{"as_of":"2026-08-06T13:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c92c2fab01af6c4ccc82cddc5fe9b5c22c4c5e73f89238da22282bfae4880a30","coverage":[{"denominator":76,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":76,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T20:21:11.691407Z","state":"measured"},{"denominator":80,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":80,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-06T06:34:29.942622+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-10T20:15:59.064352Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-10T20:17:33.764539Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"cited_work":{"arxiv_id":"2511.20333","doi":null,"metadata_source":"pith","pith_arxiv_id":"2511.20333","snapshot_observed_at":"2026-07-10T20:17:33.764539Z","title":"Nngpt: Rethinking automl with large language models","venue":"cs.AI","work_id":"46221fd5-3399-413f-b34b-409281bba506","year":2025},"citing_paper":{"arxiv_id":"2511.07329","last_updated":"2026-05-16T15:05:35Z","snapshot_observed_at":"2026-07-06T22:35:22.282985Z","submitted_at":"2025-11-10T17:31:39Z","title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-17T23:22:59.323897Z"},"links":{"cited_paper":"/paper/2511.20333","citing_paper":"/paper/2511.07329"},"observation_digest":"sha256:7d6ac736d3bdd869576f3bc704da0b4b7a02f34f7be621912a088b746ccc7f9b","observation_id":"6c111616-eef7-44da-a19d-ceb5d8974b17","resolution":{"observed_at":"2026-06-02T03:04:02.493576Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"cited_work":{"arxiv_id":"2511.20333","doi":null,"metadata_source":"pith","pith_arxiv_id":"2511.20333","snapshot_observed_at":"2026-07-10T20:17:33.764539Z","title":"Nngpt: Rethinking automl with large language models","venue":"cs.AI","work_id":"46221fd5-3399-413f-b34b-409281bba506","year":2025},"citing_paper":{"arxiv_id":"2511.07329","last_updated":"2026-05-16T15:05:35Z","snapshot_observed_at":"2026-07-06T22:35:22.282985Z","submitted_at":"2025-11-10T17:31:39Z","title":"Preparation of Fractal-Inspired Computational Architectures for Advanced Large Language Model Analysis","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T19:25:25.465712Z"},"links":{"cited_paper":"/paper/2511.20333","citing_paper":"/paper/2511.07329"},"observation_digest":"sha256:0815c915d8d6f2414616cb77f0ce04fb07417551812d19149dcf7788004dbdcb","observation_id":"61a8e056-d148-4760-be9c-0e7eb86b667a","resolution":{"observed_at":"2026-06-02T03:04:02.493576Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"cited_work":{"arxiv_id":"2511.20333","doi":null,"metadata_source":"pith","pith_arxiv_id":"2511.20333","snapshot_observed_at":"2026-07-10T20:17:33.764539Z","title":"Nngpt: Rethinking automl with large language models","venue":"cs.AI","work_id":"46221fd5-3399-413f-b34b-409281bba506","year":2025},"citing_paper":{"arxiv_id":"2512.24120","last_updated":"2026-04-16T12:18:23Z","snapshot_observed_at":"2026-07-06T22:40:23.205898Z","submitted_at":"2025-12-30T10:01:55Z","title":"Enhancing LLM-Based Neural Network Generation: Few-Shot Prompting and Efficient Validation for Automated Architecture Design","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-16T19:08:18.706760Z"},"links":{"cited_paper":"/paper/2511.20333","citing_paper":"/paper/2512.24120"},"observation_digest":"sha256:2a01a517534bab06f35bc0119e07143ef170f50dd25470464f4ba2701a14e4ac","observation_id":"26459452-cf88-4e39-a0bf-306bfcd1dda5","resolution":{"observed_at":"2026-06-02T03:04:02.493576Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"cited_work":{"arxiv_id":"2511.20333","doi":null,"metadata_source":"pith","pith_arxiv_id":"2511.20333","snapshot_observed_at":"2026-07-10T20:17:33.764539Z","title":"Nngpt: Rethinking automl with large language models","venue":"cs.AI","work_id":"46221fd5-3399-413f-b34b-409281bba506","year":2025},"citing_paper":{"arxiv_id":"2607.06839","last_updated":"2026-07-07T22:21:53Z","snapshot_observed_at":"2026-08-05T09:15:46.811590Z","submitted_at":"2026-07-07T22:21:53Z","title":"LEMUR 2: Unlocking Neural Network Diversity for AI","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-10T20:15:59.064352Z"},"links":{"cited_paper":"/paper/2511.20333","citing_paper":"/paper/2607.06839"},"observation_digest":"sha256:a17140fd367efe1134154ccdaaf93e207d1f46a64ea0ada84f8d2209158c3715","observation_id":"4d27a94f-265d-4f94-9c62-445443c8b3b1","resolution":{"observed_at":"2026-07-10T20:17:33.765979Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2511.20333/citation-record","integrity":"/paper/2511.20333/integrity","json":"/paper/2511.20333/citation-record.json","paper":"/paper/2511.20333"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T20:21:01.603382Z","title":"Efficient bayesian learning curve extrapo- lation using prior-data fitted networks.Advances in Neural Information Processing Systems, 36:19858–19886, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:01.603382Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:d8fbe1824664bf5b72b306bcc5d292d6bcbaba8fd5dd66fba4761e4dba80ebf4","observation_id":"a51cd810-0bc8-460b-8983-af9e9b94c1d3","resolution":{"observed_at":"2026-08-03T20:21:01.603382Z","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":"2026-08-03T20:21:01.687375Z","title":"Optuna: A next-generation hyperparameter optimization framework","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:01.687375Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:d4a04eb073931506c4c0130cbf5b509ce4fd444e2e3ebb2139b84704a5ce1245","observation_id":"84d26b5c-5365-431f-97a1-a1a980fdabc1","resolution":{"observed_at":"2026-08-03T20:21:01.687375Z","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":"2026-08-03T20:21:01.789283Z","title":"Optuna: A next-generation hyperparameter optimization framework","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:01.789283Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:8bdc66cf759df466d44873a2bb58606026a415a21c06e24da32caa9f19f7cbd9","observation_id":"f133707a-00ac-47e6-bba7-4dcaf21f42cf","resolution":{"observed_at":"2026-08-03T20:21:01.789283Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.01234","last_updated":"2024-01-02T15:02:42Z","snapshot_observed_at":"2026-07-06T17:10:52.289224Z","submitted_at":"2024-01-02T15:02:42Z","title":"Mixture cure semiparametric additive hazard models under partly interval censoring -- a penalized likelihood approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.01234","snapshot_observed_at":"2026-08-03T20:21:01.899498Z","title":"Enhancing llm out- put quality for specialized apis: Fine-tuning versus retrieval","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:01.899498Z"},"links":{"cited_paper":"/paper/2401.01234","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:1f829119f8613245e39386ac4b7095c94fa397ce9b2d26ec2ab67987e5d0b0ca","observation_id":"36353b2d-6f31-45ef-8105-456a835ff495","resolution":{"observed_at":"2026-08-03T20:21:01.899498Z","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":"2026-08-03T20:21:01.980602Z","title":"Algorithms for hyper-parameter optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:01.980602Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:33378b386c639e1b8d9cdfb63bef9bf0ca664db80f33435960b48bb5b4714b40","observation_id":"d202a82e-9fec-42f5-9d22-842365891625","resolution":{"observed_at":"2026-08-03T20:21:01.980602Z","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":"2026-08-03T20:21:02.095647Z","title":"Hyperopt: A python library for optimizing the hyperparameters of machine learning algorithms.SciPy, 13: 20, 2013","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.095647Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:80c36f070942237337e1b4f2b41af7690649777a6f03c2151c989a4df71d4cc8","observation_id":"d39c01bd-81d4-4faa-845c-3a65d5184b79","resolution":{"observed_at":"2026-08-03T20:21:02.095647Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14838","last_updated":"2023-11-16T18:02:19Z","snapshot_observed_at":"2026-07-06T14:56:58.621903Z","submitted_at":"2023-02-28T18:37:25Z","title":"EvoPrompting: Language Models for Code-Level Neural Architecture Search","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14838","snapshot_observed_at":"2026-08-03T20:21:02.187739Z","title":"Dohan, and David R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.187739Z"},"links":{"cited_paper":"/paper/2302.14838","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:32bc7715be3ec7ef7dc7d5c04526d5c45381fb8a3db5c841434d10392d368654","observation_id":"64c65f96-2a79-416b-8e6f-45f94053276e","resolution":{"observed_at":"2026-08-03T20:21:02.187739Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-03T20:21:02.315634Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.315634Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:59f733680f46be1f81efa592b53156b5e7d9c016327ff6ae4c8b7dbc744c31c2","observation_id":"0a018110-2765-4cae-84c3-1d7f9c2bf0c2","resolution":{"observed_at":"2026-08-03T20:21:02.315634Z","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":"2026-08-03T20:21:02.399893Z","title":"Stabilizing differen- tiable architecture search via perturbation-based regulariza- tion","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.399893Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:5d381fa7c5172ea038a4d139cfa862a78e528be1b37707d7afae0c9e2b441475","observation_id":"665d3431-9832-4030-a41c-dbae72971057","resolution":{"observed_at":"2026-08-03T20:21:02.399893Z","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":"2026-08-03T20:21:02.513460Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.513460Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:06406d018915b8926ca4ff694a6e6c379f88276fb5fbf8879c51caef6041d013","observation_id":"3f4b7037-0f7f-4496-9a71-83bed8aa50e6","resolution":{"observed_at":"2026-08-03T20:21:02.513460Z","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":"2026-08-03T20:21:02.627577Z","title":"DeepSeek-V3 technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.627577Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:f422e8bfa9bbc317e4f5383ffc81bd17635084a4edbcd79f1482f39e7c5b0b59","observation_id":"af57fe3c-ac18-42a7-8318-36877def1bf2","resolution":{"observed_at":"2026-08-03T20:21:02.627577Z","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":"2026-08-03T20:21:02.743634Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.743634Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:6ed4ab7a94fadc8fd878608f7abb2a321ecc2b5285f5a2da0c2bc8c39d22c82d","observation_id":"15de391f-6404-4306-ae1d-d888425c93a2","resolution":{"observed_at":"2026-08-03T20:21:02.743634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15554","last_updated":"2025-01-19T02:54:49Z","snapshot_observed_at":"2026-08-04T12:23:09.338111Z","submitted_at":"2024-12-20T04:28:02Z","title":"Architecture-Aware Learning Curve Extrapolation via Graph Ordinary Differential Equation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15554","snapshot_observed_at":"2026-08-03T20:21:02.803885Z","title":"Architecture-aware learning curve extrapola- tion via graph ordinary differential equation.arXiv preprint arXiv:2412.15554, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.803885Z"},"links":{"cited_paper":"/paper/2412.15554","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:d9227a206630240c005be2b1d5c63e843ffc37c10ad770bfd48de4300cb34f40","observation_id":"ada30574-4139-4b38-ab2e-2c2dfb44624c","resolution":{"observed_at":"2026-08-03T20:21:02.803885Z","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":"2026-08-03T20:21:02.913689Z","title":"Speeding up automatic hyperparameter opti- mization of deep neural networks by extrapolation of learn- ing curves","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:02.913689Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:26e03c5f89a738c080ded1d0a34746d060ec77c92b8b547193d769fe3147273f","observation_id":"01d19853-3ea6-4d52-a8f6-ae535ae17445","resolution":{"observed_at":"2026-08-03T20:21:02.913689Z","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":"2026-08-03T20:21:03.039821Z","title":"Google vizier: A service for black-box op- timization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.039821Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:ab6d1c312abfd9b0c810a312efa5b9fb2303e02883896dac176e714b607b3b05","observation_id":"8373d423-abf3-4647-8d05-a8fc07cd98bc","resolution":{"observed_at":"2026-08-03T20:21:03.039821Z","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":"2026-08-03T20:21:03.159622Z","title":"LEMUR Neural Network Dataset: Towards Seamless AutoML, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.159622Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:db87aaa9be1c5b4c4434a8d449e828378bff696ec75b35a6753ddc60e67d0ae9","observation_id":"0e055993-5ffe-4200-8fdd-8283e8d3198d","resolution":{"observed_at":"2026-08-03T20:21:03.159622Z","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":"2026-08-03T20:21:03.275795Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.275795Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:89f75f806fc2caf919a0d0e8d277c7af3aef018535e645f68384a6ac69230d3d","observation_id":"4fa50c3e-688b-4b93-86e8-be1299dd37b9","resolution":{"observed_at":"2026-08-03T20:21:03.275795Z","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":"2026-08-03T20:21:03.343050Z","title":"DeepSeek-Coder: When the large language model meets programming - the rise of code intelligence, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.343050Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:8a4a9d200bc5ea33673fe923e0c8cd874699607a17dae2605e7228ae148c2eb2","observation_id":"bee5dd62-bbff-405e-a947-946f4711b243","resolution":{"observed_at":"2026-08-03T20:21:03.343050Z","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":"2026-08-03T20:21:03.501644Z","title":"Lvis: A dataset for large vocabulary instance segmentation, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.501644Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:5ec185a03c21a553559431bb14b30e4fef9ea90bb118529cef60e50fa52a3327","observation_id":"ecdc0632-8ae5-4962-9af5-340b0e3c82e2","resolution":{"observed_at":"2026-08-03T20:21:03.501644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.01617","last_updated":"2024-10-22T04:09:15Z","snapshot_observed_at":"2026-08-06T00:33:39.168732Z","submitted_at":"2024-04-02T03:43:55Z","title":"Designing Network Algorithms via Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.01617","snapshot_observed_at":"2026-08-03T20:21:03.617029Z","title":"Designing network algorithms via large language models.arXiv preprint arXiv:2404.01617, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.617029Z"},"links":{"cited_paper":"/paper/2404.01617","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:86ae07f72227834e8af103df16e3f298584edae510742c20ef5f11f1d224f4fd","observation_id":"aee0abe8-066b-438b-8a58-f7b6a005a41d","resolution":{"observed_at":"2026-08-03T20:21:03.617029Z","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":"2026-08-03T20:21:03.727712Z","title":"Imagenette: A smaller subset of ImageNet for quick experimentation.https://github.com/ fastai/imagenette, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.727712Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:9322af1edc86a31a345fd8738a6378081d8a7a972e737d04025b2275e1418285","observation_id":"0d666a16-5a15-4822-87ad-9f49ccd5e5aa","resolution":{"observed_at":"2026-08-03T20:21:03.727712Z","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":"2026-08-03T20:21:03.906698Z","title":"Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen- Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:03.906698Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:18741c25639bd16c076cfd03c81d42a6626b0d5996863d6cbe76599684d8b720","observation_id":"f29dbf3d-c1b7-4dc7-bf1d-21f0be702b9a","resolution":{"observed_at":"2026-08-03T20:21:03.906698Z","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":"2026-08-03T20:21:04.098618Z","title":"LoRA: Low-rank adaptation of large language mod- els","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.098618Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:4c6e5fe5f6c41a59dab9471e4ff1bf1fb69e67f6a36ad6acbdcc7626fa848821","observation_id":"92d5d695-ecf9-4b1d-8104-cdf4a6327d44","resolution":{"observed_at":"2026-08-03T20:21:04.098618Z","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":"2026-08-03T20:21:04.241775Z","title":"Auto-keras: An efficient neural architecture search system","venue":null,"work_id":null,"year":1946},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.241775Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:ea3cc44ac175ac6172f4e728928582c3284f0811d6e66f7b51b07f9ab9b8368b","observation_id":"b0bf084c-30dd-4278-82dc-2aa7dcdc58d1","resolution":{"observed_at":"2026-08-03T20:21:04.241775Z","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":"2026-08-03T20:21:04.388135Z","title":"Optuna vs Code Llama: Are LLMs a New Paradigm for Hyperparameter Tuning?, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.388135Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:e5e6ed10d46dbd4c7378a43b6ea90c65dfb55add3b6051ee0972b82e1754562e","observation_id":"02a45444-639c-41a9-b9cd-35155403dcba","resolution":{"observed_at":"2026-08-03T20:21:04.388135Z","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":"2026-08-03T20:21:04.492550Z","title":"Cifar-10 (canadian institute for advanced research)","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.492550Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:4d6b38a501144f17d24487fce0bd98b4608d5fab32e118808ae535652d8c27a0","observation_id":"804f740e-eff9-4633-84a7-1742e0f7ec04","resolution":{"observed_at":"2026-08-03T20:21:04.492550Z","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":"2026-08-03T20:21:04.576519Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.576519Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:62ad3cae2e9432773b6bcff5fbf67620326310ffcf3d5fe9c8723b7ffe7e0b7e","observation_id":"3e4e8bdc-3b3e-4c34-86c0-f31601ad36a6","resolution":{"observed_at":"2026-08-03T20:21:04.576519Z","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":"2026-08-03T20:21:04.698657Z","title":"Gradient-based learning applied to document recog- nition.Proceedings of the IEEE, 86(11):2278–2324, 1998","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.698657Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:f8f40d4685571febf45d1f99b117b1ee992ed4ea612d0362bb23dfadfda087e4","observation_id":"5f66c448-9507-4492-8310-2bf427d7b948","resolution":{"observed_at":"2026-08-03T20:21:04.698657Z","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":"2026-08-03T20:21:04.837442Z","title":"Competition-level code generation with alphacode","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:04.837442Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:7a55c437ed45485d8c4bf149df1ee51ed52c47a80ec030515c6f484ea9986378","observation_id":"b235a2e0-6a3d-48b6-aae2-8cd1d5565657","resolution":{"observed_at":"2026-08-03T20:21:04.837442Z","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":"2026-08-03T20:21:05.071234Z","title":"Libcst: Concrete syntax tree parser and toolkit for python.https : / / libcst","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.071234Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:8ecb5ed1f1c65719b321ff91ecd58937dce1d72b227c91678cf25c082d063a43","observation_id":"36260c24-e7d8-47e0-9f55-61c8205b4f9c","resolution":{"observed_at":"2026-08-03T20:21:05.071234Z","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":"2026-08-03T20:21:05.270084Z","title":"Lawrence Zitnick, and Piotr Doll ´ar","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.270084Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:dc0036c68122becfae279a5702cb1487759fbaf588ae7f0884b93edbcb0772ef","observation_id":"bb4d719d-8e01-43c3-9a4f-9f5bf99151ef","resolution":{"observed_at":"2026-08-03T20:21:05.270084Z","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":"2026-08-03T20:21:05.449598Z","title":"Darts: Differentiable architecture search.arXiv preprint arXiv:1806.09055, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.449598Z"},"links":{"cited_paper":"/paper/1806.09055","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:d89d3c4ac003bca84f5f79b07d04b16d9fb86ffa84c711b79955b68b13120f24","observation_id":"bd3dc8cd-35bc-4ab9-8715-8c24dd08f56e","resolution":{"observed_at":"2026-08-03T20:21:05.449598Z","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":"2026-08-03T20:21:05.651241Z","title":"Deep learning face attributes in the wild","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.651241Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:f5f6e7c0216ddf3d15521e63ceed8b0bdfd857bb0d6019481b723d6870d8db15","observation_id":"90060bdb-4520-4b29-aac9-a8095b2a8443","resolution":{"observed_at":"2026-08-03T20:21:05.651241Z","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":"2026-08-03T20:21:05.757772Z","title":"Large language models to enhance bayesian opti- mization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.757772Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:a731ed840db6f51a9a37d687c21f906f56a92bbeec668fe2e0b052a18bfbc55d","observation_id":"0382ec5b-4f81-4c66-b25d-0ec8a1b24e63","resolution":{"observed_at":"2026-08-03T20:21:05.757772Z","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":"2026-08-03T20:21:05.871564Z","title":"Large language models to enhance bayesian opti- mization, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.871564Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:e925b3b2a2839348833a57e361fb4da215ab0c0f3dc484ed3edb13ab4080260a","observation_id":"ad3b6cab-cacf-40b7-8128-b989c3fb1f06","resolution":{"observed_at":"2026-08-03T20:21:05.871564Z","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":"2026-08-03T20:21:05.963691Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:05.963691Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:bb2afe8465be40c10551dd2dfb1faebf66c127a6542a7f583c039d8852a1ba32","observation_id":"4d596f77-3215-4795-9c2d-60f88479367b","resolution":{"observed_at":"2026-08-03T20:21:05.963691Z","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":"2026-08-03T20:21:06.069137Z","title":"Msr-darts: Minimum stable rank of dif- ferentiable architecture search","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.069137Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:458b805889d7e92bd6ee5f1e5c1da374c37b75a322319e120d8763a8d79db845","observation_id":"2b97e67d-263b-4a93-ba17-47ef271785e3","resolution":{"observed_at":"2026-08-03T20:21:06.069137Z","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":"2026-08-03T20:21:06.225613Z","title":"”torchVision: Py- Torch’s computer vision library”, ”2016”","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.225613Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:e68d222fb95e55a7b31231cd7348464280b4be2045b751141dfda99d5d0bb923","observation_id":"4b56956c-c409-4dda-841c-7ebe41c20e16","resolution":{"observed_at":"2026-08-03T20:21:06.225613Z","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":"2026-08-03T20:21:06.390760Z","title":"Peft: State-of-the-art parameter- efficient fine-tuning methods.https://github.com/ huggingface/peft, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.390760Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:6d62131e0b5f9a114bda0bdaffdf9be457f22a04751ca6733794b60eef594780","observation_id":"d968442c-94ea-4a85-9e9a-7895d5301339","resolution":{"observed_at":"2026-08-03T20:21:06.390760Z","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":"2026-08-03T20:21:06.566790Z","title":"Llmatic: Neural architecture search via large language models and quality-diversity optimization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.566790Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:17c8698d8b3dcd33c916f2d1da75ac5afd2d04b963de4065d2f41179166466b2","observation_id":"09ac3c45-322d-44c4-87f3-dacc95dca93d","resolution":{"observed_at":"2026-08-03T20:21:06.566790Z","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":"2026-08-03T20:21:06.660549Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.660549Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:3a03d6cb906624c835c91eef716ede3af315927e0d87e4cba13567e630603140","observation_id":"1fc5d4c3-61d2-482b-be47-60d505d25a01","resolution":{"observed_at":"2026-08-03T20:21:06.660549Z","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":"2026-08-03T20:21:06.821302Z","title":"GPT-4 technical report, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.821302Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:4268428140371b9ab627201029ed28b62db8d9466fa09587e854eb0d8289d35b","observation_id":"342a0a8f-8798-4607-8217-c5b4bf550bb6","resolution":{"observed_at":"2026-08-03T20:21:06.821302Z","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":"2026-08-03T20:21:06.926821Z","title":"Openmmlab: Open-source com- puter vision toolbox ecosystem.https://openmmlab","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:06.926821Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:cd32e18a735d1a2ef1f6392a038442973332dbaebf6fc98ad8d2e19a4a86a877","observation_id":"d0069129-635f-429a-919d-26d9ca0c8444","resolution":{"observed_at":"2026-08-03T20:21:06.926821Z","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":"2026-08-03T20:21:07.099400Z","title":"PyTorch: An imperative style, high- performance deep learning library, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:07.099400Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:2599448a68c1ba0a6ca4e63d3eab3ed11849920be9f46e25b0ecdc8efadeee9c","observation_id":"297b188a-5e2a-461e-a2e8-4b834e070312","resolution":{"observed_at":"2026-08-03T20:21:07.099400Z","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":"2026-08-03T20:21:07.268916Z","title":"The impact of AI on developer productivity: Ev- idence from GitHub Copilot, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:07.268916Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:47b8d723383350f453f2777f7b9e0bd2609babeb54e1c8725a1065616c7b29e7","observation_id":"7632dc75-301e-4b85-91a6-a8c023b714e6","resolution":{"observed_at":"2026-08-03T20:21:07.268916Z","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":"2026-08-03T20:21:07.440315Z","title":"Efficient neural architecture search via parame- ters sharing","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:07.440315Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:2736626a8f34a31c916d54e64c0750beecd43ebc7df94320a1d20c4c073fa9d8","observation_id":"50780231-3b0f-4a47-bfb1-6bbc4407fd29","resolution":{"observed_at":"2026-08-03T20:21:07.440315Z","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":"2026-08-03T20:21:07.610763Z","title":"Code Llama: Open Foundation Models for Code, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:07.610763Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:9aa4855778d42afdc03c4619100b49f14d2a1e4ff22930100c6ca4aa9253c36d","observation_id":"1aeb003f-53de-4aa5-8672-844ab36c4024","resolution":{"observed_at":"2026-08-03T20:21:07.610763Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.12950","last_updated":"2024-01-31T19:47:26Z","snapshot_observed_at":"2026-07-06T16:10:07.931347Z","submitted_at":"2023-08-24T17:39:13Z","title":"Code Llama: Open Foundation Models for Code","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.12950","snapshot_observed_at":"2026-08-03T20:21:07.781631Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:07.781631Z"},"links":{"cited_paper":"/paper/2308.12950","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:3f9855a3c7297c889fc798202e767873a249c981d939f889e44d980205f6728b","observation_id":"1d1c7496-56ca-4ab1-8ce4-19c068e25d5a","resolution":{"observed_at":"2026-08-03T20:21:07.781631Z","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":"2026-08-03T20:21:07.977899Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:07.977899Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:32b3938898a5a1eff2f910293baaddacb0f5b2e7baca0060690e2e9611dd32df","observation_id":"df96b19a-a8bf-4747-8e5f-a8072c96e9ea","resolution":{"observed_at":"2026-08-03T20:21:07.977899Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.00167","last_updated":"2023-02-02T23:42:12Z","snapshot_observed_at":"2026-08-06T13:25:53.501844Z","submitted_at":"2022-04-30T05:44:34Z","title":"Self-Programming Artificial Intelligence Using Code-Generating Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.00167","snapshot_observed_at":"2026-08-03T20:21:08.200185Z","title":"Self-programming artificial intelligence using code-generating language mod- els.arXiv preprint arXiv:2205.00167, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:08.200185Z"},"links":{"cited_paper":"/paper/2205.00167","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:8396815c08451265ef74f2d14fe954fec576b0441a7bcc01c91ac32b5a639bc4","observation_id":"d1aa4da8-e7c8-4422-b9e9-0d9101ca8213","resolution":{"observed_at":"2026-08-03T20:21:08.200185Z","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":"2026-08-03T20:21:08.444334Z","title":"Gomez, Lukasz Kaiser, and Illia Polosukhin","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:08.444334Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:0c78ef39797b68d0e0faa1f9b921f914c6e6ec6e2f69b4c537bdc916af44db21","observation_id":"ac956c22-3b2c-42b1-995a-b3f1bb73daf4","resolution":{"observed_at":"2026-08-03T20:21:08.444334Z","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":"2026-08-03T20:21:08.608095Z","title":"Grammar prompting for domain-specific lan- guage generation with large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:08.608095Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:43e265aa74826290fb31d428bad4cba71ddc73f6c78662c0fdcbf7522d95badb","observation_id":"7dedb6a9-bb8f-486a-9e70-550c674e4b87","resolution":{"observed_at":"2026-08-03T20:21:08.608095Z","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":"2026-08-03T20:21:08.835478Z","title":"How powerful are performance predictors in neural architecture search? InNeurIPS, pages 28454–28469,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:08.835478Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:201ab8664fc6f16427fc340044923b35699533c0a8eb8794be013fecccb5f96f","observation_id":"b87e18f8-a022-4cfb-9b6a-51693d2ab274","resolution":{"observed_at":"2026-08-03T20:21:08.835478Z","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":"2026-08-03T20:21:08.990955Z","title":"Pytorch image models (timm).https: / / github","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:08.990955Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:fcdf218f5008c30d58d7251c3f0522baf5b4c1bf42ed30c663b2c0dbdd160557","observation_id":"0c02213c-6d65-46ed-8f93-1f7431977bc4","resolution":{"observed_at":"2026-08-03T20:21:08.990955Z","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":"2026-08-03T20:21:09.144105Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.144105Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:7797e2f5f92fb6deca586e0a2622d56eeca9b18f2c81706d67c78f04cee55e70","observation_id":"f1800809-5ea0-491e-b115-82b123882bb5","resolution":{"observed_at":"2026-08-03T20:21:09.144105Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.12345","last_updated":"2023-10-18T21:43:37Z","snapshot_observed_at":"2026-07-06T16:35:19.728025Z","submitted_at":"2023-10-18T21:43:37Z","title":"ClusT3: Information Invariant Test-Time Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.12345","snapshot_observed_at":"2026-08-03T20:21:09.317478Z","title":"GPT-NAS: Generative pre-trained models for neu- ral architecture search.arXiv preprint arXiv:2310.12345,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.317478Z"},"links":{"cited_paper":"/paper/2310.12345","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:74053727f30d3026b84021856d656cbdd327d593a583b6dc187d9cecea4dd29c","observation_id":"29a9bb31-6e0e-460e-b678-f53181c73c0a","resolution":{"observed_at":"2026-08-03T20:21:09.317478Z","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":"2026-08-03T20:21:09.454980Z","title":"Cyclic differentiable architecture search","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.454980Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:f2ce0f4909d5dd3d15a1a63e2ebdb6db75f50ef177c8727e9f4899336fd8ef9e","observation_id":"46be1df0-7d39-4ae5-8a03-d19246fe3b1f","resolution":{"observed_at":"2026-08-03T20:21:09.454980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.04214","last_updated":"2026-08-05T09:43:46Z","snapshot_observed_at":"2026-08-06T13:43:18.755540Z","submitted_at":"2023-08-04T15:48:47Z","title":"On The Suitability of Differential Dataflow For Datalog Interpretation In Highly Dynamic Settings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.04214","snapshot_observed_at":"2026-08-03T20:21:09.565527Z","title":"Llm-assisted hyper- parameter tuning: A prompt-based approach.arXiv preprint arXiv:2308.04214, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.565527Z"},"links":{"cited_paper":"/paper/2308.04214","citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:433d6abd21a4d6853b05fed2e5a8d269d2f9c9acabfed5adb5143f90ddecb3ab","observation_id":"b4fe0827-3280-41f4-8f34-a528acbf9ebf","resolution":{"observed_at":"2026-08-03T20:21:09.565527Z","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":"2026-08-03T20:21:09.677884Z","title":"Places: A 10 million image database for scene recognition.IEEE Transactions on Pattern Anal- ysis and Machine Intelligence, 40(6):1452–1464, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.677884Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:5b53cf90b0f3416423731a1ee3427687866ed96f49861953a25c904f2df933e8","observation_id":"e201482c-9ed9-4929-a5b1-367c19cb118b","resolution":{"observed_at":"2026-08-03T20:21:09.677884Z","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":"2026-08-03T20:21:09.791210Z","title":"It also shows typical failure modes (e.g., schema violations, miss- ing functions) and how NNGPT surfaces them through the validator and executor stack","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.791210Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:baa17325f14a18ed465ebb6965c044dd7e07668db9cb6b7c63db2671a56011a2","observation_id":"bbc686f7-9762-4e8f-aa76-cbf367ddae1e","resolution":{"observed_at":"2026-08-03T20:21:09.791210Z","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":"2026-08-03T20:21:09.873943Z","title":"Below we review key methods from both domains, focusing on the limitations ad- dressed by NNGPT","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.873943Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:0040a42255abbe1c96066c68c1a6db52788d09679fd39648aeb79a3efcdfba1e","observation_id":"f9ec9bfd-52a2-495f-949d-94e7207cc794","resolution":{"observed_at":"2026-08-03T20:21:09.873943Z","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":"2026-08-03T20:21:09.984729Z","title":"It requires Python 3.10 or higher and CUDA for GPU-based training","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:09.984729Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:fd9326ef44c9e08253d779a810a616103c489cd20297909407fbb33e3f8c044f","observation_id":"015aed09-102e-4870-aeb9-671872009ad8","resolution":{"observed_at":"2026-08-03T20:21:09.984729Z","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":"2026-08-03T20:21:10.101643Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.101643Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:0e1230a52c15aaab85c314afc0aff30e9de5ae3ee917f3c46da360b199d4e26e","observation_id":"c3f58ab7-ec21-4bc6-a604-d20c9fbd49b4","resolution":{"observed_at":"2026-08-03T20:21:10.101643Z","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":"2026-08-03T20:21:10.214419Z","title":"DO NOT introduce new methods or parameters","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.214419Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:f12bb297ca5e73c5002b09db19eaec7ce8d2216c63a551c404a2ed58a94eaef0","observation_id":"544071d8-9b34-49f9-b218-b7afa537834e","resolution":{"observed_at":"2026-08-03T20:21:10.214419Z","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":"2026-08-03T20:21:10.358041Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.358041Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:036e36849a99b873f87ef7c4ecc8059468631613d0df77b79e503591fa941a8d","observation_id":"9cfe239d-7b69-43b6-8e7d-162ac3230b0c","resolution":{"observed_at":"2026-08-03T20:21:10.358041Z","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":"2026-08-03T20:21:10.496986Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.496986Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:b3a2389db652327cb388fb98f6397483b91d6dcc58467ffea2bee027516fc47a","observation_id":"d2080b0b-6e42-4ce4-af64-075affbdfec0","resolution":{"observed_at":"2026-08-03T20:21:10.496986Z","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":"2026-08-03T20:21:10.584331Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.584331Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:1ea0aadba51e460ad941938324c179053a742e63122af8a9ca062b301a007e4b","observation_id":"f5ab785d-3016-4e3c-880b-9a294ddacf4b","resolution":{"observed_at":"2026-08-03T20:21:10.584331Z","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":"2026-08-03T20:21:10.696738Z","title":"Here is the input code for you to modify: ’’’\\n{nn_code}\\n’’’ Listing 1","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.696738Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:e4fe236f21f39fec32149c71ba5d4f70456d92a77f1d9c6c79ec95459ecb2389","observation_id":"4dec4b9c-b43c-4a88-b434-da7fc902715d","resolution":{"observed_at":"2026-08-03T20:21:10.696738Z","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":"2026-08-03T20:21:10.865782Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:10.865782Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:a5ca6831ae7870954cc5fc417efb3ee25b76462448425a00391d4fb4d852c9fc","observation_id":"63bede1d-580f-4631-a045-d2e7d1b038d7","resolution":{"observed_at":"2026-08-03T20:21:10.865782Z","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":"2026-08-03T20:21:11.020365Z","title":"- DO NOT introduce new methods or parameters","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.020365Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:f789c3480c4b16dbf284588725ea41eac32947f04eb52947f195bdef3df4801b","observation_id":"ad680ca9-1236-46bf-b098-6c7abcd198ee","resolution":{"observed_at":"2026-08-03T20:21:11.020365Z","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":"2026-08-03T20:21:11.127384Z","title":"- Indicate the modified class explicitly","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.127384Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:2345bb8bfd0ce6e32cd8f79ce7bb6904ec7f781903314f9ad6a96493df37bca4","observation_id":"b2070d9c-eebf-476e-bfbe-dd482338f51a","resolution":{"observed_at":"2026-08-03T20:21:11.127384Z","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":"2026-08-03T20:21:11.269362Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.269362Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:b61d29b4f6c2274d78b79914246a8f694f5684447685bfdd0a3b3629ca1f684d","observation_id":"2c87125d-19f3-4aa2-9ce9-4f7b40b54b9d","resolution":{"observed_at":"2026-08-03T20:21:11.269362Z","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":"2026-08-03T20:21:11.386809Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.386809Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:17b713908c7733a1d50396a1e59eb60fcd4a118479b993f86f63c6970995a2b1","observation_id":"063fac67-eefa-46dc-bade-8a6370cdfe96","resolution":{"observed_at":"2026-08-03T20:21:11.386809Z","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":"2026-08-03T20:21:11.497221Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.497221Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:2646378d1d1eab449a862b4552e0fd955286bf0a8752c91315b3b30bc6f345f0","observation_id":"de925e55-d8a6-4205-ab14-60b58edd6d93","resolution":{"observed_at":"2026-08-03T20:21:11.497221Z","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":"2026-08-03T20:21:11.630523Z","title":"### Response:","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.630523Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:13e76c28b4e893c79d46ebb09c21b277386dd4ca921cb27d4f4b3fbac1253b34","observation_id":"687eb07d-aff2-4e8b-8ed7-f22eea807110","resolution":{"observed_at":"2026-08-03T20:21:11.630523Z","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":"2026-08-03T20:21:11.691407Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-03T20:21:11.691407Z"},"links":{"citing_paper":"/paper/2511.20333"},"observation_digest":"sha256:678201202933e115e4c40c0546eec07361c5fddfa66769f2fa3461109120be45","observation_id":"965aa4e7-677e-4e3f-8b44-abb2c1516980","resolution":{"observed_at":"2026-08-03T20:21:11.691407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2511.20333","last_updated":"2025-11-25T14:10:44Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-03T20:21:00.893019Z","submitted_at":"2025-11-25T14:10:44Z","title":"NNGPT: Rethinking AutoML with Large Language Models"},"reference_resolution":{"displayed":76,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":76,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":76},"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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"thesis":"As of 6 August 2026, this Paper Citation Record lists 76 of 76 outbound references and 4 inbound Pith citation observations for arXiv:2511.20333."}