{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:IFFUHPQEA57INBGO5FUS62XPMW","short_pith_number":"pith:IFFUHPQE","canonical_record":{"source":{"id":"2505.23843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T15:17:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f9431c37fa32c2b93fba225cdb1bf8e9b00a5ef6463339352363fc4785b8944","abstract_canon_sha256":"0ede380acda4c6df52c8fda2d686c06984519425d52bb1eef80bed7cbbb74b08"},"schema_version":"1.0"},"canonical_sha256":"414b43be04077e8684cee9692f6aef6599c69ce961b91c0b45a89be97fa03b3b","source":{"kind":"arxiv","id":"2505.23843","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23843","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23843v1","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23843","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"IFFUHPQEA57I","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"IFFUHPQEA57INBGO","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"IFFUHPQE","created_at":"2026-07-05T11:12:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:IFFUHPQEA57INBGO5FUS62XPMW","target":"record","payload":{"canonical_record":{"source":{"id":"2505.23843","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T15:17:34Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9f9431c37fa32c2b93fba225cdb1bf8e9b00a5ef6463339352363fc4785b8944","abstract_canon_sha256":"0ede380acda4c6df52c8fda2d686c06984519425d52bb1eef80bed7cbbb74b08"},"schema_version":"1.0"},"canonical_sha256":"414b43be04077e8684cee9692f6aef6599c69ce961b91c0b45a89be97fa03b3b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:36.532555Z","signature_b64":"P58uV96zJ9JmSPkiGoqYXZJDsCRQA0O5rUiDfo4BDgnbQTzszSd8pNUD+cvCCJoQQ80Ijv9X23DQlQlbg9DxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"414b43be04077e8684cee9692f6aef6599c69ce961b91c0b45a89be97fa03b3b","last_reissued_at":"2026-07-05T11:12:36.532009Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:36.532009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.23843","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":"2026-07-05T11:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9jynQP57A6kfwulqsq5+m0VXyjknZzQgijcXmHnC+Hux+Cn7yZmmmTS25bjjZCcaXVSC2vXXf0mYrySSz/thAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:24:24.420833Z"},"content_sha256":"863a125f4de019e3ad9e1f187bcec46a01a2e3c8f5f5233b74c2dd8422677012","schema_version":"1.0","event_id":"sha256:863a125f4de019e3ad9e1f187bcec46a01a2e3c8f5f5233b74c2dd8422677012"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:IFFUHPQEA57INBGO5FUS62XPMW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingyi Zheng, Tianyi Hu, Wenhan Dong, Xinlei He, Xinyi Huang, Yuemeng Zhao, Yule Liu, Zhen Sun","submitted_at":"2025-05-28T15:17:34Z","abstract_excerpt":"Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multiple benchmarks and automated evaluation metrics to assess these abilities. However, our study reveals novel insights into the limitations of existing methods, as they often yield misleading results that fail to uncover key issues, such as shortcut-taking behaviors, rigid patterns, and premature task termination. These issues obscure the true reasoning capabilities of LLMs and undermine the reliability of evaluations."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23843","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/2505.23843/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":"2026-07-05T11:12:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuDInc8x/2IzeekkVJTDzYsgdhHDY3cx09WBu6SifvReTGRY+8VJNhay6WBbu0mSjvINpF9PQF89olUJ0sR5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T22:24:24.421187Z"},"content_sha256":"2029086f9f14778ecafb33debc6fb8ca637ea5002ac52492c22950e4a8a183e1","schema_version":"1.0","event_id":"sha256:2029086f9f14778ecafb33debc6fb8ca637ea5002ac52492c22950e4a8a183e1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFFUHPQEA57INBGO5FUS62XPMW/bundle.json","state_url":"https://pith.science/pith/IFFUHPQEA57INBGO5FUS62XPMW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFFUHPQEA57INBGO5FUS62XPMW/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":"2026-08-14T22:24:24Z","links":{"resolver":"https://pith.science/pith/IFFUHPQEA57INBGO5FUS62XPMW","bundle":"https://pith.science/pith/IFFUHPQEA57INBGO5FUS62XPMW/bundle.json","state":"https://pith.science/pith/IFFUHPQEA57INBGO5FUS62XPMW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFFUHPQEA57INBGO5FUS62XPMW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IFFUHPQEA57INBGO5FUS62XPMW","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":"0ede380acda4c6df52c8fda2d686c06984519425d52bb1eef80bed7cbbb74b08","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T15:17:34Z","title_canon_sha256":"9f9431c37fa32c2b93fba225cdb1bf8e9b00a5ef6463339352363fc4785b8944"},"schema_version":"1.0","source":{"id":"2505.23843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.23843","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"arxiv_version","alias_value":"2505.23843v1","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23843","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_12","alias_value":"IFFUHPQEA57I","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_16","alias_value":"IFFUHPQEA57INBGO","created_at":"2026-07-05T11:12:36Z"},{"alias_kind":"pith_short_8","alias_value":"IFFUHPQE","created_at":"2026-07-05T11:12:36Z"}],"graph_snapshots":[{"event_id":"sha256:2029086f9f14778ecafb33debc6fb8ca637ea5002ac52492c22950e4a8a183e1","target":"graph","created_at":"2026-07-05T11:12:36Z","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/2505.23843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-round incomplete information tasks are crucial for evaluating the lateral thinking capabilities of large language models (LLMs). Currently, research primarily relies on multiple benchmarks and automated evaluation metrics to assess these abilities. However, our study reveals novel insights into the limitations of existing methods, as they often yield misleading results that fail to uncover key issues, such as shortcut-taking behaviors, rigid patterns, and premature task termination. These issues obscure the true reasoning capabilities of LLMs and undermine the reliability of evaluations.","authors_text":"Jingyi Zheng, Tianyi Hu, Wenhan Dong, Xinlei He, Xinyi Huang, Yuemeng Zhao, Yule Liu, Zhen Sun","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T15:17:34Z","title":"Evaluation Hallucination in Multi-Round Incomplete Information Lateral-Driven Reasoning Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23843","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":"sha256:863a125f4de019e3ad9e1f187bcec46a01a2e3c8f5f5233b74c2dd8422677012","target":"record","created_at":"2026-07-05T11:12:36Z","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":"0ede380acda4c6df52c8fda2d686c06984519425d52bb1eef80bed7cbbb74b08","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-28T15:17:34Z","title_canon_sha256":"9f9431c37fa32c2b93fba225cdb1bf8e9b00a5ef6463339352363fc4785b8944"},"schema_version":"1.0","source":{"id":"2505.23843","kind":"arxiv","version":1}},"canonical_sha256":"414b43be04077e8684cee9692f6aef6599c69ce961b91c0b45a89be97fa03b3b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"414b43be04077e8684cee9692f6aef6599c69ce961b91c0b45a89be97fa03b3b","first_computed_at":"2026-07-05T11:12:36.532009Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:36.532009Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P58uV96zJ9JmSPkiGoqYXZJDsCRQA0O5rUiDfo4BDgnbQTzszSd8pNUD+cvCCJoQQ80Ijv9X23DQlQlbg9DxDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:36.532555Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.23843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:863a125f4de019e3ad9e1f187bcec46a01a2e3c8f5f5233b74c2dd8422677012","sha256:2029086f9f14778ecafb33debc6fb8ca637ea5002ac52492c22950e4a8a183e1"],"state_sha256":"e420e261e4f898f0d56386367643fce6eb9afe867725b27ba495fd86e5508d1f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QCu+cP0WuSYlecNuH6rgsAgkCcoBSgQfATbwZ9mlov6N/U4Pd74ZIQFEasamK3xXSz1u/dNXVIAYjCCTG0AUDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T22:24:24.424371Z","bundle_sha256":"08f574b7eb378090b8906a5297c62de7c2fa661ae5b19fdcb7a273b5579a9a05"}}