{"as_of":"2026-08-07T06:34:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1cb641b6e341f40c80908eeed43f1e6bc59c2e3075f2825dac684eca6caa7898","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T08:13:05.223445Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.20516/citation-record","integrity":"/paper/2607.20516/integrity","json":"/paper/2607.20516/citation-record.json","paper":"/paper/2607.20516"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.08134","last_updated":"2021-03-19T10:43:12Z","snapshot_observed_at":"2026-07-06T10:34:02.819928Z","submitted_at":"2021-01-20T13:59:52Z","title":"Zero-Cost Proxies for Lightweight NAS","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.08134","snapshot_observed_at":"2026-08-02T08:13:03.283873Z","title":"arXiv preprint arXiv:2101.08134 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.283873Z"},"links":{"cited_paper":"/paper/2101.08134","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:76135ff2b0e360466a06660ec44185ff2fbcf849aee4d56727e8f1a376f45692","observation_id":"f98a51d6-0291-4429-a220-1294c5b13a21","resolution":{"observed_at":"2026-08-02T08:13:03.283873Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.20422","last_updated":"2025-02-27T09:17:49Z","snapshot_observed_at":"2026-07-06T20:43:59.574176Z","submitted_at":"2025-02-27T09:17:49Z","title":"SEKI: Self-Evolution and Knowledge Inspiration based Neural Architecture Search via Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.20422","snapshot_observed_at":"2026-08-02T08:13:03.358856Z","title":"arXiv preprint arXiv:2502.20422 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.358856Z"},"links":{"cited_paper":"/paper/2502.20422","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:c9cf9f355b87928adc604f8bf189c989a4e38fc60c12403978a666cee6857001","observation_id":"d6e2a484-7368-43b8-9bfd-0b9e4d6903b7","resolution":{"observed_at":"2026-08-02T08:13:03.358856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.02583","last_updated":"2018-10-15T01:34:35Z","snapshot_observed_at":"2026-08-03T16:15:08.176971Z","submitted_at":"2018-10-05T09:37:24Z","title":"AIRNet: Self-Supervised Affine Registration for 3D Medical Images using Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.02583","snapshot_observed_at":"2026-08-02T08:13:03.435371Z","title":"arXiv preprint arXiv:1810.02583 (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.435371Z"},"links":{"cited_paper":"/paper/1810.02583","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:5ea3cbfe31fbf3ac8c1dce83d7f7824f5fa0e69f76dd64a17ad13941a24ea3c7","observation_id":"7dba4572-7cc4-492e-9579-8787838e28e2","resolution":{"observed_at":"2026-08-02T08:13:03.435371Z","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":"2026-08-02T08:13:03.495100Z","title":"In: Advances in Neural Information Processing Systems (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.495100Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:b20a05c2af8180aab20182797890822ab07f176f5528feb9da564256cfa0a1ca","observation_id":"3303d65f-bdfe-4bad-bff6-9a9d778875db","resolution":{"observed_at":"2026-08-02T08:13:03.495100Z","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":"2026-08-02T08:13:03.574186Z","title":"In: Advances in Neural Information Processing Systems (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.574186Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:9f878b6c940b517342d6d691880d49183a7cc997400da30852ccb17860f5e282","observation_id":"3fa77059-9718-4a5e-a4b2-b732aee27ea1","resolution":{"observed_at":"2026-08-02T08:13:03.574186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.10552","last_updated":"2025-09-24T10:29:39Z","snapshot_observed_at":"2026-07-06T21:09:17.062196Z","submitted_at":"2025-04-14T09:08:00Z","title":"LEMUR Neural Network Dataset: Towards Seamless AutoML","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.10552","snapshot_observed_at":"2026-08-02T08:13:03.645303Z","title":"arXiv preprint arXiv:2504.10552 (2025),https://arxiv.org/abs/2504.10552","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.645303Z"},"links":{"cited_paper":"/paper/2504.10552","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:0a6dfa06a142d6aa575629f4ad6f61bf5be584c7612b4bd52584dcbd3d1be072","observation_id":"37142e7f-1ad4-4df4-b52e-ad4176ffca9e","resolution":{"observed_at":"2026-08-02T08:13:03.645303Z","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":"2026-08-02T08:13:03.725288Z","title":"In: Proceedings of the European Conference on Computer Vision (ECCV) (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.725288Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:fd48742ac11c3facbce045807f7153629440a2b53a4363d808c335fc1bdf6491","observation_id":"8de7a8c5-b848-4e97-b2cc-ded81974c5e1","resolution":{"observed_at":"2026-08-02T08:13:03.725288Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-02T08:13:03.782324Z","title":"arXiv preprint arXiv:2106.09685 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.782324Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:7f60cbc6177c88712cf6021c0804d53fda8fb67847ee151b194a776361176366","observation_id":"07cf3212-76fb-49e3-a28e-3acac4086709","resolution":{"observed_at":"2026-08-02T08:13:03.782324Z","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":"2026-08-02T08:13:03.857426Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.857426Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:01215e4c246b7dd3f710825ec1a7d4f157e16e9966351f00ecf0a29056d9d4b0","observation_id":"58ef5325-4fac-429a-8c6b-1d9e55a08b39","resolution":{"observed_at":"2026-08-02T08:13:03.857426Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.26037","last_updated":"2026-05-17T07:21:08Z","snapshot_observed_at":"2026-08-03T03:36:09.071995Z","submitted_at":"2025-09-30T10:12:49Z","title":"CoLLM-NAS: Collaborative Large Language Models for Efficient Knowledge-Guided Neural Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.26037","snapshot_observed_at":"2026-08-02T08:13:03.916150Z","title":"arXiv preprint arXiv:2509.26037 (2025)","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.916150Z"},"links":{"cited_paper":"/paper/2509.26037","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:cc92534b37534177d529a92ea38b2e38e45fa11a35f367e70cb2a287a7d55f04","observation_id":"1e1cb5b2-fd23-4fa7-ae03-466a69a3d40c","resolution":{"observed_at":"2026-08-02T08:13:03.916150Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.09055","last_updated":"2019-04-23T06:29:32Z","snapshot_observed_at":"2026-08-01T17:05:53.501765Z","submitted_at":"2018-06-24T00:06:13Z","title":"DARTS: Differentiable Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1806.09055","snapshot_observed_at":"2026-08-02T08:13:03.992440Z","title":"arXiv preprint arXiv:1806.09055 (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:03.992440Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:202dcbf62dcfc83f7149969149601baac4f197901787cbdf111c416105ca8736","observation_id":"c93232b0-966e-407b-a24e-d2a3e1bf8a1f","resolution":{"observed_at":"2026-08-02T08:13:03.992440Z","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":"2026-08-02T08:13:04.114653Z","title":"In: Proceedings of the IEEE/CVF International Conference on Computer Vision (2019)","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.114653Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:01b9fef0221fa52fa66c0d57228d2b6b24a13ab2e27945929f2c3996b8d732c9","observation_id":"73f21004-fa87-4527-8029-e4589d344cc8","resolution":{"observed_at":"2026-08-02T08:13:04.114653Z","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":"2026-08-02T08:13:04.175947Z","title":"In: Proceedings of the IEEE Interna- tional Conference on Computer Vision (2017)","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.175947Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:ffb43fe59ebf278dc565cff2f8863002b0eee011758b5c2f031e87b4f067ba0f","observation_id":"9cf7be36-3348-4ec9-ad2a-577348342286","resolution":{"observed_at":"2026-08-02T08:13:04.175947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.01102","last_updated":"2024-04-12T08:17:54Z","snapshot_observed_at":"2026-07-31T07:25:35.324750Z","submitted_at":"2023-06-01T19:33:21Z","title":"LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimization","version":8},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.01102","snapshot_observed_at":"2026-08-02T08:13:04.275610Z","title":"arXiv preprint arXiv:2306.01102 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.275610Z"},"links":{"cited_paper":"/paper/2306.01102","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:19dbd6fda2a1244aa268de548ad39db145a9af4a6551d274d4ea73d93aef1c8e","observation_id":"9314d172-39db-4e06-a11c-885336752981","resolution":{"observed_at":"2026-08-02T08:13:04.275610Z","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":"2026-08-02T08:13:04.408027Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.408027Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:f0d6b4645e10ccc77784a9973c53f44f97949647a1412d863cb95c47fc9a1820","observation_id":"fc9948f8-7d93-4cff-a407-4e339fa0e576","resolution":{"observed_at":"2026-08-02T08:13:04.408027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2601.08517","last_updated":"2026-05-04T13:22:35Z","snapshot_observed_at":"2026-08-02T18:38:11.484527Z","submitted_at":"2026-01-13T13:00:30Z","title":"Closed-Loop LLM Discovery of Non-Standard Channel Priors in Vision Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2601.08517","snapshot_observed_at":"2026-08-02T08:13:04.532587Z","title":"In: Proceedings of the International Conference on Pattern Recognition (ICPR) (2026),https://arxiv.org/abs/2601.08517, to appear","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.532587Z"},"links":{"cited_paper":"/paper/2601.08517","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:ee04b41144a78d9e0fb62aea48a8d62d64bf2060de2c22d4ba04f4609df09b0f","observation_id":"5024d601-fcbf-4c4a-9047-e7c8cf3f31db","resolution":{"observed_at":"2026-08-02T08:13:04.532587Z","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":"2026-08-02T08:13:04.623006Z","title":"In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.623006Z"},"links":{"citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:9bfcd0bbccf9f8feb78b37ad39e21825c8296b6db1aff02d31c3a8787973582c","observation_id":"adf47185-7aae-4136-a881-8346fce77ad5","resolution":{"observed_at":"2026-08-02T08:13:04.623006Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.05351","last_updated":"2025-02-15T04:09:35Z","snapshot_observed_at":"2026-07-06T15:25:01.109419Z","submitted_at":"2023-05-09T11:29:42Z","title":"GPT-NAS: Evolutionary Neural Architecture Search with the Generative Pre-Trained Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.05351","snapshot_observed_at":"2026-08-02T08:13:04.761560Z","title":"arXiv preprint arXiv:2305.05351 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.761560Z"},"links":{"cited_paper":"/paper/2305.05351","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:372eb782c6ed8fbb6a13c289ec0276ce77f4a6b0491fb106a279f8dd103703af","observation_id":"2771565b-bd81-4c2b-a4c8-995323be6151","resolution":{"observed_at":"2026-08-02T08:13:04.761560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.11728","last_updated":"2019-06-01T03:19:54Z","snapshot_observed_at":"2026-08-01T14:19:06.163558Z","submitted_at":"2019-03-27T23:17:28Z","title":"AutoSlim: Towards One-Shot Architecture Search for Channel Numbers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.11728","snapshot_observed_at":"2026-08-02T08:13:04.853600Z","title":"arXiv preprint arXiv:1903.11728 (2019)","venue":null,"work_id":null,"year":1903},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.853600Z"},"links":{"cited_paper":"/paper/1903.11728","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:dc7bb16101b836ff3648b7831ea1bde1df2da2d62ac8888fb9076e524b905747","observation_id":"76e5dabd-82e4-4fc2-a33b-641485da4357","resolution":{"observed_at":"2026-08-02T08:13:04.853600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1902.08142","last_updated":"2019-11-22T17:07:59Z","snapshot_observed_at":"2026-07-06T07:34:38.409337Z","submitted_at":"2019-02-21T17:11:56Z","title":"Evaluating the Search Phase of Neural Architecture Search","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.08142","snapshot_observed_at":"2026-08-02T08:13:04.927958Z","title":"arXiv preprint arXiv:1902.08142 (2019)","venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.927958Z"},"links":{"cited_paper":"/paper/1902.08142","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:9818113c3c8663b2bf63b9b1290f6abe209442d5cb4a187bbdbdeec758e84bae","observation_id":"fd57ca01-9298-4aa9-9e4f-4ad838246051","resolution":{"observed_at":"2026-08-02T08:13:04.927958Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.10970","last_updated":"2023-08-02T03:59:34Z","snapshot_observed_at":"2026-08-05T08:12:59.240898Z","submitted_at":"2023-04-21T14:06:44Z","title":"Can GPT-4 Perform Neural Architecture Search?","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.10970","snapshot_observed_at":"2026-08-02T08:13:04.975165Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:04.975165Z"},"links":{"cited_paper":"/paper/2304.10970","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:852456dbabe42c39c3b88f4b2059aaba2f3ffc48db3ef97b2ec0eec435bd2c87","observation_id":"d70cb284-59a7-4b2c-b7c7-a54c823c8479","resolution":{"observed_at":"2026-08-02T08:13:04.975165Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.01233","last_updated":"2020-02-27T02:42:45Z","snapshot_observed_at":"2026-08-07T05:22:59.203221Z","submitted_at":"2020-01-05T13:29:02Z","title":"EcoNAS: Finding Proxies for Economical Neural Architecture Search","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.01233","snapshot_observed_at":"2026-08-02T08:13:05.063182Z","title":"arXiv preprint arXiv:2001.01233 (2020)","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:05.063182Z"},"links":{"cited_paper":"/paper/2001.01233","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:d500f0577bde0f6043b04e3c927e6b2b2923502f102424c9610bba76e792a391","observation_id":"d7497ee3-9fc1-49b5-9877-8786ec2d77ea","resolution":{"observed_at":"2026-08-02T08:13:05.063182Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2408.11330","last_updated":"2024-12-18T02:51:50Z","snapshot_observed_at":"2026-07-06T19:03:48.173775Z","submitted_at":"2024-08-21T04:27:44Z","title":"Design Principle Transfer in Neural Architecture Search via Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11330","snapshot_observed_at":"2026-08-02T08:13:05.141306Z","title":"arXiv preprint arXiv:2408.11330 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:05.141306Z"},"links":{"cited_paper":"/paper/2408.11330","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:d80429a3e1203ec4552bff2c6a4f7189d25bfa6da158fcf9fb5e81accbf53059","observation_id":"f9be6044-addb-423c-956b-15c71448ea4b","resolution":{"observed_at":"2026-08-02T08:13:05.141306Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.01578","last_updated":"2017-02-15T05:28:05Z","snapshot_observed_at":"2026-07-06T05:17:29.499249Z","submitted_at":"2016-11-05T00:41:37Z","title":"Neural Architecture Search with Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.01578","snapshot_observed_at":"2026-08-02T08:13:05.223445Z","title":"arXiv preprint arXiv:1611.01578 (2016)","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-02T08:13:05.223445Z"},"links":{"cited_paper":"/paper/1611.01578","citing_paper":"/paper/2607.20516"},"observation_digest":"sha256:54d24992cab6bf5e72b7ca66c987010e1028a46ddbcb0e611f9ec0309a72fa0f","observation_id":"05ee8c9a-74d8-4569-9d92-8b5dfd489795","resolution":{"observed_at":"2026-08-02T08:13:05.223445Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.20516","last_updated":"2026-07-07T22:31:53Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-04T19:10:00.882891Z","submitted_at":"2026-07-07T22:31:53Z","title":"Scaling Closed-Loop Feature Channel Configuration with LLMs"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.20516."}