{"as_of":"2026-08-17T01:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:923927b6524bcd5b13f56627011a70a238b8c5320a543ece109ceeeb80efbdff","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T11:03:12.199715Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/2506.03627/citation-record","integrity":"/paper/2506.03627/integrity","json":"/paper/2506.03627/citation-record.json","paper":"/paper/2506.03627"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T11:03:12.605852Z","title":"Language mod- els are few-shot learners,","venue":null,"work_id":"8b9867d7-fb9e-430a-93ea-2357ab8092cd","year":1901},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.112253Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:f5dbf9c9acd2fd087295f791eb12b8bab7ce9dae64b3531892a059d33afc6988","observation_id":"83156f2d-e4b6-4f77-8270-570859ddaa04","resolution":{"observed_at":"2026-08-07T11:03:12.609185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.597505Z","title":"Palm: Scal- ing language modeling with pathways,","venue":null,"work_id":"56657aea-7919-4805-bda3-f6c405207a11","year":2023},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.115701Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:8176acf3234a8c987712c4d7fdbaa73ec50259e0c73838909deaad18b09f479c","observation_id":"a6accd47-22dc-4072-8155-1758c416beab","resolution":{"observed_at":"2026-08-07T11:03:12.601226Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.589933Z","title":"A survey on large language models for recommendation,","venue":null,"work_id":"92de75ea-4ca0-4a10-b0a3-b5c474a8980b","year":2024},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.118858Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:c3048beeb6e41d023cd093485aee8adb443f95f04d898c2de76445680be14f9a","observation_id":"307d87de-fd82-4f44-aedf-047f2d9bedfb","resolution":{"observed_at":"2026-08-07T11:03:12.593163Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.581797Z","title":"Netprompt: Neural network prompting enhances event extraction in large language models,","venue":null,"work_id":"2c085936-b5e8-4208-b75b-c095d7581240","year":2025},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.121850Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:aa2049ee2b8f4e64404892476751d1c965d032af14d616e6a5a0bea89df7f910","observation_id":"83572346-9b97-454e-9a9a-08bfbe40f4c2","resolution":{"observed_at":"2026-08-07T11:03:12.585169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2503.12605","last_updated":"2025-03-23T13:47:43Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-16T18:39:13Z","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.12605","snapshot_observed_at":"2026-08-07T11:03:12.125447Z","title":"Mul- timodal chain-of-thought reasoning: A comprehensive survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.125447Z"},"links":{"cited_paper":"/paper/2503.12605","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:3714639a22b153f65a43afa398255baf3a5f7c6cc87bfa2eb93546a1229fb955","observation_id":"750a47de-959f-4677-815a-534e850af80b","resolution":{"observed_at":"2026-08-07T11:03:12.125447Z","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":"2026-08-07T11:03:12.573614Z","title":"Chain-of-thought prompting elicits reasoning in large language models,","venue":null,"work_id":"14d0297d-1860-41cd-9d34-95b876595f04","year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.128558Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:d1fa49369cc98ff1607051849056c6c27937a81fc8b71ad4459dde0af7b62659","observation_id":"983c4d97-cf65-4b76-bbe7-70373890d4f8","resolution":{"observed_at":"2026-08-07T11:03:12.576950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.565730Z","title":"Large language models are human-level prompt engineers,","venue":null,"work_id":"878b9738-d149-401e-8449-6edbfdc3b58b","year":2023},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.131506Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:1be59758c8ff5deded5e93ae60948d5ae6f431cd2cc14e9e770fddafa9e3b190","observation_id":"9f4b79cc-e13c-4fca-86d3-545de7d3ff15","resolution":{"observed_at":"2026-08-07T11:03:12.568950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2411.05345","last_updated":"2024-11-08T05:54:05Z","snapshot_observed_at":"2026-08-16T13:01:51.560556Z","submitted_at":"2024-11-08T05:54:05Z","title":"Reasoning Robustness of LLMs to Adversarial Typographical Errors","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2411.05345","snapshot_observed_at":"2026-08-07T11:03:12.134359Z","title":"Reasoning robustness of llms to adversarial typographical errors,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.134359Z"},"links":{"cited_paper":"/paper/2411.05345","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:67a383fee08232f0162a870c19c44c11aa108361621e9c615a236ca230020dbd","observation_id":"550a8a82-c788-488b-b82d-006b182408a6","resolution":{"observed_at":"2026-08-07T11:03:12.134359Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-16T14:50:27.710091Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-07T11:03:12.137203Z","title":"An llm can fool itself: A prompt-based adversarial attack,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.137203Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:ccc5329f427f8c80f059e4a19e13b0b46624cfc6387f75f155422be81e0eca22","observation_id":"20ea3c6d-f486-4fa1-a6b1-d8d183f748bc","resolution":{"observed_at":"2026-08-07T11:03:12.137203Z","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":"2026-08-07T11:03:12.557999Z","title":"Promptrobust: Towards evaluating the robustness of large language models on adversarial prompts,","venue":null,"work_id":"34b298c4-18ba-4258-b24c-402d01621d55","year":2023},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.139607Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:1424599af0d2d4931287b733c870b0ad444d4ecc453e212897c8947180c83fb3","observation_id":"18148edc-4e91-4ac8-a2e6-08d7e57272d8","resolution":{"observed_at":"2026-08-07T11:03:12.561175Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.550012Z","title":"Measure and improve robustness in NLP models: A survey,","venue":null,"work_id":"fc1b7351-848f-42fc-a47c-c390152007d1","year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.142411Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:e4e9657413083a9e938b1e5ec52ed995bf1784a76cc22ffd883a067d3ee39313","observation_id":"5b6dbd65-e13d-4d0c-a4ce-6b7cc45e1a00","resolution":{"observed_at":"2026-08-07T11:03:12.553159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2202.12837","last_updated":"2022-10-20T14:04:10Z","snapshot_observed_at":"2026-08-16T04:47:34.593789Z","submitted_at":"2022-02-25T17:25:19Z","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.12837","snapshot_observed_at":"2026-08-07T11:03:12.144778Z","title":"Rethinking the role of demonstrations: What makes in-context learning work?,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.144778Z"},"links":{"cited_paper":"/paper/2202.12837","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:e27ae1b99d4d1c95d54f987696007140850aae8661e321d89d2f2f8206c3e5fa","observation_id":"9f8e9d78-203f-4f2b-bef4-f14474d2ddb0","resolution":{"observed_at":"2026-08-07T11:03:12.144778Z","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":"2026-08-07T11:03:12.542008Z","title":"Prompt learning for few-shot question answering via self-context data augmentation,","venue":null,"work_id":"5c350b7d-a631-4aaf-861d-4459eeb6a138","year":2025},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.147800Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:5ad19155948c0188bd5d8ace52ba0ecdd98f7b0a8f515098a3ac9b030824de3b","observation_id":"15a8c7b8-1bc8-4541-b313-40cb341be1d2","resolution":{"observed_at":"2026-08-07T11:03:12.545243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.150201Z","title":"Large lan- guage models are zero-shot reasoners,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.150201Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:0aac5afd98551a90261f19b19d3d99f187e7ea193d73c64cf261f677761af9e8","observation_id":"1c47f092-f6ee-4259-ba80-947d9fd055f5","resolution":{"observed_at":"2026-08-07T11:03:12.150201Z","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":"2026-08-07T11:03:12.530598Z","title":"Large language models as optimizers,","venue":null,"work_id":"da40d573-c555-4c25-88ef-b32a498687d9","year":2024},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.152195Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:e70d449c0ae3ef73e5815416a2b0f22d524ef314fd91615a7ff3bf578d0e608c","observation_id":"4728ccd4-7a31-41cf-9f9f-7b38f28a8de1","resolution":{"observed_at":"2026-08-07T11:03:12.533492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-07T11:03:12.154599Z","title":"Training verifiers to solve math word problems,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.154599Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:767306b02ca410cbb8827a2931f4a59c04f9185bb9a5ded9b503ef21713be8ca","observation_id":"d831d7b8-4a43-40c1-a6ef-121e920bef1a","resolution":{"observed_at":"2026-08-07T11:03:12.154599Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.00234","last_updated":"2024-10-05T11:47:02Z","snapshot_observed_at":"2026-07-06T14:36:25.690733Z","submitted_at":"2022-12-31T15:57:09Z","title":"A Survey on In-context Learning","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.00234","snapshot_observed_at":"2026-08-07T11:03:12.157526Z","title":"A survey for in-context learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.157526Z"},"links":{"cited_paper":"/paper/2301.00234","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:4fc5ba646b5c181fd3aa7b7d0b36e1bdf41834f87252416667fe026e34d81758","observation_id":"5f915cb4-1eed-42ba-a950-0f34c9f72ec6","resolution":{"observed_at":"2026-08-07T11:03:12.157526Z","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":"2026-08-07T11:03:12.521914Z","title":"Adversarial attacks and defenses in machine learning-empowered communication systems and networks: A contemporary survey,","venue":null,"work_id":"1f162d2a-6399-4fd3-9dc4-02b3c3af060d","year":2023},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.159967Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:7c644e402b13d6777889e71ca5137283dddd8c9980005e2772fd5f1273daa266","observation_id":"0b36439a-39f9-4f6f-b532-09de9bc54e86","resolution":{"observed_at":"2026-08-07T11:03:12.525466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.512959Z","title":"Program induction by rationale generation: Learning to solve and explain algebraic word problems,","venue":null,"work_id":"d5bb74ee-567a-438b-b63b-de4f0940caa2","year":2017},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.162304Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:ada109affef3c40d2849e7a0a051cbbd177f09b97e4506f6a8253e2c83241e1b","observation_id":"2f29dd02-10b9-4123-b3e1-e958477fcc96","resolution":{"observed_at":"2026-08-07T11:03:12.517249Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.504444Z","title":"Parsing algebraic word problems into equations,","venue":null,"work_id":"30a20803-6cbd-4dad-ba3f-d40f85478803","year":2015},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.165228Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:918ba0996ad5871ada55e70af73cc7838b84b73cfb4a7d884a14bc6907803ea1","observation_id":"afb56c2d-3096-4ab0-807d-a8e742f15a69","resolution":{"observed_at":"2026-08-07T11:03:12.507616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.496070Z","title":"Are NLP models really able to solve simple math word problems?,","venue":null,"work_id":"2fd7b418-34ac-47cd-a7a1-263ded057e33","year":2021},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.167704Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:3cb3d85eed43fa8eeececd97b5c433f27e8a8d9aa59c24fdd2dcc08ed77758f8","observation_id":"bdb4f8f3-6016-40fa-b9d9-257549d9958d","resolution":{"observed_at":"2026-08-07T11:03:12.499112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.483685Z","title":"Solving general arithmetic word problems,","venue":null,"work_id":"8b78fe4b-fda2-4d6f-8746-89be518302b3","year":2015},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.170152Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:89950c97c196b89290a773d353f7b912104caebea039a767cd175879100fa41c","observation_id":"11107f31-72a6-4a8c-a6dd-a015938ab8f1","resolution":{"observed_at":"2026-08-07T11:03:12.489861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.474084Z","title":"Learning to solve arithmetic word problems with verb categorization,","venue":null,"work_id":"0f63e95a-c07e-41f1-86f7-108b25b12677","year":2014},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.173092Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:f62ad0269354f00e528e0f495d913c72b0454494e0b207af58c6b0ea95886223","observation_id":"2f672979-0e3f-44b0-a86f-105c5aa31732","resolution":{"observed_at":"2026-08-07T11:03:12.477599Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.21276","last_updated":"2024-10-25T17:43:01Z","snapshot_observed_at":"2026-08-15T14:02:47.366139Z","submitted_at":"2024-10-25T17:43:01Z","title":"GPT-4o System Card","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.21276","snapshot_observed_at":"2026-08-07T11:03:12.175549Z","title":"Gpt-4o system card,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.175549Z"},"links":{"cited_paper":"/paper/2410.21276","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:a9b1dbafc4dd411cb7f828d6bacefae31baaff63a99ed7d5363d7b4ccbb60469","observation_id":"de4a306e-65d1-4874-8926-9d73cce336b9","resolution":{"observed_at":"2026-08-07T11:03:12.175549Z","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":"2026-08-07T11:03:12.178427Z","title":"Training language models to follow instructions with human feedback,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.178427Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:ed7ff48e25a324d255ede425ef69ace37630bf6d5a3f90772ec32becb8b3f84a","observation_id":"8bc96f30-9252-406f-99de-4d55edb2a4dc","resolution":{"observed_at":"2026-08-07T11:03:12.178427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.16720","last_updated":"2026-04-30T02:46:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-21T18:04:31Z","title":"OpenAI o1 System Card","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.16720","snapshot_observed_at":"2026-08-07T11:03:12.181183Z","title":"Openai o1 system card,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.181183Z"},"links":{"cited_paper":"/paper/2412.16720","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:4fa3ca0149e5123b3a3ee90e852e4e5c44f3a3fce284a17d19efbf315880c1d7","observation_id":"9caba623-246e-443d-8aa4-6a61711a7094","resolution":{"observed_at":"2026-08-07T11:03:12.181183Z","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":"2026-08-07T11:03:12.183905Z","title":"Openai o3 and o4-mini system card,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.183905Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:e2e4f626a679212d6cd75eabcd7390d861fb77e79ce9cbc98b2ad4c22487a829","observation_id":"42e98503-fd3e-4237-a180-b18dfb4b1a9d","resolution":{"observed_at":"2026-08-07T11:03:12.183905Z","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":"2026-08-07T11:03:12.437568Z","title":"Promptagent: Strategic planning with language models enables expert-level prompt optimization,","venue":null,"work_id":"36156c5f-a7b0-418e-9ecd-815659ebb1ed","year":2024},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.187306Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:ddcf98e6494ddb11b36b87d0e235ba8dfbb68eeee5a74ad6e8a6e03ec6b7b6c9","observation_id":"469e2940-05f4-48f0-bc45-6d8794a81321","resolution":{"observed_at":"2026-08-07T11:03:12.460533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04615","last_updated":"2023-06-12T17:51:15Z","snapshot_observed_at":"2026-07-06T13:19:12.109592Z","submitted_at":"2022-06-09T17:05:34Z","title":"Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04615","snapshot_observed_at":"2026-08-07T11:03:12.189700Z","title":"Beyond the imitation game: Quantifying and extrapolating the capabilities of language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.189700Z"},"links":{"cited_paper":"/paper/2206.04615","citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:77b2c6cfdf3e1319f319ae2bd7ae257b966c6e1092bc81ccdc871c7f6ef0ac7b","observation_id":"5b6662ec-59ff-40ca-bd14-983913805e19","resolution":{"observed_at":"2026-08-07T11:03:12.189700Z","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":"2026-08-07T11:03:12.297365Z","title":"CommonsenseQA: A question answering challenge targeting commonsense knowledge,","venue":null,"work_id":"a0b12da5-01c7-4578-9c03-90799ca281fd","year":2019},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.194246Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:011f764c5149f20ccffc7186b1a413618b615b11f32f198db3a67639768fc9b0","observation_id":"4b6396ea-85e4-4023-ae28-89a02a09b163","resolution":{"observed_at":"2026-08-07T11:03:12.350500Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-07T11:03:12.274034Z","title":"Did Aristotle Use a Laptop? A Question Answering Benchmark with Implicit Reasoning Strategies,","venue":null,"work_id":"d26df482-a1e7-4051-84e6-c4c2f9a064f2","year":2021},"citing_paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T11:03:12.199715Z"},"links":{"citing_paper":"/paper/2506.03627"},"observation_digest":"sha256:387b3f2ff255a4f954b4d6b21fd49c397a634321939830148b07e1cb8afacd00","observation_id":"3c7906cb-991a-4f78-a122-b4fcc5ceca94","resolution":{"observed_at":"2026-08-07T11:03:12.284759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.03627","last_updated":"2026-05-26T01:05:41Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T07:57:06.639067Z","submitted_at":"2025-06-04T07:13:27Z","title":"Robustness of Prompting: Enhancing Robustness of Large Language Models Against Prompting Attacks"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":19},"total_outbound_references":31},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2506.03627."}