80d","observation_id":"8ca8d7dd-4655-4ea8-887e-fc1485a55e77","resolution":{"observed_at":"2026-08-01T16:07:54.242096Z","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":"2026-08-01T16:07:54.244040Z","title":"et al.: Hardware-accelerated on-device learning: Training, parti- tioning, and compilation for constrained edge ai","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.244040Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:4624e1ea62fc7826bf15995c46a4a44283cccf28e2b0d5705aaeee5c92b214ca","observation_id":"8cbd0091-4a6d-4b41-9bc3-97855690d3bf","resolution":{"observed_at":"2026-08-01T16:07:54.244040Z","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":"2026-08-01T16:07:54.246216Z","title":"et al.: Continual learning: Applications and the road forward","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.246216Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:5076b96292571d0edaad51848573b3956cff4c89006cd5e163bdbcfa84f0cc0c","observation_id":"2b8299ba-d08c-4aea-9b28-02865f2b7b8f","resolution":{"observed_at":"2026-08-01T16:07:54.246216Z","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":"2026-08-01T16:07:54.248187Z","title":"et al.: A comprehensive survey of continual learning: Theory, method and application","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.248187Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:92314b4e21dd256b90338091c9cac243edaf59e62ff75bc73bb7e45bf97113b2","observation_id":"5f90d4c5-7929-4651-b754-b07dd9d505b4","resolution":{"observed_at":"2026-08-01T16:07:54.248187Z","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":"2026-08-01T16:07:54.250056Z","title":"https://doi.org/10.5281/zenodo.4414861","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.250056Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:cc4f76204db5c05439cb567d0ac45dc854d59d5ddd684125aec14e64c42c03be","observation_id":"e50c1002-0e0a-40f7-924b-c8f8e103075c","resolution":{"observed_at":"2026-08-01T16:07:54.250056Z","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":"2026-08-01T16:07:54.252182Z","title":"IEEE Transactions on Network Science and Engineering13, 6571–6588 (2026)","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.252182Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:2420872240b9a9be0dc7d4cb4eec81d5df95fa1ff3601718e8bfe886b60f960b","observation_id":"e0af608d-539e-4ee0-b110-459c6ddf5304","resolution":{"observed_at":"2026-08-01T16:07:54.252182Z","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":"10.1145/3696003","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"et al.: On-device training: A first overview on existing systems","venue":"ACM Transactions on Sensor Networks","work_id":"2654c9fe-2f63-416e-9849-9d7ac249610d","year":2024},"citing_paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T16:07:54.254144Z"},"links":{"citing_paper":"/paper/2607.18101"},"observation_digest":"sha256:579511a5b9a38585f2e60a182516b2b19df458138d30f1f2e79aa777cc8bc766","observation_id":"b9b36059-f950-4119-b33a-fb5c6c4f62d6","resolution":{"observed_at":"2026-08-01T16:09:02.533467Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2607.18101","last_updated":"2026-07-20T16:02:58Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T22:42:40.727710Z","submitted_at":"2026-07-20T16:02:58Z","title":"Empowering On-Device Model Adaptation with an Edge AI Inference Accelerator"},"reference_resolution":{"displayed":28,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":4,"verified_fuzzy":0},"total_outbound_references":28},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 28 of 28 outbound references and 0 inbound Pith citation observations for arXiv:2607.18101."}