{"as_of":"2026-08-09T08:10:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:16e8ff5a0de71dd730c48c220f5dc94355af6edeb06fe0a626b2682a3f462c2b","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":16,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":16,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T13:54:58.012525Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":13,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2401.05561","last_updated":"2024-09-30T10:17:12Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-10T22:07:21Z","title":"TrustLLM: Trustworthiness in Large Language Models","version":6},"reference_index":271,"source":"pdf_text","source_observed_at":"2026-05-18T11:17:08.108565Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2401.05561"},"observation_digest":"sha256:8028d5019f2c5dcbf3deffbf5aa680d0f4c42f4143462e6945ac959d9498dcca","observation_id":"0664db29-b933-4dc5-a11c-859a3ad58187","resolution":{"observed_at":"2026-05-18T11:17:08.780802Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2412.05579","last_updated":"2024-12-10T05:49:12Z","snapshot_observed_at":"2026-07-31T01:42:39.468673Z","submitted_at":"2024-12-07T08:07:24Z","title":"LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods","version":2},"reference_index":269,"source":"pdf_text","source_observed_at":"2026-05-11T23:08:34.312466Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2412.05579"},"observation_digest":"sha256:7b8ee6b4e13790dd86f3c2103f2b9d450456cd60837f33f3ee4c3811a5fcff09","observation_id":"2c958187-762d-457b-9b89-bda4e45cd29a","resolution":{"observed_at":"2026-05-11T23:08:35.801885Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","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":"2026-08-08T13:54:58.012525Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.07101","last_updated":"2025-02-10T22:46:57Z","snapshot_observed_at":"2026-08-09T02:41:02.274023Z","submitted_at":"2025-02-10T22:46:57Z","title":"SMAB: MAB based word Sensitivity Estimation Framework and its Applications in Adversarial Text Generation","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T13:54:58.012525Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2502.07101"},"observation_digest":"sha256:399d3c4ba75546b5bace4145b472c65d85b1700fc4cdc181414bf65ff0182af7","observation_id":"66b63fee-6e24-4a2b-b768-5dd9fcfc0def","resolution":{"observed_at":"2026-08-08T13:54:58.012525Z","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":"2026-08-07T01:43:48.385782Z","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":"2026-08-07T14:10:29.095286Z","title":"An llm can fool itself: A prompt-based adversarial attack.arXiv preprint arXiv:2310.13345, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.19864","last_updated":"2025-05-26T11:48:32Z","snapshot_observed_at":"2026-08-07T14:02:49.934041Z","submitted_at":"2025-05-26T11:48:32Z","title":"CPA-RAG:Covert Poisoning Attacks on Retrieval-Augmented Generation in Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T14:10:29.095286Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2505.19864"},"observation_digest":"sha256:e386f5fea1c47482b19dee314cc0c22b82d586917afd22459fe25c27a5aabf12","observation_id":"ad3665db-4331-49e8-bf14-e2d05e012165","resolution":{"observed_at":"2026-08-07T14:10:29.095286Z","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":"2026-08-07T01:43:48.385782Z","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":"2026-08-07T10:56:28.347809Z","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":"sha256:845b8ec8397208012b1406931ac20f499611b3ee6eaa4325da97733e5312890a","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":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","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":"2026-08-07T10:29:44.506141Z","title":"arXiv preprint arXiv:2310.13345 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05286","last_updated":"2025-06-05T17:43:27Z","snapshot_observed_at":"2026-08-07T22:50:28.502631Z","submitted_at":"2025-06-05T17:43:27Z","title":"Stable Vision Concept Transformers for Medical Diagnosis","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T10:29:44.506141Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2506.05286"},"observation_digest":"sha256:ce1f4bb44cf529933f94f743ba7fd37079e4ab1a80e012223642dc013d87b447","observation_id":"d036bc74-6729-4730-a8e7-344ed3dd9f4e","resolution":{"observed_at":"2026-08-07T10:29:44.506141Z","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":"2026-08-07T01:43:48.385782Z","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":"2026-08-07T11:00:54.087989Z","title":"An llm can fool itself: A prompt-based adversarial attack.arXiv preprint arXiv:2310.13345, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.06366","last_updated":"2025-06-12T10:22:01Z","snapshot_observed_at":"2026-08-08T03:51:35.989314Z","submitted_at":"2025-06-04T08:12:32Z","title":"AI Agent Behavioral Science","version":3},"reference_index":174,"source":"pdf_text","source_observed_at":"2026-08-07T11:00:54.087989Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2506.06366"},"observation_digest":"sha256:e708ddd8ace0c74f98b22cd5fedbe372848cb023875b643c172dff3ba19990f3","observation_id":"3c4fbc80-487a-42b6-afbd-7bf4c346500c","resolution":{"observed_at":"2026-08-07T11:00:54.087989Z","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":"2026-08-07T01:43:48.385782Z","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":"2026-08-07T05:43:35.300296Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.07184","last_updated":"2025-06-08T15:08:52Z","snapshot_observed_at":"2026-08-08T16:44:02.022482Z","submitted_at":"2025-06-08T15:08:52Z","title":"Mitigating Behavioral Hallucination in Multimodal Large Language Models for Sequential Images","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T05:43:35.300296Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2506.07184"},"observation_digest":"sha256:8d278977605d52f72e16d6a4e2c604c3a5d8cffc8711bc9b8de31e47feae7471","observation_id":"a49bcc17-1f88-4835-9860-f7d9666e8067","resolution":{"observed_at":"2026-08-07T05:43:35.300296Z","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":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2507.05660","last_updated":"2026-05-21T16:31:21Z","snapshot_observed_at":"2026-07-29T18:54:03.959574Z","submitted_at":"2025-07-08T04:40:09Z","title":"Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI","version":3},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-05-22T12:17:59.458633Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2507.05660"},"observation_digest":"sha256:272d7bb1f3e1382880c7968cfa5cba0ff307c7cbd174ead80dce8ec4075902ec","observation_id":"c2b617af-1ddb-4b57-94bc-dcd7c3bea922","resolution":{"observed_at":"2026-05-22T12:21:31.125849Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","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":"2026-08-06T05:29:20.296271Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.01781","last_updated":"2025-08-03T14:37:16Z","snapshot_observed_at":"2026-08-07T21:40:51.636920Z","submitted_at":"2025-08-03T14:37:16Z","title":"A comprehensive taxonomy of hallucinations in Large Language Models","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-06T05:29:20.296271Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2508.01781"},"observation_digest":"sha256:ad2df49eb07ccfc005ccdbe3a1b817fe6ad8562f5db8147fdf329fbdb19ce59e","observation_id":"935b09e4-0305-4d31-b7ce-cf784eff5c55","resolution":{"observed_at":"2026-08-06T05:29:20.296271Z","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":"2026-08-07T01:43:48.385782Z","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":"2026-08-05T17:26:48.566674Z","title":"An llm can fool itself: A prompt-based adversarial attack.arXiv preprint arXiv:2310.13345, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.16318","last_updated":"2025-09-01T08:35:27Z","snapshot_observed_at":"2026-08-07T01:49:06.395378Z","submitted_at":"2025-08-22T11:57:55Z","title":"SATORI: Static Test Oracle Generation for REST APIs","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T17:26:48.566674Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2508.16318"},"observation_digest":"sha256:8633ecc49edb7621efa9e1b07aa128278be942d7a809d4d3b43c236c0b474651","observation_id":"94009e85-a9e6-40a2-bae6-8286cba4e480","resolution":{"observed_at":"2026-08-05T17:26:48.566674Z","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":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2602.00979","last_updated":"2026-05-22T03:20:51Z","snapshot_observed_at":"2026-08-03T15:56:56.036971Z","submitted_at":"2026-02-01T02:39:51Z","title":"GradingAttack: Exposing Security Vulnerabilities in LLM Based Educational Grading Agents","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-25T07:02:28.660002Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2602.00979"},"observation_digest":"sha256:12c02fd549199d2d3b48fa9d5fedf24b98dfaa41647385b68c9da59370085933","observation_id":"4787619a-ca0e-4ceb-8121-ef48f21c05f6","resolution":{"observed_at":"2026-05-25T07:05:26.669251Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2604.19724","last_updated":"2026-04-21T17:48:51Z","snapshot_observed_at":"2026-08-06T08:43:13.824032Z","submitted_at":"2026-04-21T17:48:51Z","title":"Benign Overfitting in Adversarial Training for Vision Transformers","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-05-10T02:58:29.672338Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2604.19724"},"observation_digest":"sha256:9cfdf0b89b67d843094fcec1dfa56cbf1d32e2699043e12bcb2b7bc8fa429a86","observation_id":"b00ef2a5-1dc9-46e1-9878-90a4131980d6","resolution":{"observed_at":"2026-05-11T12:46:21.061239Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2605.16551","last_updated":"2026-06-08T17:56:23Z","snapshot_observed_at":"2026-07-31T17:39:46.872890Z","submitted_at":"2026-05-15T18:50:43Z","title":"PQR: A Framework to Generate Diverse and Realistic User Queries that Elicit QA Agent Failures","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-05-20T18:03:07.646917Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2605.16551"},"observation_digest":"sha256:00b300175b2ff7356e3dd4ed6a05692ff5182a4f5c779f98c5692c2088e65b77","observation_id":"b6b36e91-b6ad-4cb9-8cbc-33b1de7fd6fb","resolution":{"observed_at":"2026-05-20T18:03:36.748253Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2606.09388","last_updated":"2026-06-08T12:03:51Z","snapshot_observed_at":"2026-08-07T01:03:05.186184Z","submitted_at":"2026-06-08T12:03:51Z","title":"Distilling Safe LLM Systems via Soft Prompts for On Device Settings","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-06-27T17:15:51.375580Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2606.09388"},"observation_digest":"sha256:bb400565fea71b3c12502fb8a5eeec40744d03229890d8629b54985032841244","observation_id":"275b586b-3586-4265-8cde-f189cc396a80","resolution":{"observed_at":"2026-07-03T00:27:29.237616Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack","version":1},"cited_work":{"arxiv_id":"2310.13345","doi":"10.48550/arxiv.2310.13345","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.13345","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"An llm can fool itself: A prompt-based adversarial attack","venue":"arXiv (Cornell University)","work_id":"fd846fb3-a9f6-4aaa-9fd4-673adbd9dfd3","year":2023},"citing_paper":{"arxiv_id":"2606.30556","last_updated":"2026-06-29T16:51:31Z","snapshot_observed_at":"2026-08-07T13:43:00.994295Z","submitted_at":"2026-06-29T16:51:31Z","title":"Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-06-30T05:59:58.183264Z"},"links":{"cited_paper":"/paper/2310.13345","citing_paper":"/paper/2606.30556"},"observation_digest":"sha256:05edb427b0f923a50fb3691d121e6a68006575e5469155da8be747196007feba","observation_id":"97c10da7-4b51-4b51-821a-9ca4411c7f67","resolution":{"observed_at":"2026-06-30T06:04:21.525917Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T00:53:09.651738+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2310.13345/citation-record","integrity":"/paper/2310.13345/integrity","json":"/paper/2310.13345/citation-record.json","paper":"/paper/2310.13345"},"outbound":[],"paper":{"arxiv_id":"2310.13345","last_updated":"2023-10-20T08:16:46Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T01:43:48.385782Z","submitted_at":"2023-10-20T08:16:46Z","title":"An LLM can Fool Itself: A Prompt-Based Adversarial Attack"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 16 inbound Pith citation observations for arXiv:2310.13345."}