{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:L5LV6M5C53Z5L7YNKR5UFHP2CG","short_pith_number":"pith:L5LV6M5C","canonical_record":{"source":{"id":"2406.11020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:26:44Z","cross_cats_sorted":[],"title_canon_sha256":"1790ddd2bbe3e09d33237b7283ef234804173c989141df948082c3c2d70308a5","abstract_canon_sha256":"54f2047a35f6e6364aab2cec41d3ea7cb188f9fff0ec69f738ab1b3aba9699cf"},"schema_version":"1.0"},"canonical_sha256":"5f575f33a2eef3d5ff0d547b429dfa11999ff1b71f9d7abebb6d96f65411b95c","source":{"kind":"arxiv","id":"2406.11020","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11020","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11020v1","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11020","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"L5LV6M5C53Z5","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"L5LV6M5C53Z5L7YN","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"L5LV6M5C","created_at":"2026-07-05T08:32:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:L5LV6M5C53Z5L7YNKR5UFHP2CG","target":"record","payload":{"canonical_record":{"source":{"id":"2406.11020","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:26:44Z","cross_cats_sorted":[],"title_canon_sha256":"1790ddd2bbe3e09d33237b7283ef234804173c989141df948082c3c2d70308a5","abstract_canon_sha256":"54f2047a35f6e6364aab2cec41d3ea7cb188f9fff0ec69f738ab1b3aba9699cf"},"schema_version":"1.0"},"canonical_sha256":"5f575f33a2eef3d5ff0d547b429dfa11999ff1b71f9d7abebb6d96f65411b95c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:47.672554Z","signature_b64":"H/zj+2EGb6m70GYnrHxRAIVwCWIbDU8hkKHuWv8YvQFpBAF1I5tB40yWaeYFx04KmfYxKRErxqcP9TYdHfGYAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f575f33a2eef3d5ff0d547b429dfa11999ff1b71f9d7abebb6d96f65411b95c","last_reissued_at":"2026-07-05T08:32:47.672081Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:47.672081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.11020","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":"2026-07-05T08:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AGlkJGOoZwWoOSHdvAAvEwas0KCUtEZ1FThYZvgi3U0WT3BpfhHlw4WcADPBLpH7vVs0+vkaqUoyTBfq7tOYAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:09:34.113609Z"},"content_sha256":"95163e5484d440910e56e5509c42bf7c4415e4ca10cb6b84928b1ab6ef3d3834","schema_version":"1.0","event_id":"sha256:95163e5484d440910e56e5509c42bf7c4415e4ca10cb6b84928b1ab6ef3d3834"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:L5LV6M5C53Z5L7YNKR5UFHP2CG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RUPBench: Benchmarking Reasoning Under Perturbations for Robustness Evaluation in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Yun Zhao, Yuqing Wang","submitted_at":"2024-06-16T17:26:44Z","abstract_excerpt":"With the increasing use of large language models (LLMs), ensuring reliable performance in diverse, real-world environments is essential. Despite their remarkable achievements, LLMs often struggle with adversarial inputs, significantly impacting their effectiveness in practical applications. To systematically understand the robustness of LLMs, we present RUPBench, a comprehensive benchmark designed to evaluate LLM robustness across diverse reasoning tasks. Our benchmark incorporates 15 reasoning datasets, categorized into commonsense, arithmetic, logical, and knowledge-intensive reasoning, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11020","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/2406.11020/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":"2026-07-05T08:32:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oLEKktvRA7i38JHyEkkHkkPwi5mvLYQ7wJPe3/m+ZUHWIKGaY467+gv9D903L2MntX+Hu9KOW60m15kSELXQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:09:34.114188Z"},"content_sha256":"5b7d4f27212ffbe826e20f29e2ad5832edd2ebbf9d8a0cb1e2c13b345cd09b8f","schema_version":"1.0","event_id":"sha256:5b7d4f27212ffbe826e20f29e2ad5832edd2ebbf9d8a0cb1e2c13b345cd09b8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG/bundle.json","state_url":"https://pith.science/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG/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":"2026-08-19T14:09:34Z","links":{"resolver":"https://pith.science/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG","bundle":"https://pith.science/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG/bundle.json","state":"https://pith.science/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L5LV6M5C53Z5L7YNKR5UFHP2CG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:L5LV6M5C53Z5L7YNKR5UFHP2CG","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":"54f2047a35f6e6364aab2cec41d3ea7cb188f9fff0ec69f738ab1b3aba9699cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:26:44Z","title_canon_sha256":"1790ddd2bbe3e09d33237b7283ef234804173c989141df948082c3c2d70308a5"},"schema_version":"1.0","source":{"id":"2406.11020","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.11020","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"arxiv_version","alias_value":"2406.11020v1","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11020","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_12","alias_value":"L5LV6M5C53Z5","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_16","alias_value":"L5LV6M5C53Z5L7YN","created_at":"2026-07-05T08:32:47Z"},{"alias_kind":"pith_short_8","alias_value":"L5LV6M5C","created_at":"2026-07-05T08:32:47Z"}],"graph_snapshots":[{"event_id":"sha256:5b7d4f27212ffbe826e20f29e2ad5832edd2ebbf9d8a0cb1e2c13b345cd09b8f","target":"graph","created_at":"2026-07-05T08:32:47Z","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/2406.11020/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the increasing use of large language models (LLMs), ensuring reliable performance in diverse, real-world environments is essential. Despite their remarkable achievements, LLMs often struggle with adversarial inputs, significantly impacting their effectiveness in practical applications. To systematically understand the robustness of LLMs, we present RUPBench, a comprehensive benchmark designed to evaluate LLM robustness across diverse reasoning tasks. Our benchmark incorporates 15 reasoning datasets, categorized into commonsense, arithmetic, logical, and knowledge-intensive reasoning, and ","authors_text":"Yun Zhao, Yuqing Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:26:44Z","title":"RUPBench: Benchmarking Reasoning Under Perturbations for Robustness Evaluation in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11020","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":"sha256:95163e5484d440910e56e5509c42bf7c4415e4ca10cb6b84928b1ab6ef3d3834","target":"record","created_at":"2026-07-05T08:32:47Z","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":"54f2047a35f6e6364aab2cec41d3ea7cb188f9fff0ec69f738ab1b3aba9699cf","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-16T17:26:44Z","title_canon_sha256":"1790ddd2bbe3e09d33237b7283ef234804173c989141df948082c3c2d70308a5"},"schema_version":"1.0","source":{"id":"2406.11020","kind":"arxiv","version":1}},"canonical_sha256":"5f575f33a2eef3d5ff0d547b429dfa11999ff1b71f9d7abebb6d96f65411b95c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f575f33a2eef3d5ff0d547b429dfa11999ff1b71f9d7abebb6d96f65411b95c","first_computed_at":"2026-07-05T08:32:47.672081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:32:47.672081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H/zj+2EGb6m70GYnrHxRAIVwCWIbDU8hkKHuWv8YvQFpBAF1I5tB40yWaeYFx04KmfYxKRErxqcP9TYdHfGYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:32:47.672554Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.11020","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95163e5484d440910e56e5509c42bf7c4415e4ca10cb6b84928b1ab6ef3d3834","sha256:5b7d4f27212ffbe826e20f29e2ad5832edd2ebbf9d8a0cb1e2c13b345cd09b8f"],"state_sha256":"75f2a44d8f9c65d3e99d94a5378553250095712369916501501821e0d2a879ea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y00SukBLzUxBiIYC/uwpsQdMZH1+HWwZaconWHxaH/0N1StBxutkbzwLiFSuZY6yYqYQyGF//Ix660gzLtrbAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:09:34.120963Z","bundle_sha256":"bb7911e080fd161a803846365ced8bc1a6b6c9be98c1da095aed3f5afb8d7255"}}