{"as_of":"2026-08-13T16:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d80695ebf756714725e61155a58502e96f8aaaf3f35a0a8c925b7ceaa4b8edfa","coverage":[{"denominator":21,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":21,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T15:14:28.528461Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2608.09558/citation-record","integrity":"/paper/2608.09558/integrity","json":"/paper/2608.09558/citation-record.json","paper":"/paper/2608.09558"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T15:14:28.904491Z","title":"Aobo Kong, Shiwan Zhao, Hao Chen, Qicheng Li, Yong Qin, Ruiqi Sun, Xin Zhou, Enzhi Wang, and Xiaohang Dong","venue":null,"work_id":"e523fda3-ccaf-492e-a5eb-30e6ebc629c2","year":2024},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.482213Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:3a9a9e2b5dc771ee20f84cc1d77c1df54299ef565c0b21bbda815a0719ace86d","observation_id":"55bdee17-4ebd-4de6-90e6-e47b798fc584","resolution":{"observed_at":"2026-08-11T15:14:28.908493Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T15:14:28.892039Z","title":"URLhttps://aclanthology.org/2024.naacl-long.228/","venue":null,"work_id":"5b5a9d35-68a6-4bf0-9555-756176905e01","year":2024},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.486306Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:62b0f23cecd4fbf7375023871f0da1b92fc11255ed547cb7887fc34a59d4d034","observation_id":"3dc08dc5-b260-4b3b-b1b3-bd717fc15f60","resolution":{"observed_at":"2026-08-11T15:14:28.896232Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.14201","last_updated":"2023-11-03T11:59:45Z","snapshot_observed_at":"2026-08-13T05:43:54.008878Z","submitted_at":"2023-10-22T06:34:09Z","title":"Prompt Engineering Through the Lens of Optimal Control","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.14201","snapshot_observed_at":"2026-08-11T15:14:28.489885Z","title":"Wolfgang Maass, Thomas Natschläger, and Henry Markram","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.489885Z"},"links":{"cited_paper":"/paper/2310.14201","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:536c2a391a793c1a800e787b90444e2b1c03b40b2919936a39bf6c0c30423337","observation_id":"319692d9-0506-4982-9f2d-6efd7f23bbf1","resolution":{"observed_at":"2026-08-11T15:14:28.489885Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.00421","last_updated":"2025-08-30T09:08:00Z","snapshot_observed_at":"2026-08-11T03:33:14.501107Z","submitted_at":"2025-08-30T09:08:00Z","title":"Memory Limitations of Prompt Tuning in Transformers","version":1},"cited_work":{"arxiv_id":"2509.00421","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.00421","snapshot_observed_at":"2026-08-11T15:14:28.639388Z","title":"Memory Limitations of Prompt Tuning in Transformers","venue":"cs.LG","work_id":"89d37065-4de2-429f-9d9b-a5405b74d196","year":2025},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.493489Z"},"links":{"cited_paper":"/paper/2509.00421","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:a66c89f8c4d32dfcb97f1894a17f140c161c88b1f1361982b11110b231a88df4","observation_id":"520f5c59-ddea-4682-a1f2-4c902019a962","resolution":{"observed_at":"2026-08-11T15:14:28.643858Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.20561","last_updated":"2025-03-26T13:58:02Z","snapshot_observed_at":"2026-08-07T16:35:28.758912Z","submitted_at":"2025-03-26T13:58:02Z","title":"A Theoretical Framework for Prompt Engineering: Approximating Smooth Functions with Transformer Prompts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.20561","snapshot_observed_at":"2026-08-11T15:14:28.497840Z","title":"Partha Niyogi, Stephen Smale, and Shmuel Weinberger","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.497840Z"},"links":{"cited_paper":"/paper/2503.20561","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:cbc2f6bc1fbf6051ddaed3e8456db70c13d87507c4a48949b44e83aaed5dd3cb","observation_id":"c3e154bd-b875-46b0-aa18-f66063b44914","resolution":{"observed_at":"2026-08-11T15:14:28.497840Z","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":"2026-08-11T15:14:28.878337Z","title":"neurips.cc/paper_files/paper/2008/file/0efe32849d230d7f53049ddc4a4b0c60-Paper.pdf","venue":null,"work_id":"f58cb33a-9d74-4bfd-8bc9-9c7c549cfa28","year":2008},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.505851Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:517d83cb5ad61dae2efb6c7405def932198f0ef1fd5cc0f9cd07bc2068af09ba","observation_id":"75638d22-d25f-4541-883f-66d04e1ded28","resolution":{"observed_at":"2026-08-11T15:14:28.883476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.07927","last_updated":"2025-03-16T06:23:34Z","snapshot_observed_at":"2026-08-05T17:55:26.008016Z","submitted_at":"2024-02-05T19:49:13Z","title":"A Systematic Survey of Prompt Engineering in Large Language Models: Techniques and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.07927","snapshot_observed_at":"2026-08-11T15:14:28.509353Z","title":"Timo Schick, Jane Dwivedi-Yu, Roberto Dessi, Roberta Raileanu, Maria Lomeli, Eric Hambro, Luke Zettle- moyer, Nicola Cancedda, and Thomas Scialom","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.509353Z"},"links":{"cited_paper":"/paper/2402.07927","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:8cbd9bd907d2bac3c761d3d76fbcff9cca3092d755c0181c4cb9dc82af9c5cf4","observation_id":"cfc1bd5f-4143-43f9-92e9-56aafa9fea4f","resolution":{"observed_at":"2026-08-11T15:14:28.509353Z","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":"2026-08-11T15:14:28.866257Z","title":"Sheng Shen, Alexei Baevski, Ari S","venue":null,"work_id":"37d205b2-3d8a-47aa-91b4-5c187ea8656d","year":2021},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.513059Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:d769393138e906b4736a24c6200137b027de0a4a13012541b43c48e8c80c84ec","observation_id":"d0377090-656d-436b-bfcd-370965a8d63a","resolution":{"observed_at":"2026-08-11T15:14:28.870448Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T15:14:28.853936Z","title":"Taylor Shin, Yasaman Razeghi, Robert L","venue":null,"work_id":"3e657905-4985-417f-97e7-0b04f7f00576","year":2020},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.516665Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:021bf25ab3697cca4eedd727f5c1b9d0469d487619016f05b7c011a39e5b8177","observation_id":"ab05c692-9e98-42f7-a706-11c611fa7dbe","resolution":{"observed_at":"2026-08-11T15:14:28.857596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T15:14:28.840735Z","title":null,"venue":null,"work_id":"360073d0-7cc0-47dd-a58e-d95c91677ab4","year":2019},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.520473Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:612edf205d99c20778a4ffdc22be16b9aeec518a6922af607bdf8b8e8a59d3c4","observation_id":"b700c30a-d31b-4787-bb6d-3251da822f4a","resolution":{"observed_at":"2026-08-11T15:14:28.844839Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T15:14:28.528461Z","title":"Ziqian Zhong and Jacob Andreas","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.528461Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:06d30e8551c9d5cdefe429b5679dd286a21ee4ffcb2a83acff305c36e9e97536","observation_id":"afaebf6b-be54-4666-9b65-f5e2cae03b2c","resolution":{"observed_at":"2026-08-11T15:14:28.528461Z","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":"2026-08-11T15:14:28.444916Z","title":"Aman Bhargava, Cameron Witkowski, Shi-Zhuo Looi, and Matt Thomson","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":1993,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.444916Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:dcc4c0502f445702fb6af61e921509fcaa1d585348af5254cea4a17a198fa01f","observation_id":"531442ae-a4dd-4152-bb5c-eae1f8455131","resolution":{"observed_at":"2026-08-11T15:14:28.444916Z","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":"10.1016/s1874-5849(01)80010-3","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T15:14:28.592816Z","title":"URLhttps://www.sciencedirect.com/ science/article/pii/S1874584901800103","venue":null,"work_id":"d169f9e0-334b-4727-9864-853ef04c38ee","year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2001,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.458655Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:589fd04acec096ae4fc557e363d7dc44653a852fb6fb5623e9ea1dc7a1849305","observation_id":"ef8c7d97-dfa6-4d2d-81de-c4c07362313f","resolution":{"observed_at":"2026-08-11T15:14:28.598434Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"stable/2046146","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T15:14:28.814095Z","title":"URLhttp://www.jstor.org/stable/20461468","venue":null,"work_id":"d59836a1-a1de-4078-a883-6fed2b8a41d6","year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.454426Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:8c36a09ae0168db3d770ad9894079e5bda521c7fe310f7adaae5a0322e8e27a4","observation_id":"db644739-6760-4ed6-b99f-c86c427e5eaf","resolution":{"observed_at":"2026-08-11T15:14:28.821419Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-11T15:14:28.502151Z","title":"doi: 10.1007/s00454-008-9053-2","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2008,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.502151Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:d4b659e6ea0a326297e6fe87a70fdf1d5b1e53b4aa11e97e8223521fec59e7cf","observation_id":"9167ca07-2d34-4cbb-be02-44bbd6176b36","resolution":{"observed_at":"2026-08-11T15:14:28.502151Z","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":"2026-08-11T15:14:28.468717Z","title":"Kurt Hornik","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.468717Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:23a4621feddd072d667f9f9e1d264c37db29a7b3bc57c7d7525a7b5b93226da2","observation_id":"a8944c00-def7-4953-909c-78353ca6bed5","resolution":{"observed_at":"2026-08-11T15:14:28.468717Z","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":"2026-08-11T15:14:28.523835Z","title":"doi: https://doi.org/10.1016/j.neunet.2017.07.002","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.523835Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:1b709a7653275b811e075ba73f9ab31501471c8efc3df873b2bfd244cd87de9e","observation_id":"fc41d120-ad51-4b59-8f49-755ee2832bc6","resolution":{"observed_at":"2026-08-11T15:14:28.523835Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.04444","last_updated":"2024-07-03T22:23:50Z","snapshot_observed_at":"2026-08-13T05:58:50.122488Z","submitted_at":"2023-10-02T22:35:40Z","title":"What's the Magic Word? A Control Theory of LLM Prompting","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.04444","snapshot_observed_at":"2026-08-11T15:14:28.449797Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.449797Z"},"links":{"cited_paper":"/paper/2310.04444","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:7a1af3919da6503a053333cb34cc3a0eee4a8af5218ce52d8c29d1cc630de681","observation_id":"0359eeb5-c02f-4b9a-9888-99a2d532ff7b","resolution":{"observed_at":"2026-08-11T15:14:28.449797Z","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":"2026-08-11T15:14:28.477903Z","title":"URLhttps://proceedings.neurips.cc/paper_files/paper/2024/file/ 7f64034009f4a5fa417a57e1a987c5cd-Paper-Conference.pdf","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.477903Z"},"links":{"citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:abfe60b70998d9b5d3a256a5e987cb8e13f9a25833b875f93ddd1fa49464239e","observation_id":"2315d1d7-7bc4-4a57-bebf-441004df4772","resolution":{"observed_at":"2026-08-11T15:14:28.477903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.01115","last_updated":"2025-09-03T19:18:47Z","snapshot_observed_at":"2026-08-08T11:54:01.449606Z","submitted_at":"2025-06-01T18:42:39Z","title":"Is Random Attention Sufficient for Sequence Modeling? Disentangling Trainable Components in the Transformer","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.01115","snapshot_observed_at":"2026-08-11T15:14:28.463703Z","title":"Shivam Garg, Dimitris Tsipras, Percy Liang, and Gregory Valiant","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.463703Z"},"links":{"cited_paper":"/paper/2506.01115","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:23cc329595384a72ed3e669f31f3a0c7a50c8783908b175d28037c640beb056f","observation_id":"69de66da-b7a2-4dcd-93e9-190b1aee2527","resolution":{"observed_at":"2026-08-11T15:14:28.463703Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.05176","last_updated":"2026-05-06T17:42:07Z","snapshot_observed_at":"2026-08-12T16:38:43.556782Z","submitted_at":"2026-05-06T17:42:07Z","title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","version":1},"cited_work":{"arxiv_id":"2605.05176","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.05176","snapshot_observed_at":"2026-08-11T15:14:28.666724Z","title":"Understanding In-Context Learning for Nonlinear Regression with Transformers: Attention as Featurizer","venue":"cs.LG","work_id":"573bb425-d503-4832-b9fd-fd57f940dd3c","year":2026},"citing_paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-11T15:14:28.472925Z"},"links":{"cited_paper":"/paper/2605.05176","citing_paper":"/paper/2608.09558"},"observation_digest":"sha256:7b32f5e6d45606c06e2f7d6283a23100aaa6f371f4973bf12def89a697430d35","observation_id":"b2c4d46a-e8e6-4268-acc7-4022a34ba82c","resolution":{"observed_at":"2026-08-11T15:14:28.670556Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2608.09558","last_updated":"2026-08-10T12:57:22Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T16:21:34.613874Z","submitted_at":"2026-08-10T12:57:22Z","title":"Training-Free Universal Approximation by Prompting Random Transformers"},"reference_resolution":{"displayed":21,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":4,"verified_fuzzy":5},"total_outbound_references":21},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 21 of 21 outbound references and 0 inbound Pith citation observations for arXiv:2608.09558."}