{"as_of":"2026-08-05T16:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ee13d4d90d31d55972c0c0fe6862bc3eefcf41eb6cfc57c97b3ed10ee6955cf7","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-21T05:00:49.763040Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-05T06:32:48.257954+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-29T18:26:56.988465Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-01T22:26:17.984520Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"cited_work":{"arxiv_id":"2605.21318","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.21318","snapshot_observed_at":"2026-07-01T22:26:17.984520Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","venue":"cs.CL","work_id":"274db665-5999-4d9f-9962-c8199dec1bae","year":2026},"citing_paper":{"arxiv_id":"2605.26655","last_updated":"2026-05-26T07:39:36Z","snapshot_observed_at":"2026-08-03T22:04:49.341773Z","submitted_at":"2026-05-26T07:39:36Z","title":"Why Prompt Optimization Works, and Why It Sometimes Doesn't: A Causal-Inspired Edit-Level Analysis","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-06-29T18:26:56.988465Z"},"links":{"cited_paper":"/paper/2605.21318","citing_paper":"/paper/2605.26655"},"observation_digest":"sha256:e7127530ac1e2a9e0ae1b69a8759be4d41ff24cd2341f72787bfd1cc758e98bc","observation_id":"26b8e14f-f2c0-4e32-9943-193dec970ab8","resolution":{"observed_at":"2026-06-29T18:33:50.836380Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"cited_work":{"arxiv_id":"2605.21318","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.21318","snapshot_observed_at":"2026-07-01T22:26:17.984520Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","venue":"cs.CL","work_id":"274db665-5999-4d9f-9962-c8199dec1bae","year":2026},"citing_paper":{"arxiv_id":"2606.01637","last_updated":"2026-06-06T04:57:23Z","snapshot_observed_at":"2026-07-06T23:42:12.125247Z","submitted_at":"2026-06-01T03:42:00Z","title":"Easier to Mislead Than to Correct: Harmful and Beneficial Revision in LLM Conformity","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-06-28T15:22:03.044613Z"},"links":{"cited_paper":"/paper/2605.21318","citing_paper":"/paper/2606.01637"},"observation_digest":"sha256:5ef859188f82400ad973bb418670d24ff75606ac6656b91aa53e11129e2aaf4d","observation_id":"abe8a45c-f6be-479d-b2c1-169952dd78c9","resolution":{"observed_at":"2026-07-01T22:26:17.985684Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2605.21318/citation-record","integrity":"/paper/2605.21318/integrity","json":"/paper/2605.21318/citation-record.json","paper":"/paper/2605.21318"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T16:57:25.332055Z","title":"Language models are few-shot learners.Advances in neural information processing systems, 33:1877–1901","venue":null,"work_id":"bd7ec542-9242-446e-955e-bb75e729be5d","year":1901},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:d6af2f23420f58b65e9d6e1f27e711a64cd1121cce086eb2d0e216d9d54bb79f","observation_id":"3a9d7fee-4c26-442a-9342-c8f64e83b536","resolution":{"observed_at":"2026-05-21T05:03:58.859656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":"2303.08774","doi":"10.1002/tea.20265","metadata_source":"pith","pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GPT-4 Technical Report","venue":"cs.CL","work_id":"b928e041-6991-4c08-8c81-0359e4097c7b","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:8b5f2712e8071fddf6d41515fff4b93ce9d1b2ab9b5bce7e251b95df2e9eb7d2","observation_id":"dd860c8a-0842-46c6-80c0-a9967bed0f47","resolution":{"observed_at":"2026-05-21T05:03:58.000214Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":"2312.11805","doi":"10.1038/nrn2888","metadata_source":"pith","pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Gemini: A Family of Highly Capable Multimodal Models","venue":"cs.CL","work_id":"83f7c85b-3f11-450f-ac0c-64d9745220b2","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:3a05a365b3cc812c751eadf472dba45b743c05585ffaa7d418cffb05a5fac563","observation_id":"8e8e1e75-72c7-40dc-aac5-3d06c23b465a","resolution":{"observed_at":"2026-05-21T05:03:58.008168Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2601.14230","last_updated":"2026-05-31T05:19:53Z","snapshot_observed_at":"2026-08-03T09:21:00.637246Z","submitted_at":"2026-01-20T18:44:04Z","title":"MASCOT: Towards Multi-Agent Socio-Collaborative Companion Systems","version":2},"cited_work":{"arxiv_id":"2601.14230","doi":null,"metadata_source":"pith","pith_arxiv_id":"2601.14230","snapshot_observed_at":"2026-07-02T13:16:58.879920Z","title":"Mascot: Towards multi-agent socio- collaborative companion systems","venue":"cs.CL","work_id":"ae7b7fe1-2ff1-4709-8020-7cdf9aeffdaf","year":2026},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2601.14230","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:92eb91817da7613ed69bec368d4942474d29eb47e745c71a75fd90356c489c35","observation_id":"ed523a5b-488b-412a-a0ab-fd4baa99d464","resolution":{"observed_at":"2026-06-02T02:04:13.222420Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Companioncast: A multi-agent conversational ai framework with spatial audio for social co-viewing experiences.ACM CHI 2026 Workshop on Human-Agent Collaboration","venue":null,"work_id":"c7c5d254-8356-406a-9f69-f36e388df66c","year":2026},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:3ec3815e74abb222c41f6ae739656a5bfdb5ba1c31bb0531feb6f32e72a7fb3f","observation_id":"30d6f451-35af-4e29-b918-0ff5d5331582","resolution":{"observed_at":"2026-05-21T05:03:58.812380Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"gradient descent","venue":null,"work_id":"3aff4bb2-ea06-4fc6-af2a-1aa1cf4dbc96","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:df768d6ff63990a2f14ee961a148d12b0e6fc194a627f7e83cf496e3daede804","observation_id":"0fc4b583-994a-49e5-b425-96b0b1652cb5","resolution":{"observed_at":"2026-05-21T05:03:58.803325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Teach better or show smarter? on instructions and exemplars in automatic prompt optimization.NeurIPS, 37:58174–58244","venue":null,"work_id":"34bb1a7f-533b-4f08-a78f-7bdf63ac4571","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:1d20cebaa7e77e532a047a8a7fed10c762ad0fe526f63fcae679432768de7670","observation_id":"0fb1cb0b-ec8c-4c32-b640-611df2b15c99","resolution":{"observed_at":"2026-05-21T05:03:58.806930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.07496","last_updated":"2024-06-11T17:32:21Z","snapshot_observed_at":"2026-07-06T18:29:04.294349Z","submitted_at":"2024-06-11T17:32:21Z","title":"TextGrad: Automatic \"Differentiation\" via Text","version":1},"cited_work":{"arxiv_id":"2406.07496","doi":"10.48550/arxiv.2406.07496","metadata_source":"pith","pith_arxiv_id":"2406.07496","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"TextGrad: Automatic \"Differentiation\" via Text","venue":"cs.CL","work_id":"c52b4841-a4b4-4b4e-bc86-8ef6645a9bbb","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2406.07496","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:42b8877e0963c4bced748a700d1e6067bebd4fe74b10d34352d60652d8b648c3","observation_id":"2bf1dd20-57b9-4cfe-a819-462c59a51399","resolution":{"observed_at":"2026-05-21T05:03:58.037275Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-14T18:20:25.209279+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T18:20:25.209279+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Prosa: Assessing and understanding the prompt sensitivity of llms","venue":null,"work_id":"e35aee60-4ade-4e4b-8025-c011c9a225ce","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:b370ef1abab365218b5342ab794c1fe05fa92294cd5cf8791243c729936348a9","observation_id":"5fe26cc5-7bba-47ed-b0f3-b65898130b07","resolution":{"observed_at":"2026-05-21T05:03:58.808568Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Self-regulating prompts: Foundational model adaptation without forgetting","venue":null,"work_id":"9833bb4d-3649-4c5e-90cf-b2b358fa7a89","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:ca9e800b81cc5b74183f71b69854c65a14e4acac73c875513eaaf5280e10e364","observation_id":"b5ec7bef-dea4-45a7-a411-4775fe1b72f2","resolution":{"observed_at":"2026-05-21T05:03:58.810658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-07T18:24:00.832973Z","title":"Same task, more tokens: the impact of input length on the reasoning performance of large language models","venue":null,"work_id":"15cc7171-4ceb-4a63-88e1-7087aca13501","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:5610bb8c420f41703820a15244666159f21efe7d3a4e504926bca5360f809d7e","observation_id":"01271660-7692-4548-85e3-8ada6e941d04","resolution":{"observed_at":"2026-05-21T05:03:58.798123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-10T20:07:33.937442Z","title":"Lost in the middle: How language models use long contexts.Transactions of the association for computational linguistics, 12:157–173","venue":null,"work_id":"d18f0dc7-06f6-403e-aa38-f5f19bba0db5","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:85ff0ccb93a0d1b4975756b83e997a48d5dcbba811c4c81ad8c62a2c21fcf892","observation_id":"66ab4021-1d27-490c-b366-81da386203d6","resolution":{"observed_at":"2026-05-21T05:03:58.801066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Sara: Selective and adaptive retrieval-augmented generation with context compression","venue":null,"work_id":"88b85a63-a735-42db-a1d5-94d4da9ac545","year":2026},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:d444f4ea7e4b3e9c83d43fd4c0de453634e0519d9d57f2a8c83b6be1a609dd20","observation_id":"add6c128-cd15-4c5b-91b5-6b63e660b735","resolution":{"observed_at":"2026-05-21T05:03:58.805053Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-10T11:37:03.941805Z","title":"Chain-of-thought prompting elicits reasoning in large language models.Advances in neural information processing systems, 35:24824–24837","venue":null,"work_id":"3256b5a6-76d9-460c-ad77-5d232058ad6d","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:256beb33793eb718fa7149132a953aec2f04e264075724cc23b509180f2547de","observation_id":"5b3a03d3-8751-4d73-979b-a1f0074cc91c","resolution":{"observed_at":"2026-05-21T05:03:58.815199Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.11171","last_updated":"2023-03-07T17:57:37Z","snapshot_observed_at":"2026-07-06T12:50:22.773056Z","submitted_at":"2022-03-21T17:48:52Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","version":4},"cited_work":{"arxiv_id":"2203.11171","doi":"10.1101/2025.04.03.646459","metadata_source":"pith","pith_arxiv_id":"2203.11171","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models","venue":"cs.CL","work_id":"8c6d5a6b-b5cc-4105-9c84-9c34bb9375bb","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2203.11171","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:cc240cfadd05f2c0e94a84932945d2b2cc2262caeaa77b6ab1b1bfb937497f99","observation_id":"3d6ac22c-bba3-4597-ba2d-4ddf738fa57d","resolution":{"observed_at":"2026-05-21T05:03:57.995469Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-21T18:52:42.88633+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.03629","last_updated":"2023-03-10T01:00:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2022-10-06T01:00:32Z","title":"ReAct: Synergizing Reasoning and Acting in Language Models","version":3},"cited_work":{"arxiv_id":"2210.03629","doi":"10.48550/arxiv.2210.03629","metadata_source":"pith","pith_arxiv_id":"2210.03629","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"ReAct: Synergizing Reasoning and Acting in Language Models","venue":"cs.CL","work_id":"407a2351-25f1-497d-b611-f77d0292a8e6","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2210.03629","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:775de552ca0cbef70a00505fe7175a4279cc0bd089d637a9710130d56132ca4e","observation_id":"75dcf14c-2636-48ab-87b5-43a5bcaf33bc","resolution":{"observed_at":"2026-05-21T05:03:57.998005Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-07-12T03:19:36.897515+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-12T03:19:36.897515+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12588","last_updated":"2023-10-23T01:27:38Z","snapshot_observed_at":"2026-08-02T13:06:11.850456Z","submitted_at":"2022-11-22T21:06:00Z","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","version":4},"cited_work":{"arxiv_id":"2211.12588","doi":"10.48550/arxiv.2211.12588","metadata_source":"pith","pith_arxiv_id":"2211.12588","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Program of Thoughts Prompting: Disentangling Computation from Reasoning for Numerical Reasoning Tasks","venue":"cs.CL","work_id":"618aa44c-a6c6-425c-abce-8aa8aa842921","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2211.12588","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:25acf1108374164bbbe95c0a46259b1f35e82852c23473dd68a15a3eba1f7e73","observation_id":"fc78468a-12a7-410d-b8bb-fe3fd90002bb","resolution":{"observed_at":"2026-05-21T05:03:57.993079Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-08T12:44:53.692757Z","title":"Tree of thoughts: Deliberate problem solving with large language models.Advances in neural informa- tion processing systems, 36:11809–11822","venue":null,"work_id":"e1f89960-6a3b-451c-b6f2-7c7d1a108531","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:7e6eff4d6f798e3d967b28848e61603fe37171d8986550fa320769cc33e097cb","observation_id":"db62e292-ad47-4590-815d-e51a055a0d8c","resolution":{"observed_at":"2026-05-21T05:03:58.790274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Autoprompt: Eliciting knowledge from language models with automatically generated prompts","venue":null,"work_id":"3003f6ef-07a8-4bcf-847c-a0c5ec8f8834","year":2020},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:3d5f41e92b6af758aa762df4b22a291d6b06d5431449f8c34471fdd82f3befb9","observation_id":"64fae4b9-687c-4ca0-aafc-88ac75c84f1b","resolution":{"observed_at":"2026-05-21T05:03:58.792012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Rlprompt: Optimizing discrete text prompts with reinforcement learning","venue":null,"work_id":"2f1d4191-8c67-4871-bded-a71763c39fb5","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:05624324966a8c1ea0c802570af79e82c31bf55b0384b1cf4c7f28703763e906","observation_id":"299e6464-ef87-4150-bff3-c3a8366a497b","resolution":{"observed_at":"2026-05-21T05:03:58.793803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Large language models are human-level prompt engineers","venue":null,"work_id":"aac263ff-ed0a-4b73-93fb-a970e22bbd02","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:c22913af5d3c2f2006f63dbde7da647c513be47521764c5073ed2923ae1c618b","observation_id":"8d03d059-ede2-4328-aeeb-6a34ba28695d","resolution":{"observed_at":"2026-05-21T05:03:58.796367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.08532","last_updated":"2025-05-01T11:56:52Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-15T16:50:09Z","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","version":3},"cited_work":{"arxiv_id":"2309.08532","doi":"10.48550/arxiv.2309.08532","metadata_source":"pith","pith_arxiv_id":"2309.08532","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"EvoPrompt: Connecting LLMs with Evolutionary Algorithms Yields Powerful Prompt Optimizers","venue":"cs.CL","work_id":"fa7fdd38-244f-4722-a136-ba8667c8a974","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2309.08532","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:e185fa0dc139191df9e3011d084227a35a80bfebbe8d4e58227f92277d0a028a","observation_id":"906acfff-0796-43b0-a484-1c4517cbd42d","resolution":{"observed_at":"2026-05-21T05:03:58.014028Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.16797","last_updated":"2023-09-28T19:01:07Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-28T19:01:07Z","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","version":1},"cited_work":{"arxiv_id":"2309.16797","doi":"10.48550/arxiv.2309.16797","metadata_source":"pith","pith_arxiv_id":"2309.16797","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution","venue":"cs.CL","work_id":"01508be0-d975-4ff6-8045-1e0b229fbab4","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2309.16797","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:2b6a2e3e6396699d021f421332a1effbc8c2310a07e0fd21472456e949b31859","observation_id":"2d70de9c-b7fa-4bda-8e2d-2e9c254677a0","resolution":{"observed_at":"2026-05-21T05:03:57.990626Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.03714","last_updated":"2023-10-05T17:37:25Z","snapshot_observed_at":"2026-08-04T05:21:05.846165Z","submitted_at":"2023-10-05T17:37:25Z","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","version":1},"cited_work":{"arxiv_id":"2310.03714","doi":"10.48550/arxiv.2310.03714","metadata_source":"pith","pith_arxiv_id":"2310.03714","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","venue":"cs.CL","work_id":"d490f594-f5fc-47b0-ae6a-6550e50fe095","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2310.03714","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:a8b6e477e9d6f22ff28610718fd57822598c3579edc9534aef56bf0405573576","observation_id":"6c5fb93a-5ab5-4952-b17f-9313b26e833f","resolution":{"observed_at":"2026-05-21T05:03:58.019619Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.03092","last_updated":"2025-06-18T04:06:03Z","snapshot_observed_at":"2026-08-05T13:27:52.801293Z","submitted_at":"2024-12-04T07:44:35Z","title":"REVOLVE: Optimizing AI Systems by Tracking Response Evolution in Textual Optimization","version":2},"cited_work":{"arxiv_id":"2412.03092","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.03092","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Zhang, H","venue":null,"work_id":"cbdf306d-87ad-4c0b-9b5d-d0a6669ad3d5","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2412.03092","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:0a446b775614b13fb9e4a776ce3a7f19b2151537d544b81a021a21a6d2b21413","observation_id":"7d29d5ab-841c-4c71-a70a-1399db731b02","resolution":{"observed_at":"2026-05-21T05:03:57.988132Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.19514","doi":"10.48550/arxiv.2505.19514","metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Sipdo: Closed-loop prompt optimization via synthetic data feedback","venue":"ArXiv.org","work_id":"9c38eceb-8b7e-4cc6-ab64-f9cf504de93a","year":2025},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:eebe9bff2cb791bd0cc56c7c560c8fca1f9043a0b5f39dcd06b46c927be650d4","observation_id":"379f775b-ebd4-4307-a4fc-5d1fae606c25","resolution":{"observed_at":"2026-05-21T05:03:58.022321Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Robust prompt optimization for large language models against distribution shifts","venue":null,"work_id":"8838328b-2b12-40e4-bc0a-e644c9e08d7b","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:479b4ce1b96537e2d12ba3ed3650b481273494d88c3535400ad12956be2bacf5","observation_id":"7a269d69-f2e9-40fb-86ef-e27f0594bd30","resolution":{"observed_at":"2026-05-21T05:03:58.788586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2509.24130","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-01T22:26:17.988935Z","title":"Beyond magic words: Sharpness-aware prompt evolving for robust large language models with tare","venue":null,"work_id":"5605d51a-15ea-4034-9627-69076e65d587","year":2025},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:d98bde3ca332e46b712f65892f875dc9735d9b766ff1904009a6b03fbbbb809a","observation_id":"4ba05a5b-4ba7-4fb9-9ac7-a29d548eee9b","resolution":{"observed_at":"2026-05-21T05:03:58.030999Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13413","last_updated":"2025-03-19T14:18:01Z","snapshot_observed_at":"2026-07-06T20:54:04.912422Z","submitted_at":"2025-03-17T17:42:51Z","title":"DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective","version":3},"cited_work":{"arxiv_id":"2503.13413","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.13413","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dlpo: Towards a robust, efficient, and generalizable prompt optimization framework from a deep-learning perspective","venue":null,"work_id":"a95592f9-cbac-4acc-9e1c-3fadc50568c8","year":2025},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2503.13413","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:27b996e3ade748a0bba3a3f9f6abd66f1b5857ee05c9c2fc75077f585a9f5a44","observation_id":"f4798ee8-6c12-4d46-aba9-dfd6e2ae573d","resolution":{"observed_at":"2026-05-21T05:03:58.016989Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2508.18749","last_updated":"2025-08-26T07:25:45Z","snapshot_observed_at":"2026-07-06T22:18:45.529787Z","submitted_at":"2025-08-26T07:25:45Z","title":"Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution","version":1},"cited_work":{"arxiv_id":"2508.18749","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2508.18749","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Reflection-enhanced meta-optimization integrating textgrad-style prompt optimization with memory-driven self-evolution","venue":null,"work_id":"cd8ba401-adb8-4cde-b2bb-1dab98afb76c","year":2025},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2508.18749","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:9ae94c1082cb19f2771587459f86416c325b0bd4cb4872db2aff45ff8d797b5c","observation_id":"518a1191-3cf8-48d0-993c-735c47a11a60","resolution":{"observed_at":"2026-05-21T05:03:58.011408Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Ridge regression: Biased estimation for nonorthogonal problems.Technometrics, 12(1):55–67","venue":null,"work_id":"d34c2d0f-66e5-4f17-9ca4-fb61302b284e","year":1970},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:0e73ef2d5fb560a9fc73f415b580a6fadf8b86dfb3f3cd5e38be997b2becb40b","observation_id":"e51749ec-be94-4047-9306-afd00e9a5767","resolution":{"observed_at":"2026-05-21T05:03:58.817728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"A simple weight decay can improve generalization.Advances in neural information processing systems, 4","venue":null,"work_id":"0122534d-dc4c-48e5-8405-186eb65d3997","year":1991},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:9f9f196261e6426ab8bb5a51d16da337c2a5be17a512df9185d5c1b07b9777a3","observation_id":"47e64b2a-c5e8-4b0e-94df-7112419e9c0f","resolution":{"observed_at":"2026-05-21T05:03:58.819514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Regularization of neural networks using dropconnect","venue":null,"work_id":"a14b7ba8-c531-447d-8f65-0f7b0f58b576","year":2013},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:15db31b50c9fcc00ad992e2043285d14cab2b06d0032be392d33719609bdb81a","observation_id":"0cefb57d-a27d-47dc-a4b5-30e4c21e7b49","resolution":{"observed_at":"2026-05-21T05:03:58.851441Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Dropout: a simple way to prevent neural networks from overfitting.The journal of machine learning research, 15(1):1929–1958","venue":null,"work_id":"89676d55-83a1-4373-b8c8-77e23c24288e","year":1929},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:8f5d51cf33f1145821edbaed5cce48f31ed1a6ac8432f0a46816f4354b4b5c3a","observation_id":"36c61cfc-6475-4b65-928d-51c9d795cbb4","resolution":{"observed_at":"2026-05-21T05:03:58.854204Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-07T00:23:12.968084Z","title":"Regression shrinkage and selection via the lasso.Journal of the Royal Statistical Society Series B: Statistical Methodology, 58(1):267–288","venue":null,"work_id":"4782a55e-8183-4187-851d-d9e477c3e541","year":1996},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:5c86cb458ea8b31a75474565e72188b5505f6d25d9f3f4316d003d643df96bee","observation_id":"a00ce547-107c-4a21-9bd2-a558bfdc5261","resolution":{"observed_at":"2026-05-21T05:03:58.857097Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Regularization and variable selection via the elastic net.Journal of the Royal Statistical Society Series B: Statistical Methodology, 67(2):301–320","venue":null,"work_id":"61413cf4-45f7-4aef-950c-c6e76930460d","year":2005},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:02e47f022c95d32eedc5b6866690d5e055a12abbb379447781e9663e5b7deeb3","observation_id":"0a6bc19d-a215-4533-808e-a5d3e812a780","resolution":{"observed_at":"2026-05-21T05:03:58.847641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping.Advances in neural information processing systems, 13","venue":null,"work_id":"6755283d-9ea0-4b97-9d43-0fa98ae24e4d","year":2000},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:c4cf663bfd3fed2b51e9404cce8bbaaad63768d143ddcee3f8c5ce8993df24de","observation_id":"fed1a4bd-e3df-4bcd-8b11-8ad58a8e46f1","resolution":{"observed_at":"2026-05-21T05:03:58.842271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":"57803dd8-347c-4dfe-8458-77cb9f6b120e","year":2021},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:0d3c52c64d202a1d101c14982fa639a8e72400a698de7255e390432f237e3f65","observation_id":"4493b371-5a93-44e6-bee3-40899e07853b","resolution":{"observed_at":"2026-05-21T05:03:58.840389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"The power of scale for parameter-efficient prompt tuning","venue":null,"work_id":"9fba5629-dd45-4005-8d22-434717c1bbf8","year":2021},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:71e71d343eaf01d64018fa56fd2b02d593268947f8953c8844c285cdbe10a046","observation_id":"ddcf5691-5617-4685-98f7-a4e3861bbf72","resolution":{"observed_at":"2026-05-21T05:03:58.843953Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"P-tuning: Prompt tuning can be comparable to fine-tuning across scales and tasks","venue":null,"work_id":"e0a16660-cbbe-483b-8802-2967b049e8c9","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:baf7c9574cd6c3e943a5fc9156d5bab479570d16c5583a24d603530fa07b620d","observation_id":"4cc3cd7e-bdaa-4380-a767-39f3c78b6840","resolution":{"observed_at":"2026-05-21T05:03:58.845850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-05T23:31:35.854639Z","title":"Challenging big-bench tasks and whether chain-of-thought can solve them","venue":null,"work_id":"0d1a520c-07db-456c-98e3-9cacc91d7269","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:0db5b69cd041564a8362a6ab8fbf1f6fbbd0ac84d2d3db7575dd45d5da69408d","observation_id":"b2a7cc70-ecc8-48a0-a4ee-139ff07e9990","resolution":{"observed_at":"2026-05-21T05:03:58.832409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models.Transactions on machine learning research","venue":null,"work_id":"9bc09692-c8ea-420c-a5c0-9dc127e56312","year":2023},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:d7532aa8589c1ecde80211dccb457a9b0c49ef041c3245c6b83276138669baa6","observation_id":"789a121c-8270-4ab2-9160-1ce5606b2b1a","resolution":{"observed_at":"2026-05-21T05:03:58.835941Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-04T15:46:25.710484Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":"2110.14168","doi":"10.1002/j.1545-","metadata_source":"pith","pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Training Verifiers to Solve Math Word Problems","venue":"cs.LG","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":2021},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:5ef2443c650ce4dae7e6ebe507acf06603f195f34f77a6c9c100b9a80ff7d23c","observation_id":"770072f9-5e67-4d8a-81a5-05b95ca1d141","resolution":{"observed_at":"2026-05-21T05:03:58.024832Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-05T02:30:41.747858Z","title":null,"venue":null,"work_id":"c3796a34-a60a-4514-a471-ec45df63ba74","year":2021},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:199022aa5a61739641c4138fe5b9c13dc2d272a35baf0a9b03b9f31b3830d73f","observation_id":"18479d25-0e46-4b0d-a2d6-ec11ec3dc8b8","resolution":{"observed_at":"2026-05-21T05:03:58.830552Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-05T02:30:41.759903Z","title":"Solving general arithmetic word problems","venue":null,"work_id":"243ca4b1-4441-4207-8d00-8f5d8086bbdb","year":2015},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:84590700640b9c5a9bfd2ebbce274eaf5b65a9488c567d9cab609bed9851a6f7","observation_id":"31b3c717-37f1-41b7-b14e-7e18ab8f9234","resolution":{"observed_at":"2026-05-21T05:03:58.838656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Mawps: A math word problem repository","venue":null,"work_id":"ff43bc62-8559-46ba-a3fc-df7148409dc3","year":2016},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:02ab934b45c2e52636db744ddb23cdcdf9e3673498777ad76950f4b5bcddc8d6","observation_id":"b73646e9-117f-460c-ac49-736783b4393e","resolution":{"observed_at":"2026-05-21T05:03:58.849772Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":"2407.10671","doi":"10.18653/v1/2024.naacl-long.246","metadata_source":"pith","pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Qwen2 Technical Report","venue":"cs.CL","work_id":"a1857881-ab9b-4b80-9b5f-9ae4b5c2566d","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:f2982340b51b41b014ddb0e5455d2a63c8821abc8f4c759fac696777dcbe08eb","observation_id":"f30f16f7-702c-447e-a5ba-f687cccab994","resolution":{"observed_at":"2026-05-21T05:03:58.027389Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.14219","last_updated":"2024-08-30T21:17:17Z","snapshot_observed_at":"2026-07-06T18:03:47.096406Z","submitted_at":"2024-04-22T14:32:33Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","version":4},"cited_work":{"arxiv_id":"2404.14219","doi":"10.48550/arxiv.2404.14219","metadata_source":"pith","pith_arxiv_id":"2404.14219","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone","venue":"cs.CL","work_id":"feef9556-a016-493c-abd2-0c97a23a7ebf","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2404.14219","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:7416f99a2ec84d3e640e24e06ad2be4d89cacbbc17eca91b382ae4c05c91ec2d","observation_id":"155aa08f-33b1-4158-8217-3c36b883a27a","resolution":{"observed_at":"2026-05-21T05:03:58.034140Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":"2407.21783","doi":"10.1016/s0749-0720(15","metadata_source":"pith","pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"The Llama 3 Herd of Models","venue":"cs.AI","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:d8306981c65a80dcd0813e3f03c026780c642a713b18fec49fa7204222fb7afe","observation_id":"f06ad41a-a109-49fa-82f3-3f6d03f2273a","resolution":{"observed_at":"2026-05-21T05:03:58.005702Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-07-08T13:04:57.066611Z","title":null,"venue":null,"work_id":"5367b59e-43c6-4ca3-84fa-fcc5e6a40037","year":2024},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:f36c15ebb0d9de9a00c665e3a1b69839d1f512a51c91676c67018378ea3dd3f7","observation_id":"79a79597-32f2-4148-becf-31fe742d69b2","resolution":{"observed_at":"2026-05-21T05:03:58.826674Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Gpt-4o","venue":null,"work_id":"ccd12086-a981-4347-9b55-4f5007c5faab","year":2025},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:b830820131af8cbb2481075843019f4a3c7171745e9216fbda5ffc9abc9fd337","observation_id":"85926ce8-720f-4542-96de-e046b1352b4b","resolution":{"observed_at":"2026-05-21T05:03:58.828280Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Think step-by-step","venue":null,"work_id":"25ac3cd5-09b0-4ec0-9a73-2a6fa3104b4d","year":2022},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:9db237c2cb0510f51ebafa4df1a047356648c2212003fb3e2a5dc4f6afb1b3cf","observation_id":"212f7188-e5a2-443b-9c90-415c59d54ee9","resolution":{"observed_at":"2026-05-21T05:03:58.822911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"Remove references to specific entities, exact numbers, or particular examples","venue":null,"work_id":"e2f5fa93-3f30-448a-bef2-bfd63f3be1ef","year":null},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:5ba0f4dbb48444d106b88f103f2319c1864ec1a47aa2fb865d70f8eef9ad18d0","observation_id":"6b9b2d46-b36d-40c5-9fb0-2ebfdf2ba93b","resolution":{"observed_at":"2026-05-21T05:03:58.821107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+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":"2026-06-05T21:23:00.469572Z","title":"operations","venue":null,"work_id":"d646467a-5149-455a-9965-e7876a5278d6","year":null},"citing_paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-21T05:00:49.763040Z"},"links":{"citing_paper":"/paper/2605.21318"},"observation_digest":"sha256:021c73c0f00c473421e15f2238aea605adc7148924c14b560b55aa489210c382","observation_id":"7353538f-8b69-479a-8e47-04978d476419","resolution":{"observed_at":"2026-05-21T05:03:58.824589Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-05T06:32:48.257954+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.21318","last_updated":"2026-05-20T15:47:26Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T23:31:46.877766Z","submitted_at":"2026-05-20T15:47:26Z","title":"TextReg: Mitigating Prompt Distributional Overfitting via Regularized Text-Space Optimization"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":1,"unresolved":2,"verified_exact":18,"verified_fuzzy":32},"total_outbound_references":54},"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":"2026-08-05T06:32:48.257954+00:00","source":"crossref"},{"observed_at":"2026-08-05T06:32:44.755628+00:00","source":"retraction_watch"}],"thesis":"As of 5 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 2 inbound Pith citation observations for arXiv:2605.21318."}