{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6G7GCSIIXNIOHZKWLUIT6QBAPH","short_pith_number":"pith:6G7GCSII","canonical_record":{"source":{"id":"2402.11100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:12:53Z","cross_cats_sorted":[],"title_canon_sha256":"29353415238792c43627be8660edc84afd924e4f4123c3ab191819365b2cbd1f","abstract_canon_sha256":"8dc1b22403278af71aed61277e0a4aa4cc3bde28168fff0776523869c0a218c3"},"schema_version":"1.0"},"canonical_sha256":"f1be614908bb50e3e5565d113f402079c99143ff3ea148b6b4611b82c8850935","source":{"kind":"arxiv","id":"2402.11100","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11100","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11100v2","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11100","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"6G7GCSIIXNIO","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"6G7GCSIIXNIOHZKW","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"6G7GCSII","created_at":"2026-07-05T08:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6G7GCSIIXNIOHZKWLUIT6QBAPH","target":"record","payload":{"canonical_record":{"source":{"id":"2402.11100","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:12:53Z","cross_cats_sorted":[],"title_canon_sha256":"29353415238792c43627be8660edc84afd924e4f4123c3ab191819365b2cbd1f","abstract_canon_sha256":"8dc1b22403278af71aed61277e0a4aa4cc3bde28168fff0776523869c0a218c3"},"schema_version":"1.0"},"canonical_sha256":"f1be614908bb50e3e5565d113f402079c99143ff3ea148b6b4611b82c8850935","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:22.393012Z","signature_b64":"bcthFBty8T/4LIzBsaqqSafTXg8W/HYixGo1yA35sauieg8YbmVdt1kxy4sWJFunm5LTSFURM6ypuR62M6nZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1be614908bb50e3e5565d113f402079c99143ff3ea148b6b4611b82c8850935","last_reissued_at":"2026-07-05T08:29:22.392574Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:22.392574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.11100","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jgn2S1lbuo1K6z3IUATBzgiY6y986ODREK91q90VvoqTWpcI2AcIh1ABrPMWv9UJYAVmWlmGWapnQ6EpreT5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:57:19.069323Z"},"content_sha256":"15c2522d2c93a73ac9a75ab681aa7afd3b0db3b3491412a81255d73788ae9e8f","schema_version":"1.0","event_id":"sha256:15c2522d2c93a73ac9a75ab681aa7afd3b0db3b3491412a81255d73788ae9e8f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6G7GCSIIXNIOHZKWLUIT6QBAPH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai-Tao Zheng, Philip S. Yu, Qingyu Zhou, Shirong Ma, Xuming Hu, Yangning Li, Yinghui Li, Yuanzhen Luo","submitted_at":"2024-02-16T22:12:53Z","abstract_excerpt":"Recently, Large Language Models (LLMs) make remarkable evolutions in language understanding and generation. Following this, various benchmarks for measuring all kinds of capabilities of LLMs have sprung up. In this paper, we challenge the reasoning and understanding abilities of LLMs by proposing a FaLlacy Understanding Benchmark (FLUB) containing cunning texts that are easy for humans to understand but difficult for models to grasp. Specifically, the cunning texts that FLUB focuses on mainly consist of the tricky, humorous, and misleading texts collected from the real internet environment. An"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11100","kind":"arxiv","version":2},"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/2402.11100/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":"2026-07-05T08:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iI/I/dCk2L/rQbCdMA+bZxtqp2rFbRHm9VnA/Gmdpb5VpMqwepK1eLJhjP4ofUUrGvsBJ605LWaygxzRDTOcDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T18:57:19.070703Z"},"content_sha256":"52a5f7fd3fde9e81912273805fca6f9bf0a312726e6633db5009df001b9f5aa5","schema_version":"1.0","event_id":"sha256:52a5f7fd3fde9e81912273805fca6f9bf0a312726e6633db5009df001b9f5aa5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH/bundle.json","state_url":"https://pith.science/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH/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":"2026-08-04T18:57:19Z","links":{"resolver":"https://pith.science/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH","bundle":"https://pith.science/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH/bundle.json","state":"https://pith.science/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6G7GCSIIXNIOHZKWLUIT6QBAPH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6G7GCSIIXNIOHZKWLUIT6QBAPH","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":"8dc1b22403278af71aed61277e0a4aa4cc3bde28168fff0776523869c0a218c3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:12:53Z","title_canon_sha256":"29353415238792c43627be8660edc84afd924e4f4123c3ab191819365b2cbd1f"},"schema_version":"1.0","source":{"id":"2402.11100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.11100","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2402.11100v2","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11100","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"6G7GCSIIXNIO","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"6G7GCSIIXNIOHZKW","created_at":"2026-07-05T08:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"6G7GCSII","created_at":"2026-07-05T08:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:52a5f7fd3fde9e81912273805fca6f9bf0a312726e6633db5009df001b9f5aa5","target":"graph","created_at":"2026-07-05T08:29:22Z","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/2402.11100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Large Language Models (LLMs) make remarkable evolutions in language understanding and generation. Following this, various benchmarks for measuring all kinds of capabilities of LLMs have sprung up. In this paper, we challenge the reasoning and understanding abilities of LLMs by proposing a FaLlacy Understanding Benchmark (FLUB) containing cunning texts that are easy for humans to understand but difficult for models to grasp. Specifically, the cunning texts that FLUB focuses on mainly consist of the tricky, humorous, and misleading texts collected from the real internet environment. An","authors_text":"Hai-Tao Zheng, Philip S. Yu, Qingyu Zhou, Shirong Ma, Xuming Hu, Yangning Li, Yinghui Li, Yuanzhen Luo","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:12:53Z","title":"When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11100","kind":"arxiv","version":2},"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":"sha256:15c2522d2c93a73ac9a75ab681aa7afd3b0db3b3491412a81255d73788ae9e8f","target":"record","created_at":"2026-07-05T08:29:22Z","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":"8dc1b22403278af71aed61277e0a4aa4cc3bde28168fff0776523869c0a218c3","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-16T22:12:53Z","title_canon_sha256":"29353415238792c43627be8660edc84afd924e4f4123c3ab191819365b2cbd1f"},"schema_version":"1.0","source":{"id":"2402.11100","kind":"arxiv","version":2}},"canonical_sha256":"f1be614908bb50e3e5565d113f402079c99143ff3ea148b6b4611b82c8850935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f1be614908bb50e3e5565d113f402079c99143ff3ea148b6b4611b82c8850935","first_computed_at":"2026-07-05T08:29:22.392574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:22.392574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bcthFBty8T/4LIzBsaqqSafTXg8W/HYixGo1yA35sauieg8YbmVdt1kxy4sWJFunm5LTSFURM6ypuR62M6nZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:22.393012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.11100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15c2522d2c93a73ac9a75ab681aa7afd3b0db3b3491412a81255d73788ae9e8f","sha256:52a5f7fd3fde9e81912273805fca6f9bf0a312726e6633db5009df001b9f5aa5"],"state_sha256":"44838723c6968c77b3cf4ebf7e7de8fe2c0137fabd47a0e7da2298f6f4bb9f3d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"knEnL4OPTIECIMqxXP2IZ/RT67NCPqRymMr/aBV5+GeUsl9rK7XQd82I10GaBBGqg75u12Cr022Tb+H+Mv97AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T18:57:19.078244Z","bundle_sha256":"a2b8fbb54be742d9f5ddb068ad8507becc6a893805ed7a0c36ad52526eab47e5"}}