{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LJT2M35PQVGJH65ZWFHXFUWHDZ","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":"9dc6c7fb4622ce7294bc611ee6d81cc96b0a8ecbb72443de44cb6e27aedbc2ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T08:45:46Z","title_canon_sha256":"6765cc8f0cec03c2ffc814f2bdfa7ec7d739957c1916ab0cfdd22824c1d36da4"},"schema_version":"1.0","source":{"id":"2307.05113","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.05113","created_at":"2026-07-05T07:58:21Z"},{"alias_kind":"arxiv_version","alias_value":"2307.05113v3","created_at":"2026-07-05T07:58:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05113","created_at":"2026-07-05T07:58:21Z"},{"alias_kind":"pith_short_12","alias_value":"LJT2M35PQVGJ","created_at":"2026-07-05T07:58:21Z"},{"alias_kind":"pith_short_16","alias_value":"LJT2M35PQVGJH65Z","created_at":"2026-07-05T07:58:21Z"},{"alias_kind":"pith_short_8","alias_value":"LJT2M35P","created_at":"2026-07-05T07:58:21Z"}],"graph_snapshots":[{"event_id":"sha256:9fca77fc7ec68f5f479fcf478cf33283ce7910d71273442ca67017e9a133039c","target":"graph","created_at":"2026-07-05T07:58:21Z","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/2307.05113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detectives frequently engage in information detection and reasoning simultaneously when making decisions across various cases, especially when confronted with a vast amount of information. With the rapid development of large language models~(LLMs), evaluating how these models identify key information and reason to solve questions becomes increasingly relevant. We introduces the DetectBench, a reading comprehension dataset designed to assess a model's ability to jointly ability in key information detection and multi-hop reasoning when facing complex and implicit information. The DetectBench com","authors_text":"Haoning Ye, Hongwei Feng, Jiangjie Chen, Lin Zhang, Xiaoxuan Zhu, Yan Gao, Yanghua Xiao, Yao Hu, Zheyu Ye, Zhouhong Gu, Zihan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T08:45:46Z","title":"Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05113","kind":"arxiv","version":3},"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:d324c44074f2c2f8bf9cf5b00b29a06497cfff9f3f3a1cd7705e41ce85ab579c","target":"record","created_at":"2026-07-05T07:58:21Z","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":"9dc6c7fb4622ce7294bc611ee6d81cc96b0a8ecbb72443de44cb6e27aedbc2ba","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T08:45:46Z","title_canon_sha256":"6765cc8f0cec03c2ffc814f2bdfa7ec7d739957c1916ab0cfdd22824c1d36da4"},"schema_version":"1.0","source":{"id":"2307.05113","kind":"arxiv","version":3}},"canonical_sha256":"5a67a66faf854c93fbb9b14f72d2c71e668cd2565c8cdd8ab79406499cf42663","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a67a66faf854c93fbb9b14f72d2c71e668cd2565c8cdd8ab79406499cf42663","first_computed_at":"2026-07-05T07:58:21.360586Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:21.360586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OGYsy2iEGIzi0O7sR0lzZUyPiyA/dx9lHw+kP9v70NWs8F/bzfLmaE3pEtV5pj2iOGFiLbXCHhgJ7mc92fBQBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:21.361144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.05113","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d324c44074f2c2f8bf9cf5b00b29a06497cfff9f3f3a1cd7705e41ce85ab579c","sha256:9fca77fc7ec68f5f479fcf478cf33283ce7910d71273442ca67017e9a133039c"],"state_sha256":"e560be132702bffa42fcea21c861b086a89f03342ac91025b5842c48a848def4"}