{"as_of":"2026-08-21T23:12:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:68a63f79703c64e1996188f74e3103428e068d7a28766bc95651689f5e498994","coverage":[{"denominator":129,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:46:50.968546Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2506.07109/citation-record","integrity":"/paper/2506.07109/integrity","json":"/paper/2506.07109/citation-record.json","paper":"/paper/2506.07109"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:50.490177Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.490177Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:89567b7e9e0489b3eaafda2c5128f718cd4253d085495f81c40d3d11de0cd6bf","observation_id":"66b2fe41-cfab-472e-89cd-bd90be7ab621","resolution":{"observed_at":"2026-08-07T05:46:50.490177Z","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":"2026-08-07T05:46:50.497161Z","title":"ROBEL : R obotics benchmarks for learning with low-cost robots","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.497161Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:0b6ced89ab9d5559f391acb3420bc2c4786cfd8f2e955589af0e7f27bdd1e0fe","observation_id":"33a919d5-6a6c-4a39-909b-e693e01fdf74","resolution":{"observed_at":"2026-08-07T05:46:50.497161Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.13673","last_updated":"2025-05-19T11:12:27Z","snapshot_observed_at":"2026-08-18T16:00:47.608550Z","submitted_at":"2023-05-23T04:28:16Z","title":"Physics of Language Models: Part 1, Learning Hierarchical Language Structures","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.13673","snapshot_observed_at":"2026-08-07T05:46:50.502926Z","title":"and Li, Y","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.502926Z"},"links":{"cited_paper":"/paper/2305.13673","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:3008d78fdc477b0e8602a4e44b961561fa689051c09fcd6bcee694bd58fcd432","observation_id":"b8de66ac-afab-4682-88a5-9eb397a2530d","resolution":{"observed_at":"2026-08-07T05:46:50.502926Z","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":"2026-08-07T05:46:50.508645Z","title":"The Claude 3 model family: Opus, Sonnet, Haiku","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.508645Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:0a898c56bce0273b736a41c78e73965e1b07f61768aaca1c3252958e6be1942a","observation_id":"e7235103-f95e-4655-889a-7fb66c2133ff","resolution":{"observed_at":"2026-08-07T05:46:50.508645Z","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":"2026-08-07T05:46:50.513800Z","title":"Evolutionary Algorithms in Theory and Practice: Evolution Strategies, Evolutionary Programming, Genetic Algorithms","venue":null,"work_id":null,"year":1996},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.513800Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:039c4644e9b1fc307681282d111d5cb2520882869ea245a697f422baec1eed1c","observation_id":"9fd3f527-433b-4e04-8ecf-dc89c5ac0046","resolution":{"observed_at":"2026-08-07T05:46:50.513800Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.05927","last_updated":"2023-02-12T14:37:25Z","snapshot_observed_at":"2026-08-16T15:55:57.208926Z","submitted_at":"2023-02-12T14:37:25Z","title":"Transfer Learning for Bayesian Optimization: A Survey","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.05927","snapshot_observed_at":"2026-08-07T05:46:50.519015Z","title":"Transfer learning for B ayesian optimization: A survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.519015Z"},"links":{"cited_paper":"/paper/2302.05927","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:68aa24e151caff5ce25864bb24af330e9ae2d919948d4415aa8269a470d00d09","observation_id":"cc8d825f-5f93-4a47-939c-94bf9ccf5d42","resolution":{"observed_at":"2026-08-07T05:46:50.519015Z","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":"2026-08-07T05:46:50.524757Z","title":"R., Daulton, S., Letham, B., Wilson, A","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.524757Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f50ec7eea3277c4cbe192bbd8636c63cb5134f56703a36c1b4cd8d5a2124f5d1","observation_id":"e0890a54-d18e-4377-be60-cac8e18cfae2","resolution":{"observed_at":"2026-08-07T05:46:50.524757Z","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":"2026-08-07T05:46:50.530494Z","title":"A., Vedenko, A., Kurland, J","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.530494Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:849021cc77192b359e57f3de8710901283c0e2e998fdbe0308e78788b7874af2","observation_id":"221b7ce2-47ac-4034-a15c-91d89e6476c0","resolution":{"observed_at":"2026-08-07T05:46:50.530494Z","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":"2026-08-07T05:46:50.535486Z","title":"and Deb , K","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.535486Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:052a13d5dc1ba8e8a65cfeebeac2f5aae14ff035eb821f286a0dc5f440bab548","observation_id":"57f104e6-ded3-4caf-a451-d67403a4516f","resolution":{"observed_at":"2026-08-07T05:46:50.535486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.01540","last_updated":"2016-06-05T17:54:48Z","snapshot_observed_at":"2026-08-13T12:26:05.192883Z","submitted_at":"2016-06-05T17:54:48Z","title":"OpenAI Gym","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.01540","snapshot_observed_at":"2026-08-07T05:46:50.540416Z","title":"Open AI G ym","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.540416Z"},"links":{"cited_paper":"/paper/1606.01540","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f25a0bf3de1d7b383f903a2c21d24fb6d1fb8c59304ab62ed92836d5969db5f4","observation_id":"8896a356-2f3d-40a1-baee-d7767ba2e430","resolution":{"observed_at":"2026-08-07T05:46:50.540416Z","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":"2026-08-07T05:46:50.545430Z","title":null,"venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.545430Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:8d5d6f9f38325e9d7713f074ba6db67366d4092619845fa87bc04eae2592bb77","observation_id":"1d8e87a9-039c-4e82-9588-d9a122adfd97","resolution":{"observed_at":"2026-08-07T05:46:50.545430Z","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":"2026-08-07T05:46:50.550372Z","title":"Linear algebra with T ransformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.550372Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f2078a8e6d8a153d21f79153068bff27f8249e256418cceac8a6f8bbc79eaede","observation_id":"dc3eb461-372a-4748-b63c-248ab056318a","resolution":{"observed_at":"2026-08-07T05:46:50.550372Z","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":"2026-08-07T05:46:50.555209Z","title":"N., and Doppa, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.555209Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:fbfcfa98a82f02d6ff6a8da91a7f84bad5118c1c230284aa234469b1dd023c82","observation_id":"656ef425-2805-47d1-8b6b-f0bbb6b493b8","resolution":{"observed_at":"2026-08-07T05:46:50.555209Z","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":"2026-08-07T05:46:50.559673Z","title":"Robust guided diffusion for offline black-box optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.559673Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:887e71d386396abd5891dd461ea20d136f49f5bde399c7d7ebe53e41167b23e9","observation_id":"35e9264f-0d44-4745-a97e-b05c4f6bba34","resolution":{"observed_at":"2026-08-07T05:46:50.559673Z","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":"2026-08-07T05:46:50.564285Z","title":"S., Zhang, Y., Fu, J., Liu, X","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.564285Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:d725d457660af146c7b41d49517323c14c4dda903fb7cce5bce1ef7bfddefcd3","observation_id":"e7edf9be-f754-4092-aa44-f62f02497b3b","resolution":{"observed_at":"2026-08-07T05:46:50.564285Z","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":"2026-08-07T05:46:50.569074Z","title":"S., Beckham, C., Liu, Z., Liu, X","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.569074Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:79cbb4f4c20718d5ff441f32b5ea483ed2ad4300cc5230765e59370057793cc3","observation_id":"90b20739-3b0f-4a30-8229-dd2b2c4e2baa","resolution":{"observed_at":"2026-08-07T05:46:50.569074Z","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":"2026-08-07T05:46:50.573701Z","title":"S., Zhang, Y., Liu, X","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.573701Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f0798b94f74d601804dab9838d0cc71ef4606aa1002994e98409690de9321dca","observation_id":"d9ae7634-54e4-47b8-ae6e-c9dcd1a833d9","resolution":{"observed_at":"2026-08-07T05:46:50.573701Z","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":"2026-08-07T05:46:50.578377Z","title":"A simple framework for contrastive learning of visual representations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.578377Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:3ab5ee0028694807b4efead0e16ef5225a38fb233d7f8de0368127f4908ae9f4","observation_id":"0811fa3f-ef0d-49e3-b872-eb0c13033cca","resolution":{"observed_at":"2026-08-07T05:46:50.578377Z","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":"2026-08-07T05:46:50.583128Z","title":"Towards learning universal hyperparameter optimizers with T ransformers","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.583128Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:d56b1c865641a612a5db88d57564f163c41492c6e5e1aea3293012aa4ab2c173","observation_id":"de4992fc-bf18-4b0e-8c67-c1896cdd9e7c","resolution":{"observed_at":"2026-08-07T05:46:50.583128Z","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":"2026-08-07T05:46:50.588109Z","title":"G rad N orm: G radient normalization for adaptive loss balancing in deep multitask networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.588109Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:089742b2f36074b4be5a38c99ece982c8e89bfc1a0b7107fab651d44d11bc73d","observation_id":"3b627e41-78ed-43d4-996a-36ebf5d0811f","resolution":{"observed_at":"2026-08-07T05:46:50.588109Z","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":"2026-08-07T05:46:50.592793Z","title":"C., Nguyen, P","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.592793Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:6335816226c44a93a69b7c1ec2626938a0ac48a2e5f9244e26dbf129a2ca2def","observation_id":"38ad414d-a876-4f17-9190-d66f205ba38f","resolution":{"observed_at":"2026-08-07T05:46:50.592793Z","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":"2026-08-07T05:46:50.597472Z","title":"C., Nguyen, P","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.597472Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:720562cb6669ec1d911b02ae4cd61ddbecc02481e30b4b5f9f60450975c2602f","observation_id":"acb9ca31-8328-4461-8866-132b62f6b617","resolution":{"observed_at":"2026-08-07T05:46:50.597472Z","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":"2026-08-07T05:46:50.602041Z","title":"S., Babu, C","venue":null,"work_id":null,"year":1947},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.602041Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:e668f8d28841a34238eb07da227f21597eeb42caf6932aa00b7484dd20334605","observation_id":"cb273cca-c55a-450d-b411-760d25685efb","resolution":{"observed_at":"2026-08-07T05:46:50.602041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.12948","last_updated":"2026-01-04T03:57:36Z","snapshot_observed_at":"2026-08-15T12:33:55.451951Z","submitted_at":"2025-01-22T15:19:35Z","title":"DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.12948","snapshot_observed_at":"2026-08-07T05:46:50.606800Z","title":"DeepSeek-R1 : I ncentivizing reasoning capability in LLMs via reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.606800Z"},"links":{"cited_paper":"/paper/2501.12948","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:857a9fcad44184417e1ac8244a533065a30143640253cd36bd24387c71a67a16","observation_id":"5fe20fb4-2ba9-4b29-b5b1-04e7d850d3a2","resolution":{"observed_at":"2026-08-07T05:46:50.606800Z","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":"2026-08-07T05:46:50.611613Z","title":"M., Friesen, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.611613Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:eb9f31c984ceeadcdd1cc7641ba44c37afae71e94ef150e0c389fe5e393e9ebb","observation_id":"bca0c9e5-1db2-4605-90cf-4895dca86b3f","resolution":{"observed_at":"2026-08-07T05:46:50.611613Z","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":"2026-08-07T05:46:50.616496Z","title":"Transfer learning for B ayesian optimization on heterogeneous search spaces","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.616496Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:b2ae58859583378ab157203b5411b4810fdc13ca0587cf640c45ae705374e5c2","observation_id":"66f99325-3154-4ada-9fcd-ce5a60fb24ba","resolution":{"observed_at":"2026-08-07T05:46:50.616496Z","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":"2026-08-07T05:46:50.621217Z","title":"and Listgarten, J","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.621217Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:59c1d80faaae418a40ad4639944d5a2c9deca9cd4142fb9a189f80f98e72088b","observation_id":"2cf024f8-45e3-4bc2-b47b-3037379b266e","resolution":{"observed_at":"2026-08-07T05:46:50.621217Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.02811","last_updated":"2018-07-08T13:06:26Z","snapshot_observed_at":"2026-08-18T00:58:48.914606Z","submitted_at":"2018-07-08T13:06:26Z","title":"A Tutorial on Bayesian Optimization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.02811","snapshot_observed_at":"2026-08-07T05:46:50.625821Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.625821Z"},"links":{"cited_paper":"/paper/1807.02811","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:3283ae8ecd79b0eb8c8489729775e2de17540ba05c4fc646c278e9ddb4ddd61f","observation_id":"5843be38-8518-4c22-9319-6c8ade65e492","resolution":{"observed_at":"2026-08-07T05:46:50.625821Z","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":"2026-08-07T05:46:50.630809Z","title":"and Levine, S","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.630809Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:7fd553e3153914bc123f8a8b3eda831e2104ffbbceef640c771f39db9d5734ac","observation_id":"72423144-ac0c-4d9a-9dc8-448c6c818eae","resolution":{"observed_at":"2026-08-07T05:46:50.630809Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.01956","last_updated":"2025-06-27T17:15:09Z","snapshot_observed_at":"2026-08-19T21:07:25.964858Z","submitted_at":"2025-01-03T18:59:23Z","title":"Metadata Conditioning Accelerates Language Model Pre-training","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.01956","snapshot_observed_at":"2026-08-07T05:46:50.635514Z","title":"Metadata conditioning accelerates language model pre-training","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.635514Z"},"links":{"cited_paper":"/paper/2501.01956","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f9e67614bdd6cc83e08b3fee4425e75b3094b58d95b6adaf06c124027697e13e","observation_id":"1d30adb7-d191-4790-a90a-f7355e50c89a","resolution":{"observed_at":"2026-08-07T05:46:50.635514Z","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":"2026-08-07T05:46:50.641256Z","title":"S., and Valiant, G","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.641256Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:bd01f72a27bb8b94bdb5d64ae69b4d8c07dabf960b6732b97e28ba50a0c03c09","observation_id":"374560e3-76a4-43fe-aaf7-4a869a6ad9bd","resolution":{"observed_at":"2026-08-07T05:46:50.641256Z","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":"2026-08-07T05:46:50.645829Z","title":"W., Rezende, D., and Eslami, S","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.645829Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:ab74e08bdc6c894bc53150a1c0b21d5f8ad2eacba173896947304051b473acea","observation_id":"25aa5a80-fc11-480a-8dd7-ffb8e9a6a638","resolution":{"observed_at":"2026-08-07T05:46:50.645829Z","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":"2026-08-07T05:46:50.650530Z","title":"B ayesian Optimization","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.650530Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:03efba5706553a9d520480841a99c83d419b4303d7231f48ab43c83ea8060a82","observation_id":"7d679e1d-d8da-43a8-82b2-7d2d1f3af2ce","resolution":{"observed_at":"2026-08-07T05:46:50.650530Z","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":"2026-08-07T05:46:50.655586Z","title":"A., and Hennig, P","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.655586Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:6aa1007c1f13dcae95d6cc853b5328cd8dfb45ec4ed32e30f765a798fa57ba73","observation_id":"05b1de14-92e7-4923-bbee-fd1b6b364b98","resolution":{"observed_at":"2026-08-07T05:46:50.655586Z","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":"2026-08-07T05:46:50.660385Z","title":"J., Bento, A","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.660385Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:be9fa6c982e350a3de3d9b01d057ba52e197c7a85691f338feadfc2ef18dd879","observation_id":"aaef6bd0-835a-419c-bd2b-28dae6ab71a3","resolution":{"observed_at":"2026-08-07T05:46:50.660385Z","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":"2026-08-07T05:46:50.665007Z","title":"S.-H., Shi, Y.-H., and Zhang, J","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.665007Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:5f6f36ec54114bc6677f03c14a7ecaf6e816da14aff1c431d926a45f24f57620","observation_id":"edef43bc-3804-43e2-941d-81666a35a499","resolution":{"observed_at":"2026-08-07T05:46:50.665007Z","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":"2026-08-07T05:46:50.669448Z","title":"Generative adversarial networks","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.669448Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:0c4e6b965bb6b1b94118337dd4208111ae0da554e69fcfcf79050891dd98f372","observation_id":"eb6ad50a-67f3-4190-836a-39f5120a0ec1","resolution":{"observed_at":"2026-08-07T05:46:50.669448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.05905","last_updated":"2019-01-29T12:10:47Z","snapshot_observed_at":"2026-08-17T07:51:41.384508Z","submitted_at":"2018-12-13T04:44:29Z","title":"Soft Actor-Critic Algorithms and Applications","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.05905","snapshot_observed_at":"2026-08-07T05:46:50.674061Z","title":"Soft actor-critic algorithms and applications","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.674061Z"},"links":{"cited_paper":"/paper/1812.05905","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:8a1d5e2258352410eea5ac4a444efc636011deec4191dc6a96bae50f4f0df39a","observation_id":"471d5b87-67f0-4e4e-8eca-0322fa44fdbe","resolution":{"observed_at":"2026-08-07T05:46:50.674061Z","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":"2026-08-07T05:46:50.678895Z","title":"A data-driven statistical model for predicting the critical temperature of a superconductor","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.678895Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:67d54feb30589e4053ab89496552ed1a49a57c6cb0e2720a4066e751ee431de4","observation_id":"e86fa803-e6e1-4c1a-82c0-8765f9d63b74","resolution":{"observed_at":"2026-08-07T05:46:50.678895Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1604.00772","last_updated":"2023-03-10T09:45:23Z","snapshot_observed_at":"2026-08-16T12:36:28.312560Z","submitted_at":"2016-04-04T08:16:12Z","title":"The CMA Evolution Strategy: A Tutorial","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1604.00772","snapshot_observed_at":"2026-08-07T05:46:50.683363Z","title":"The CMA evolution strategy: A tutorial","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.683363Z"},"links":{"cited_paper":"/paper/1604.00772","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:dd20e637ee1ac3a331c47f4c487d55ecaedb0f39f1836dd694a9a4a65feb5561","observation_id":"27a9356a-9260-4edf-b3a2-c651b1135c7e","resolution":{"observed_at":"2026-08-07T05:46:50.683363Z","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":"2026-08-07T05:46:50.688216Z","title":"V., and Auger, A","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.688216Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f2b27e2201b457f150b6901599e86134412a708ae3994128a1c6b0cb3b1cf59a","observation_id":"ef9bb0ad-78cf-42a3-bdc7-d74386fb73d1","resolution":{"observed_at":"2026-08-07T05:46:50.688216Z","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":"2026-08-07T05:46:50.693850Z","title":"MetaBalance : I mproving multi-task recommendations via adapting gradient magnitudes of auxiliary tasks","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.693850Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:46eb758f53aa01b41535e72aa815fcf6e384258dbb2cf5c0df212679300b6d02","observation_id":"3e2bbd4e-7ffc-4925-b5b1-06a95015b1a0","resolution":{"observed_at":"2026-08-07T05:46:50.693850Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1207.0580","last_updated":"2012-07-03T06:35:15Z","snapshot_observed_at":"2026-08-15T00:54:35.320150Z","submitted_at":"2012-07-03T06:35:15Z","title":"Improving neural networks by preventing co-adaptation of feature detectors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1207.0580","snapshot_observed_at":"2026-08-07T05:46:50.698302Z","title":"E., Srivastava, N., Krizhevsky, A., Sutskever, I., and Salakhutdinov, R","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.698302Z"},"links":{"cited_paper":"/paper/1207.0580","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:fcfe3db9a531e9317e5362913b71660abb5e3149d9fb3b29272ce8176c2237e1","observation_id":"4cc7245f-074b-47ea-a8b3-507b58c98154","resolution":{"observed_at":"2026-08-07T05:46:50.698302Z","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":"2026-08-07T05:46:50.703079Z","title":"Denoising diffusion probabilistic models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.703079Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:1a03284c48828092e303eda53557acbcd87c2508e5c49cc300a38009b0efab99","observation_id":"41efb133-4e60-4a41-9844-4e943c6b2a64","resolution":{"observed_at":"2026-08-07T05:46:50.703079Z","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":"2026-08-07T05:46:50.707714Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.707714Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:b52ea17c2d8092bd698925debd29540fca7d2aef1883cf1f4c136b13a034c49c","observation_id":"8b3750b4-e129-4164-beaf-3929aead74a1","resolution":{"observed_at":"2026-08-07T05:46:50.707714Z","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":"2026-08-07T05:46:50.712289Z","title":"u ller, S., Purucker, L., Krishnakumar, A., K \\","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.712289Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:938d777fa47a6dc9027591d34b9d1bbb2df1a36ea87c4ba5f5284241e8656b5e","observation_id":"10321f19-9e89-4cd1-967d-6813155f58dd","resolution":{"observed_at":"2026-08-07T05:46:50.712289Z","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":"2026-08-07T05:46:50.716988Z","title":"BO : A ugmenting acquisition functions with user beliefs for B ayesian optimization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.716988Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:c77d655eae8f1f2a940719205c311794b5874b1cdf3d175ec0fb4c65380f64d7","observation_id":"2a3aca31-e59a-46ef-8100-7bb9edc02027","resolution":{"observed_at":"2026-08-07T05:46:50.716988Z","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":"2026-08-07T05:46:50.721440Z","title":"A general framework for user-guided B ayesian optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.721440Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:8c28e3ce1a06d26644e027777fdbb7e00f99a1998dbddba9dca32df9c3620f83","observation_id":"13946176-b0fe-4ec8-b767-09ff00ae31a6","resolution":{"observed_at":"2026-08-07T05:46:50.721440Z","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":"2026-08-07T05:46:50.726003Z","title":"Global Optimization and Space Pruning for Spacecraft Trajectory Design , pp.\\ 178--199","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.726003Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:8f1a73372f6253e2e1f8ca5c11e8edb755657c1bc46813f9f461b6a606b8ff7f","observation_id":"71ca837c-8c56-442a-85a2-a9e7eecbbda2","resolution":{"observed_at":"2026-08-07T05:46:50.726003Z","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":"2026-08-07T05:46:50.731052Z","title":"and Manuel L \\' o pez-Ib \\' a \\ n ez, M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.731052Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:0b89822126cebfa9e27f206c1f505cb18b1de453c9a14b63af5487c8bc558525","observation_id":"2c7ed28b-52a5-4dbb-96b6-2e1c28ae8d9f","resolution":{"observed_at":"2026-08-07T05:46:50.731052Z","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":"2026-08-07T05:46:50.735643Z","title":"LLMOPT : L earning to define and solve general optimization problems from scratch","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.735643Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:6fa11c1a9c2729dcc2c8da933742db60d02593108639e0a1b25878ff4634c665","observation_id":"dcf0824e-70a2-4cc6-bd34-5dfa316d3ba5","resolution":{"observed_at":"2026-08-07T05:46:50.735643Z","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":"2026-08-07T05:46:50.740109Z","title":"and Eberhart, R","venue":null,"work_id":null,"year":1942},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.740109Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:082350f0b37b5ff4469de47947e47e1bfd5e9e4fd9d14487cc113b38264ae761","observation_id":"22fd3850-e3df-41d7-9ea6-644506a74fd6","resolution":{"observed_at":"2026-08-07T05:46:50.740109Z","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":"2026-08-07T05:46:50.744648Z","title":"I., Grosnit, A., Deik, D.-G.-X., Robert, P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.744648Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:031f9b7c0e189ce95082e546df53d9d15ed528b2acd323314a7b44cd7e9ed8cd","observation_id":"37e64a08-5b4e-4272-9fda-489314c5c302","resolution":{"observed_at":"2026-08-07T05:46:50.744648Z","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":"2026-08-07T05:46:50.749174Z","title":"Bootstrapped training of score-conditioned generator for offline design of biological sequences","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.749174Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:11e687c22ff8480bfe400377b84e809dd63e9250ec5e91eec00c02392776a782","observation_id":"d0038105-c51d-431e-bbbb-539c9bfc93fd","resolution":{"observed_at":"2026-08-07T05:46:50.749174Z","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":"2026-08-07T05:46:50.753555Z","title":"Offline model-based optimization: C omprehensive review","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.753555Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:61e38913f636fb4b1794d8e61829b4f08e11567f775df405f7d947d9892ef95a","observation_id":"92f0d48a-3531-4c26-987c-b359c350b1a6","resolution":{"observed_at":"2026-08-07T05:46:50.753555Z","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":"2026-08-07T05:46:50.758199Z","title":"D., Wu, D., Wang, H., Ferber, A., Ma, Y.-A., Gomes, C","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.758199Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:afdfa8a2ef8c458a9e13874e9e03e3840e4a962e4c95b7afd87643c2270abd9c","observation_id":"2e6fd2ee-c192-48a9-bd20-bdba3c1e69fb","resolution":{"observed_at":"2026-08-07T05:46:50.758199Z","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":"2026-08-07T05:46:50.762328Z","title":"M., and Grover, A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.762328Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:73a01ad7c0f36bdd9da3640145dc81f9aa6c90a21ae141d939fb7f3a407eae9f","observation_id":"7fe35e5d-10d9-4e70-ba11-2cfb3af597ed","resolution":{"observed_at":"2026-08-07T05:46:50.762328Z","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":"2026-08-07T05:46:50.767105Z","title":"G., Abbeel, P., and Levine, S","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.767105Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:67219ddcfa85279e3316edc36faf21a71044e7a91fcb3ab2756cf3973271dbe3","observation_id":"acc63c32-0d0c-4d46-a990-850e49ffacbd","resolution":{"observed_at":"2026-08-07T05:46:50.767105Z","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":"2026-08-07T05:46:50.771622Z","title":"G., Uehara, M., Levine, S., and Abbeel, P","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.771622Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:b79b6ea586c052fdacde101ef369fe4704f9213ac2e75d6cee7b23708c7010e2","observation_id":"2ffa4941-1aff-4e74-92e6-bf1d06d1844b","resolution":{"observed_at":"2026-08-07T05:46:50.771622Z","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":"2026-08-07T05:46:50.776204Z","title":"and Richardson, J","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.776204Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:e354eb99183079790957d94c12b9a395f38fd7e34147c7689ff8b2ff460c1855","observation_id":"e417f9fd-5cfc-40c3-b3be-7eb24ce4e149","resolution":{"observed_at":"2026-08-07T05:46:50.776204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.664796Z","title":"and Levine, S","venue":null,"work_id":"e0db3616-be8d-4393-b863-149f2986a860","year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.780655Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:72c42e12c75550f216c4983e490aa22d73bf0e298de9665958c76cbb87b93a11","observation_id":"cc7032a0-7dd0-46dc-84a1-59238bfc6762","resolution":{"observed_at":"2026-08-07T05:46:52.669592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.648215Z","title":"Data-driven offline optimization for architecting hardware accelerators","venue":null,"work_id":"f435c445-3ca9-4774-9d04-250f9368fd77","year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.785477Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:4802db5cc6482874a2c0191eee2cdab77258cef49f4913e4714f7ee4a11e1b4f","observation_id":"b3204e25-6862-4352-9106-8669737e684f","resolution":{"observed_at":"2026-08-07T05:46:52.653509Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.631137Z","title":null,"venue":null,"work_id":"e0ba80fc-ccd3-44c7-a4b6-3e06452cefa4","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.790177Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:b3936d04b60d3ff94cd7691d86ba75ea2b38b12599543f6e5abea77ccd086ca7","observation_id":"6cc894d4-74d2-4424-9ca0-f2f186d3c8b5","resolution":{"observed_at":"2026-08-07T05:46:52.636623Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.615574Z","title":null,"venue":null,"work_id":"41837691-d56a-405b-b1c8-9262a91e0833","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.794753Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:cb28dfcbc97c42c38b24a5aa2c17f7ea8e8d191cb0e1b16d9753d5f34cf534d2","observation_id":"68353828-f2c0-4f92-b66b-94e0f0749519","resolution":{"observed_at":"2026-08-07T05:46:52.620466Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.601183Z","title":null,"venue":null,"work_id":"515480dd-2c52-4887-a72f-0fc79d198514","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.799342Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:3bbb6eb281affdf439ccab68cb12bb5cf038e3052216c630735efaf30e711e3a","observation_id":"8d55afd6-eaf3-4680-b49b-00328cc37c0a","resolution":{"observed_at":"2026-08-07T05:46:52.605686Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.585694Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"7d6f5856-1c47-4bcd-807d-1f1c3f424bc3","year":2021},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.804107Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:1371f1811e981fff6db0a8152318227bf1a984af1d0d91101c14758a181e98ba","observation_id":"861b1b3b-d807-4ef4-bd47-14ecb1ac7cf2","resolution":{"observed_at":"2026-08-07T05:46:52.590621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.570348Z","title":"C., Hutter, F., Feurer, M., and Bischl, B","venue":null,"work_id":"58fb4b9e-3ea6-4b41-9b4c-9bfbc281d824","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.808930Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:b2d6b6ebdea6298becbc5b7389a4f03febf0acf99cde7059de552cbe7050ada5","observation_id":"f9938b15-e455-4cbc-b6ee-b3c34182c8e8","resolution":{"observed_at":"2026-08-07T05:46:52.575189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.555771Z","title":"Evolution of heuristics: T owards efficient automatic algorithm design using large language model","venue":null,"work_id":"148331a9-2dbb-47c8-a265-fc78bd99119a","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.813472Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f1f841342e93484d7227b17fd03cb5175ba97fb9c40157f3b4e357d3231aaaa3","observation_id":"c1e485b2-c358-43cc-8fe7-2ffd0ba06a0d","resolution":{"observed_at":"2026-08-07T05:46:52.560508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:50.817895Z","title":"A systematic survey on large language models for algorithm design","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.817895Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:4ea1a5a903703bc84f6c02c437d9a7538ccb0f7a12a7caa326a74e85d345056a","observation_id":"6e91c608-ac11-486c-9b4a-8e2852057a75","resolution":{"observed_at":"2026-08-07T05:46:50.817895Z","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":"2026-08-07T05:46:50.822431Z","title":"LLM4AD : A platform for algorithm design with large language model","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.822431Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:2a770ad36b251710d8c672e5bf3657a239ef69ea6826117f1720bd712fbd747d","observation_id":"a933e565-db59-4f93-a425-9cc5835deb84","resolution":{"observed_at":"2026-08-07T05:46:50.822431Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.541235Z","title":"J., Saleh, M., Pot, E., Goodrich, B., Sepassi, R., Kaiser, L., and Shazeer, N","venue":null,"work_id":"df5c42eb-48b3-46bf-98f6-b510fb89bd51","year":2018},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.827099Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:f362a3ce95d619862693fe2bd8d91d25b45cb578a2d2fc59a6b3b7b076c4eb32","observation_id":"aeb409e7-9e10-4186-b45a-e2ebe42a93a9","resolution":{"observed_at":"2026-08-07T05:46:52.546016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.526981Z","title":"Large language models to enhance B ayesian optimization","venue":null,"work_id":"c4f3fcc0-0a52-45ae-94f9-8c69227954bf","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.831834Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:84f2bdef4466fb8b8ec26a538b18e7c9babe2353c514ef08a82a0b94e4c304ab","observation_id":"8719976b-779d-4b2c-ae53-ee6b0e88ef6a","resolution":{"observed_at":"2026-08-07T05:46:52.531725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.512129Z","title":"and Hutter, F","venue":null,"work_id":"9d8b8f87-64cf-4948-a8bf-ccdfab6c6ab6","year":2019},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.836562Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:a9edc96a0ca4160bd0742a4dffc5185c0d175b46f1acad12b502b73c2dde82a8","observation_id":"655d6ab9-46a9-4e70-91cd-c8ea4bdcc9d6","resolution":{"observed_at":"2026-08-07T05:46:52.516817Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.496623Z","title":"Degradation-resistant offline optimization via accumulative risk control","venue":null,"work_id":"696b37d7-cefc-4043-b9b0-6e14b1672900","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.841333Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:23d6f29698711d74465bb301db920cfd56104501d2d48dc36ca8402b1d386c0f","observation_id":"895cd0c5-7d9e-460a-b00b-82037f85d083","resolution":{"observed_at":"2026-08-07T05:46:52.501478Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01131","last_updated":"2024-03-05T11:11:41Z","snapshot_observed_at":"2026-08-18T15:06:41.915299Z","submitted_at":"2024-03-02T08:21:59Z","title":"LLaMoCo: Instruction Tuning of Large Language Models for Optimization Code Generation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01131","snapshot_observed_at":"2026-08-07T05:46:50.845870Z","title":"LLaMoCo : I nstruction tuning of large language models for optimization code generation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.845870Z"},"links":{"cited_paper":"/paper/2403.01131","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:6a8591c671d2255a95a68ee5b602dfc89150da57f5a9eb565ef7dce9a61e5d14","observation_id":"d50dbff0-6b9a-42f6-9d44-21fda8af08f0","resolution":{"observed_at":"2026-08-07T05:46:50.845870Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.481550Z","title":null,"venue":null,"work_id":"1f84bc85-f730-4be4-b819-47507d3710ac","year":2008},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.850862Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:79fff7daeacb1d98f809e7dc7be2bb4963d694a2d9658171adc61cedc7a78ca2","observation_id":"5442e2df-620f-41c8-94ce-1b2f8f7f5c44","resolution":{"observed_at":"2026-08-07T05:46:52.486338Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.466359Z","title":null,"venue":null,"work_id":"1c308737-8573-4c78-804e-062b718d39b5","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.855779Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:06ba0a41a3787ac5420983ec2326a30dcf6920ea83f2da7dea625bb1ddbb3556","observation_id":"fc04e0f7-bfef-47fd-8843-4464f0f41af1","resolution":{"observed_at":"2026-08-07T05:46:52.471371Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.451375Z","title":"M., Krishnamoorthy, S., and Grover, A","venue":null,"work_id":"2aa41c55-9801-4cb4-a587-4562769caf60","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.860596Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:3240de2c2065bfd3200876464748e2a0ba06fe45c02ff6579e29e2e0f7371988","observation_id":"f5254b0d-8726-4b53-82d6-5afaf682d47c","resolution":{"observed_at":"2026-08-07T05:46:52.456183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.436091Z","title":"P., Grabocka, J., and Hutter, F","venue":null,"work_id":"44881f63-43b1-43d8-97d5-2c83ce3f637c","year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.864947Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:fc86958009858da11acef46b4834876c41734761305a08350b5445ce33ae928b","observation_id":"5eb5f13b-4a05-4095-96cf-fb0eec83c283","resolution":{"observed_at":"2026-08-07T05:46:52.440905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.420666Z","title":"PFNs4BO : I n-context learning for B ayesian optimization","venue":null,"work_id":"6754da12-1ef5-4a2e-afe7-e345df3886a7","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.869591Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:5678e6b5a679699ce489129df5af2904319598a6e836e45f3d0340124c3a1061","observation_id":"9a91adfd-f83d-428e-ac97-efa72b8d0581","resolution":{"observed_at":"2026-08-07T05:46:52.425571Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.406178Z","title":"L., Zhang, F., and Barak, B","venue":null,"work_id":"32d46340-4396-4752-8e42-43a225a581fa","year":2019},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.874734Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:786699439973fdf44c24c7af665f8d86e1ef5178cd581371661dca576980470c","observation_id":"03e37889-f957-455d-8e6d-0bd94a8e06c8","resolution":{"observed_at":"2026-08-07T05:46:52.410902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.390785Z","title":"and Grover, A","venue":null,"work_id":"d23e536d-3628-41a2-ad33-7242ed4bb3d9","year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.879915Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:0308011dd797770c2846a2f297bebac8fd35c677fc33aa49576314948b8b6a24","observation_id":"bb32b67c-5ca4-4245-8348-fba42889cf61","resolution":{"observed_at":"2026-08-07T05:46:52.395832Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.376193Z","title":"and Grover, A","venue":null,"work_id":"a69b85bd-a7f9-46f3-98c6-04f14d5e7e81","year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.884783Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:27c248b45aac450ea2bf7ea25d8da034b08c89f962efd65b87699fa9815cc510","observation_id":"05d11ff9-b6f8-41cd-baec-49dfa2c3c0fa","resolution":{"observed_at":"2026-08-07T05:46:52.380606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.361687Z","title":"ExPT : S ynthetic pretraining for few-shot experimental design","venue":null,"work_id":"63a97d19-a668-4c72-a536-124b8d180499","year":2023},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.889529Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:180599972292ccee8319e058f3a07582d5a2144bc05a8a514c3b0025ef0d74aa","observation_id":"fe775602-b00e-4735-b197-21bc6832613b","resolution":{"observed_at":"2026-08-07T05:46:52.366687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:50.894274Z","title":"Predicting from strings: L anguage model embeddings for B ayesian optimization","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.894274Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:0e20281716fdcaee5a58e386ec4aa92f285ec89b73bd3b9b8a2897cc23f7d431","observation_id":"0f6101b1-9450-4a16-927c-450132fe9bf6","resolution":{"observed_at":"2026-08-07T05:46:50.894274Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.346488Z","title":"Z., Shirobokov, S., Kozlovskii, B., Ruiz, F","venue":null,"work_id":"783923c5-8901-4f49-a2c2-00b5c6d309a7","year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.898943Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:c8b5fd9be684d36d23d440ac7b51b9a3b4bd0fdd64efd722b0d01571846d9968","observation_id":"b2aa5e46-f99e-463f-8170-5ff2a2b9dc12","resolution":{"observed_at":"2026-08-07T05:46:52.351674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.331136Z","title":"Introduction to Game Physics with Box2D","venue":null,"work_id":"4e489248-171f-4baa-b431-636bf026d0db","year":2017},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.903696Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:fdb6c814c1bf12ab46ae7253c6206095dff73c79f0d764cd9ae3bfdb0bba06ef","observation_id":"59dc732a-ef14-4376-b167-95d8afcff708","resolution":{"observed_at":"2026-08-07T05:46:52.336167Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.315396Z","title":"Data-driven offline decision-making via invariant representation learning","venue":null,"work_id":"54f8da65-937d-465d-a1c8-f304ced86a18","year":2022},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.909173Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:96580f28e753fe3dcffda47c1c2a987154e1101557b4686f192950fdc03ad522","observation_id":"827333c0-06c2-4a11-8cc3-704b9e3dc85f","resolution":{"observed_at":"2026-08-07T05:46:52.320584Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.299308Z","title":"SOO - B ench: B enchmarks for evaluating the stability of offline black-box optimization","venue":null,"work_id":"5a6ea8ec-6989-4341-b0eb-398bdd430bbd","year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.913886Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:9c0512c1c6af63b9fadce132dd3c2095340cb7b4149c8a13d586aa01e74bc3ff","observation_id":"15a4d381-c9e2-499e-9606-786918bd8965","resolution":{"observed_at":"2026-08-07T05:46:52.304256Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-08-17T18:50:07.059564Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T05:46:50.919390Z","title":"Qwen2.5 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.919390Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:29b7cc53832c17406d45c38fc2d75af0db7043be047d8a07ea0e90422b9324d5","observation_id":"86ff406b-9fb9-4384-9c9f-2217554f14de","resolution":{"observed_at":"2026-08-07T05:46:50.919390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.284205Z","title":null,"venue":null,"work_id":"8c6c5c8d-d241-44e9-9438-8d1f39a62ad3","year":2020},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.924603Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:df85835a6ed69b96e51f72da9f5f24eea35c0a9ecd0e4f08f50bf69c28512554","observation_id":"c2c2356f-f154-471f-8a1a-cca78ad7bc00","resolution":{"observed_at":"2026-08-07T05:46:52.288832Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.269710Z","title":null,"venue":null,"work_id":"8a28703c-64d2-4a99-a906-8b7edfd8c66b","year":2006},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.929405Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:127923de131f87497fd7751a70ff19621b3876273d1722f0a4177d77d2d67ede","observation_id":"6ed1f301-adcb-4dce-a75e-9af698f296d5","resolution":{"observed_at":"2026-08-07T05:46:52.274176Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.254682Z","title":"P., Dupont, E., Ruiz, F","venue":null,"work_id":"2837aa1e-cd0a-42fb-8fdb-feb136a7d2b3","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.934521Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:bca11c5bca426a16ff3c32cb55e2b839172c4e14e7a15b6b3173a33b779150ba","observation_id":"89ae224e-c449-4518-b98d-864ae52395b6","resolution":{"observed_at":"2026-08-07T05:46:52.259400Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.239983Z","title":"GTOPX space mission benchmarks","venue":null,"work_id":"37554edc-332b-41b4-b311-7343c54d45ce","year":2021},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.939204Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:a08171e808602380417d840777648abcb5676c7be8f454e996829fc3fdbe5bf1","observation_id":"f722d3a1-beff-4b26-8942-f4dc6f7a212d","resolution":{"observed_at":"2026-08-07T05:46:52.244719Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.225242Z","title":"P., and de Freitas, N","venue":null,"work_id":"2f043996-27fe-4b7a-a65e-4ec45f244d61","year":2016},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.943933Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:b4d4973f5b7f886bd1dbdb81398f65a3f489f8e084e66274d51ad1f2c0421412","observation_id":"be807eec-56be-4dee-a164-1d261a98d61d","resolution":{"observed_at":"2026-08-07T05:46:52.229935Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.210568Z","title":"B., and Reddy, C","venue":null,"work_id":"8928a93b-f222-49fc-af9f-82a60759b7ee","year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.948895Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:cd5586fb3f98f4b49c83dd92b111d43f3dc009d5d3bbcb02781523f597536f17","observation_id":"554c0a99-3880-4f29-8197-2c84d1ccea3e","resolution":{"observed_at":"2026-08-07T05:46:52.215438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.195195Z","title":"Reinforced in-context black-box optimization","venue":null,"work_id":"c6b61624-14c6-4024-8352-a97f2c5d0812","year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.953803Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:2cca70d53ae7c094529b45feea0a683f91a2c872e5e370122171f161303c0280","observation_id":"99c3f16a-8434-4d2c-9795-40655495dcf9","resolution":{"observed_at":"2026-08-07T05:46:52.200262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2501.19383","last_updated":"2025-08-12T03:41:13Z","snapshot_observed_at":"2026-08-18T17:10:55.675162Z","submitted_at":"2025-01-31T18:37:42Z","title":"Decoding-based Regression","version":2},"cited_work":{"arxiv_id":"2501.19383","doi":null,"metadata_source":"pith","pith_arxiv_id":"2501.19383","snapshot_observed_at":"2026-08-07T05:46:51.188015Z","title":"Decoding-based Regression","venue":"cs.LG","work_id":"d01b25d6-5a6b-4b9b-ad6b-fe9c277c00fa","year":2025},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.958771Z"},"links":{"cited_paper":"/paper/2501.19383","citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:2df442ac8f397474e31e4a1b39dbc08230efd285e5fe73cd625cb1dfb594d713","observation_id":"8a8d8ac8-09a7-4679-89a7-6310e4519f1c","resolution":{"observed_at":"2026-08-07T05:46:51.194156Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.179538Z","title":"OmniPred : L anguage models as universal regressors","venue":null,"work_id":"76d2cb9d-e08f-45c8-94f7-7ea1318b918b","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.963667Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:bbb85cb3c498af498390e7f397e0dea202de26c132f1ec10cba101d093f589ed","observation_id":"b23dbbc6-5058-4b81-afff-516627c131b7","resolution":{"observed_at":"2026-08-07T05:46:52.184663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T05:46:52.165148Z","title":"T., Lee, C., Tang, Y., and Chen, Y","venue":null,"work_id":"77024845-8413-4054-a698-6a23905e1671","year":2024},"citing_paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-07T05:46:50.968546Z"},"links":{"citing_paper":"/paper/2506.07109"},"observation_digest":"sha256:78a8711a2fe8142c3c8f8238edeaaf43aad146c57c352a3757777531cbca045f","observation_id":"756053c7-3e79-41b6-bafe-dcdb0467f2f2","resolution":{"observed_at":"2026-08-07T05:46:52.169613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.07109","last_updated":"2025-06-08T12:41:18Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T09:55:10.891346Z","submitted_at":"2025-06-08T12:41:18Z","title":"Towards Universal Offline Black-Box Optimization via Learning Language Model Embeddings"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":72,"verified_exact":1,"verified_fuzzy":27},"total_outbound_references":129},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 100 of 129 outbound references and 0 inbound Pith citation observations for arXiv:2506.07109."}