{"as_of":"2026-08-20T15:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c27d1b3503cc943b865743b941788e9c08b3bcb17a52665591c9a2463677715d","coverage":[{"denominator":33,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":33,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T21:02:50.434091Z","state":"measured"},{"denominator":33,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":33,"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/2505.11067/citation-record","integrity":"/paper/2505.11067/integrity","json":"/paper/2505.11067/citation-record.json","paper":"/paper/2505.11067"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.835883Z","title":"A survey on deep transfer learning,","venue":null,"work_id":"9fa29a15-c1d5-4611-9912-f1cc3cb6231d","year":2018},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.313049Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:e789863e762ec062cad4821966c6543a0e3ca12b6bf62adacc0f62e0d53810ee","observation_id":"a69b4599-9ce3-45a4-906a-ed2097951e80","resolution":{"observed_at":"2026-08-15T21:02:50.839916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2108.07258","last_updated":"2022-07-12T23:45:14Z","snapshot_observed_at":"2026-08-02T09:20:40.804790Z","submitted_at":"2021-08-16T17:50:08Z","title":"On the Opportunities and Risks of Foundation Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.07258","snapshot_observed_at":"2026-08-15T21:02:50.317351Z","title":"On the opportunities and risks of foundation models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.317351Z"},"links":{"cited_paper":"/paper/2108.07258","citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:cd1fb3a8c2b6a1aeeed204cff9eff22e2eebb487e1521c9fcc4ad58c7b5f6676","observation_id":"d1f9949c-5fec-49f1-bb4f-9f287430017b","resolution":{"observed_at":"2026-08-15T21:02:50.317351Z","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":"2026-08-15T21:02:50.321237Z","title":"Detecting llm-generated text in computing education: Comparative study for chatgpt cases,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.321237Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:68cf0a0e5d9ce3780ff8c1b631a993124c08cf8737802b3c5ec803810fdf894e","observation_id":"1ccbcc16-ceb3-49a7-8b0c-5d3733df6078","resolution":{"observed_at":"2026-08-15T21:02:50.321237Z","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":"2026-08-15T21:02:50.325022Z","title":"Large language models in medicine,","venue":null,"work_id":null,"year":1930},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.325022Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:23c49143456aef659ddc87455d80a816cbf25dc9d6fb98b0ea760b4c9df58f47","observation_id":"15939338-3018-4275-875f-0906319a236d","resolution":{"observed_at":"2026-08-15T21:02:50.325022Z","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":"2026-08-15T21:02:50.805938Z","title":"Driving with llms: Fusing object- level vector modality for explainable autonomous driving,","venue":null,"work_id":"1da81f24-c723-4f2f-ac0f-b540d9b87c31","year":2024},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.329250Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:caf25671d64066ab2c8c15f77177e2d3e79becd6c01fd5a79784b861f419cf52","observation_id":"2c445950-f482-43d5-93d4-27e79d3cecbe","resolution":{"observed_at":"2026-08-15T21:02:50.810475Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.791466Z","title":"Large language models in finance: A survey,","venue":null,"work_id":"56cadd7d-2775-479a-9edc-98b85e72df50","year":2023},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.334560Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:32bd39b7802b7acd785f77a8f28f22a199877abecd55d52a2c4002ab241b8623","observation_id":"007a1a66-e15c-4d2b-a3f1-ccabee024bb4","resolution":{"observed_at":"2026-08-15T21:02:50.796838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2206.07682","last_updated":"2022-10-26T05:06:24Z","snapshot_observed_at":"2026-08-17T00:14:01.413100Z","submitted_at":"2022-06-15T17:32:01Z","title":"Emergent Abilities of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.07682","snapshot_observed_at":"2026-08-15T21:02:50.339173Z","title":"Emergent abilities of large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.339173Z"},"links":{"cited_paper":"/paper/2206.07682","citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9433f75be7199a7bee5d5fe1f5755c8648c1eeb949ac7e82e91d333adcd86b63","observation_id":"2d3ad8a2-7ce0-4c74-8b15-e58d1260574c","resolution":{"observed_at":"2026-08-15T21:02:50.339173Z","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":"2026-08-15T21:02:50.778251Z","title":"A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations,","venue":null,"work_id":"ae7a7755-6277-4d11-b62c-45c0fd6461b5","year":2023},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.343535Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:95d75c583c57ef3be477fc7a68b5cea003eedbcbec7fbe9abbe8f40a52f096b0","observation_id":"41855a3f-9791-4eb2-a92a-955c8b99bd9d","resolution":{"observed_at":"2026-08-15T21:02:50.782538Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2306.13549","last_updated":"2024-11-29T15:51:23Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-23T15:21:52Z","title":"A Survey on Multimodal Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.13549","snapshot_observed_at":"2026-08-15T21:02:50.346778Z","title":"A survey on multimodal large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.346778Z"},"links":{"cited_paper":"/paper/2306.13549","citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:59c653c90ee7126cef6a94938a5ff0dcfaec28ba358b0c1a519ae40c74edd1c2","observation_id":"6948e19e-f85c-48cf-a645-9753148b22f9","resolution":{"observed_at":"2026-08-15T21:02:50.346778Z","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":"2026-08-15T21:02:50.350127Z","title":"A joint energy and latency framework for transfer learning over 5g industrial edge networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.350127Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:509bc6e215d6ac6341ea997b404dd8820e598781cc3287bfcb5b531a9dafd436","observation_id":"84081f6b-96a0-40cb-ab20-c42802b16cb1","resolution":{"observed_at":"2026-08-15T21:02:50.350127Z","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":"2026-08-15T21:02:50.758465Z","title":"Efficient privacy preserving edge intelligent computing framework for image classifica- tion in iot,","venue":null,"work_id":"0fb69ea4-745f-4364-b3f1-ea73bff88b86","year":2021},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.353131Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9a851bc5c930c153bfd1bf1e3b9c03f70f4b59a0bb3eb5746c2abe596706dfb9","observation_id":"ba90216a-4efc-4e30-ba6e-299c4ca48a43","resolution":{"observed_at":"2026-08-15T21:02:50.762167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.746064Z","title":"Demonstration of transfer learning using 14 nm technology analog reram array,","venue":null,"work_id":"496f9d62-45ff-43a2-a793-18bc8e9a7654","year":2024},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.356048Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:006c9b32f6213545c1628989976dba2e6e9d0449638ea6f521f5a8a58adce3fc","observation_id":"fd8a3b3d-4d08-422a-802f-65a8ce40c552","resolution":{"observed_at":"2026-08-15T21:02:50.750235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.734046Z","title":"Ohm’s law + kirchhoff’s current law = better ai: Neural-network processing done in memory with analog circuits will save energy,","venue":null,"work_id":"ed27aa52-6755-4eb6-8413-cdbb1bca0c01","year":2021},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.359063Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:f71e2411c634dcb843ce997ee9a03df15b2d0c2a5cbed0c3ad91e353dba0882a","observation_id":"f608c18e-c386-4e61-a98e-02194bbce223","resolution":{"observed_at":"2026-08-15T21:02:50.738052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.721399Z","title":"A heterogeneous and programmable compute-in-memory accelerator architecture for analog-ai using dense 2-d mesh,","venue":null,"work_id":"475a9f11-d72d-4f46-aed8-1f02195aa906","year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.362167Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9529f3b6f38ffdae14d679c4a815900a004e90b6ed8d5cc5a2ea56b628edbc82","observation_id":"d9620d05-6414-409f-8350-2fd229061867","resolution":{"observed_at":"2026-08-15T21:02:50.725822Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.708982Z","title":"Bottom-up and top-down ap- proaches for the design of neuromorphic processing systems: tradeoffs and synergies between natural and artificial intelligence,","venue":null,"work_id":"928f3b26-466d-45f6-b836-b9083d39deb5","year":2023},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.365853Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:995c6a2a17f61779c27907489eb219cedf9bcd6f7c11982c5821dfe1ccc03510","observation_id":"490d77d0-4b7a-47d5-9b40-2856da20ded6","resolution":{"observed_at":"2026-08-15T21:02:50.713489Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.697616Z","title":"Computational phase- change memory: Beyond von neumann computing,","venue":null,"work_id":"902b5b9e-45b2-4370-bdad-e46c38b08d31","year":2019},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.369193Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9ca7524168a45efe61963cccd9e8082bb87ddc900420d230f6fc2c7018269017","observation_id":"f8af0513-8dfc-43e6-83b9-48b73a036c29","resolution":{"observed_at":"2026-08-15T21:02:50.701575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.685943Z","title":"Using the ibm analog in-memory hardware acceleration kit for neural network training and inference,","venue":null,"work_id":"fa2cb64d-a676-4bed-935f-d49501561985","year":2023},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.372720Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:77c8e0d6e0ad3c77a2f54c4dfadab5392c5d3fab6ef80c37c2b692ccf2f020d5","observation_id":"03932fc3-9292-407d-b6a0-5d3b6c641af6","resolution":{"observed_at":"2026-08-15T21:02:50.689683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.673633Z","title":"Analog-memory- based 14nm hardware accelerator for dense deep neural networks includ- ing transformers,","venue":null,"work_id":"2df1572c-587f-4a33-b32e-24462a5cf957","year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.376434Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9afb5f01055e0464736bcd866c9a1b4cd545e84310b9e7c31596e5c843976c00","observation_id":"08ffd413-24f4-4273-8004-a1f97430cc87","resolution":{"observed_at":"2026-08-15T21:02:50.678198Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.662745Z","title":"Impact of asymmetric weight update on neural network training with tiki-taka algorithm,","venue":null,"work_id":"23f7eb6d-83ac-44e2-a0a2-8b22286b77d8","year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.380052Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:444ed24380d9eaa3e179495632051ac7928aaffce52fa113cf721ce84cf303c2","observation_id":"b7f6b22a-ab39-4e50-82cf-8812716b6f7d","resolution":{"observed_at":"2026-08-15T21:02:50.666108Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.652835Z","title":"Fast and robust analog in-memory deep neural network training,","venue":null,"work_id":"24778aa2-28fa-48c7-b934-107479c9bc7b","year":2024},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.383573Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:781a5098488fcd0cc5b0a70e597f17fecb4a298401fcb60d2d562e79e12a891a","observation_id":"5636ed93-3f72-4a59-b970-e41b1de76b4c","resolution":{"observed_at":"2026-08-15T21:02:50.656185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.641601Z","title":"Neural network learning using non-ideal resistive memory devices,","venue":null,"work_id":"99a40ad4-5c1c-457e-a143-745d81b16c29","year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.386989Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:7a34aacf52be577eb77e37cb3771999a690249c6ea4ffc8782950d7b0ee24f53","observation_id":"9ccd18b1-0f5f-43f1-aae4-34a6963e310a","resolution":{"observed_at":"2026-08-15T21:02:50.645451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.629757Z","title":"Training large-scale artificial neural networks on simulated resistive crossbar arrays,","venue":null,"work_id":"bb793145-0671-4bed-812c-52b8f64ea302","year":2019},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.390935Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:0111a71961edbc5825a807e0ab9bf58f36558e21dd0e07be51522e6438c80afc","observation_id":"8ae18437-13bc-459a-b3f3-bc48b352ba64","resolution":{"observed_at":"2026-08-15T21:02:50.633792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.617808Z","title":"Mixed-precision architecture based on computational memory for training deep neural networks,","venue":null,"work_id":"a0e432d1-7db8-49b6-8f7f-c8eb1e40463d","year":2018},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.394682Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:a9dd52fa8cc099045f7612bc313190c7e5880060b3cf23992f8903cf1dec90b4","observation_id":"08bdd632-edc3-4a34-a38b-f94378492cd0","resolution":{"observed_at":"2026-08-15T21:02:50.621994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.604053Z","title":"Acceleration of deep neural network training with resistive cross-point devices,","venue":null,"work_id":"8d888c06-50ba-479e-ae3c-2c5a5ef2c90b","year":2016},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.399213Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:d26119548b90bc4c1006de61eb1ccc29eef6760f293cc5706bae488b870ca931","observation_id":"f8cb2d2a-4471-4fd1-afb2-ff430ea34e5f","resolution":{"observed_at":"2026-08-15T21:02:50.609021Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.589138Z","title":"Algorithm for training neural networks on resistive device arrays,","venue":null,"work_id":"a35bfa19-5ba8-4d41-b647-f666eea872ae","year":2020},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.403037Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:616cb03855432d485aa9eeb70190c3e2a6021173b3ddcf85d45f6548d7546c44","observation_id":"585beae3-3ae6-4f7e-83a1-c3cdf63880df","resolution":{"observed_at":"2026-08-15T21:02:50.593424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.577282Z","title":"Enabling training of neural networks on noisy hardware,","venue":null,"work_id":"fd39847e-3f39-4834-aa0d-5787f7d25a66","year":2021},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.407194Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:d1c1d0111e1bb69977f9d2ef187ac6ae6c93e642159c645ce062aa9ffd8c1c4f","observation_id":"72af6156-144a-4573-bb6d-c48caf797315","resolution":{"observed_at":"2026-08-15T21:02:50.581142Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.564630Z","title":"Deep learning acceleration in 14nm cmos compatible reram array: device, material and algorithm co-optimization,","venue":null,"work_id":"dfcfe1c5-4112-4d79-bbd0-81969837dc66","year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.411026Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9c942c5bff4f5b597e0cbe9f698bd27430827d865b12c4466d51f644c5971f77","observation_id":"7bae4c48-2093-4580-9f26-6107833ea02e","resolution":{"observed_at":"2026-08-15T21:02:50.568943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T21:02:50.551590Z","title":"Circuit techniques for reducing the effects of op-amp imperfections: autozeroing, correlated double sampling, and chopper stabilization,","venue":null,"work_id":"e4cb4b0e-38b5-4605-9875-423e11fc232f","year":1996},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.414768Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:2ec029dcda3cee05bf753c7b03aeea3e34c6ba9da91e2f427bee2e1e93536148","observation_id":"f3bae9f5-6d13-4e32-a408-3523012e7d6e","resolution":{"observed_at":"2026-08-15T21:02:50.556013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2026-08-15T21:02:50.419361Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.419361Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:9429fd9bb72508425197b499fa6ce0e6e2e4c4c288301971bff4d895e01bf739","observation_id":"2d4eabf9-7831-44c2-8af5-87b257b47ca5","resolution":{"observed_at":"2026-08-15T21:02:50.419361Z","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":"2026-08-15T21:02:50.423242Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.423242Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:69484fbd1b7fc831f3422d09292da7d09144bac3e1d9e8fe5739677c2c734a65","observation_id":"da113d1f-e478-446f-ba99-2eb6c3fd9c7e","resolution":{"observed_at":"2026-08-15T21:02:50.423242Z","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":"2026-08-15T21:02:50.427053Z","title":"A survey on vision transformer,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.427053Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:fc77383d4c0999350f417bba82671bc568da4b4f4dae4cc6edc8378998ed8b43","observation_id":"3880c667-2b6d-40f1-a7a0-6970ae51fea7","resolution":{"observed_at":"2026-08-15T21:02:50.427053Z","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":"2026-08-15T21:02:50.430644Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.430644Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:8ddc917ded53bd0c2c0e5d0b1cc0b24cc8b0261905c91399921197438be231b8","observation_id":"fc1b0602-185c-45c1-b245-4c5d1286d905","resolution":{"observed_at":"2026-08-15T21:02:50.430644Z","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":"2026-08-15T21:02:50.500783Z","title":"Impact of l 1 batch normalization on analog noise resistant property of deep learning models,","venue":null,"work_id":"b0932130-7485-40cb-b8a4-c320f9db74e9","year":2022},"citing_paper":{"arxiv_id":"2505.11067","last_updated":"2025-05-16T10:02:32Z","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T21:02:50.434091Z"},"links":{"citing_paper":"/paper/2505.11067"},"observation_digest":"sha256:591dbcd655a0ad4787ce4f9e75cf53c0eef69ac2ffdb2afd04ebd187716a23b6","observation_id":"fa107951-4625-4e04-8f14-46364c4e2e11","resolution":{"observed_at":"2026-08-15T21:02:50.508131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2505.11067","last_updated":"2025-05-16T10:02:32Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T00:09:46.801302Z","submitted_at":"2025-05-16T10:02:32Z","title":"Assessing the Performance of Analog Training for Transfer Learning"},"reference_resolution":{"displayed":33,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":10,"verified_exact":0,"verified_fuzzy":23},"total_outbound_references":33},"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 33 of 33 outbound references and 0 inbound Pith citation observations for arXiv:2505.11067."}