{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:AZBDYHXMEMVZYGVIGOA5BBPLRC","short_pith_number":"pith:AZBDYHXM","canonical_record":{"source":{"id":"2505.13195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T14:50:44Z","cross_cats_sorted":[],"title_canon_sha256":"b842b0821eca5eb807904abf06b8b44520095addd9a527bfee41e87aa0d2d50f","abstract_canon_sha256":"82506cdc18d26e5b3376b5ad1234b60449a4290cc2f01feb789e410d381f813d"},"schema_version":"1.0"},"canonical_sha256":"06423c1eec232b9c1aa83381d085eb88a5a1ec8bedefe451c4110c4a829edd6c","source":{"kind":"arxiv","id":"2505.13195","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13195","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13195v1","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13195","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"AZBDYHXMEMVZ","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"AZBDYHXMEMVZYGVI","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"AZBDYHXM","created_at":"2026-07-05T11:05:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:AZBDYHXMEMVZYGVIGOA5BBPLRC","target":"record","payload":{"canonical_record":{"source":{"id":"2505.13195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T14:50:44Z","cross_cats_sorted":[],"title_canon_sha256":"b842b0821eca5eb807904abf06b8b44520095addd9a527bfee41e87aa0d2d50f","abstract_canon_sha256":"82506cdc18d26e5b3376b5ad1234b60449a4290cc2f01feb789e410d381f813d"},"schema_version":"1.0"},"canonical_sha256":"06423c1eec232b9c1aa83381d085eb88a5a1ec8bedefe451c4110c4a829edd6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:26.493739Z","signature_b64":"ONxNIeJ8Jg4opvvtiyRPf/ePuBWF4ARdlUZoIA39D+7qgHuuWz3W7FSXEyaXRXbYSbzo7dCKO1q9GRde/GmVAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06423c1eec232b9c1aa83381d085eb88a5a1ec8bedefe451c4110c4a829edd6c","last_reissued_at":"2026-07-05T11:05:26.493158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:26.493158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.13195","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jsAsWKzxNL3YO8YjsLBL4JkeUA8OCgVVl/scCAoiBZTHy+lsJdE7Pnh6skst8mb+e6bjw9YRKo45KynCDVUFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:19:18.415566Z"},"content_sha256":"2ef005f9e21cbf7f093a67ac4508cde38df3ba462a99f77692de4607d2cf8bec","schema_version":"1.0","event_id":"sha256:2ef005f9e21cbf7f093a67ac4508cde38df3ba462a99f77692de4607d2cf8bec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:AZBDYHXMEMVZYGVIGOA5BBPLRC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haomiaomiao Wang, Libao Deng, Lili Zhang, Long Cheng, Tomas Ward","submitted_at":"2025-05-19T14:50:44Z","abstract_excerpt":"As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation metrics focus primarily on reasoning accuracy or factual correctness, they often overlook whether LLMs are robust to adversarial manipulation or capable of using adaptive strategy in dynamic environments. This paper introduces an adversarial evaluation framework designed to systematically stress-test the decision-making processes of LLMs under interactive and ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13195","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.13195/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:05:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3EnT+deVm7RQw4qsvbPtdowdjcB7RorcLJaTHHUo/HrzPv3wpSEFqiCyHCjjGrVN8kMWo/synV/sOURUKRQjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T07:19:18.417283Z"},"content_sha256":"2b98a9810896d7131d75b970989e5e9c29b0804c8a469c60c45331c22c5b899b","schema_version":"1.0","event_id":"sha256:2b98a9810896d7131d75b970989e5e9c29b0804c8a469c60c45331c22c5b899b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC/bundle.json","state_url":"https://pith.science/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T07:19:18Z","links":{"resolver":"https://pith.science/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC","bundle":"https://pith.science/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC/bundle.json","state":"https://pith.science/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AZBDYHXMEMVZYGVIGOA5BBPLRC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AZBDYHXMEMVZYGVIGOA5BBPLRC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"82506cdc18d26e5b3376b5ad1234b60449a4290cc2f01feb789e410d381f813d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T14:50:44Z","title_canon_sha256":"b842b0821eca5eb807904abf06b8b44520095addd9a527bfee41e87aa0d2d50f"},"schema_version":"1.0","source":{"id":"2505.13195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.13195","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.13195v1","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13195","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_12","alias_value":"AZBDYHXMEMVZ","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_16","alias_value":"AZBDYHXMEMVZYGVI","created_at":"2026-07-05T11:05:26Z"},{"alias_kind":"pith_short_8","alias_value":"AZBDYHXM","created_at":"2026-07-05T11:05:26Z"}],"graph_snapshots":[{"event_id":"sha256:2b98a9810896d7131d75b970989e5e9c29b0804c8a469c60c45331c22c5b899b","target":"graph","created_at":"2026-07-05T11:05:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.13195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) become increasingly integrated into real-world decision-making systems, understanding their behavioural vulnerabilities remains a critical challenge for AI safety and alignment. While existing evaluation metrics focus primarily on reasoning accuracy or factual correctness, they often overlook whether LLMs are robust to adversarial manipulation or capable of using adaptive strategy in dynamic environments. This paper introduces an adversarial evaluation framework designed to systematically stress-test the decision-making processes of LLMs under interactive and ad","authors_text":"Haomiaomiao Wang, Libao Deng, Lili Zhang, Long Cheng, Tomas Ward","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T14:50:44Z","title":"Adversarial Testing in LLMs: Insights into Decision-Making Vulnerabilities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13195","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2ef005f9e21cbf7f093a67ac4508cde38df3ba462a99f77692de4607d2cf8bec","target":"record","created_at":"2026-07-05T11:05:26Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"82506cdc18d26e5b3376b5ad1234b60449a4290cc2f01feb789e410d381f813d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-19T14:50:44Z","title_canon_sha256":"b842b0821eca5eb807904abf06b8b44520095addd9a527bfee41e87aa0d2d50f"},"schema_version":"1.0","source":{"id":"2505.13195","kind":"arxiv","version":1}},"canonical_sha256":"06423c1eec232b9c1aa83381d085eb88a5a1ec8bedefe451c4110c4a829edd6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"06423c1eec232b9c1aa83381d085eb88a5a1ec8bedefe451c4110c4a829edd6c","first_computed_at":"2026-07-05T11:05:26.493158Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:26.493158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ONxNIeJ8Jg4opvvtiyRPf/ePuBWF4ARdlUZoIA39D+7qgHuuWz3W7FSXEyaXRXbYSbzo7dCKO1q9GRde/GmVAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:26.493739Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.13195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2ef005f9e21cbf7f093a67ac4508cde38df3ba462a99f77692de4607d2cf8bec","sha256:2b98a9810896d7131d75b970989e5e9c29b0804c8a469c60c45331c22c5b899b"],"state_sha256":"ac68f292cdf239d0414a3fdef804737fccebd0100ac84ec1cf9a34fb505b3697"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FwQgvlGic4wLhwulu1++1WCQ1tD2Eh8ASVEoT0tieYzBUBnNvJTxD0suPkpwAO1lMAXbXqLwvrpV2VAQk9EXAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T07:19:18.430341Z","bundle_sha256":"218dffb5c3945fd3a612b399868bb00543de1d2964d127e9d01b6d477e09af93"}}