{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:LJT2M35PQVGJH65ZWFHXFUWHDZ","short_pith_number":"pith:LJT2M35P","schema_version":"1.0","canonical_sha256":"5a67a66faf854c93fbb9b14f72d2c71e668cd2565c8cdd8ab79406499cf42663","source":{"kind":"arxiv","id":"2307.05113","version":3},"attestation_state":"computed","paper":{"title":"Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoning Ye, Hongwei Feng, Jiangjie Chen, Lin Zhang, Xiaoxuan Zhu, Yan Gao, Yanghua Xiao, Yao Hu, Zheyu Ye, Zhouhong Gu, Zihan Li","submitted_at":"2023-07-11T08:45:46Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2307.05113","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-07-11T08:45:46Z","cross_cats_sorted":[],"title_canon_sha256":"6765cc8f0cec03c2ffc814f2bdfa7ec7d739957c1916ab0cfdd22824c1d36da4","abstract_canon_sha256":"9dc6c7fb4622ce7294bc611ee6d81cc96b0a8ecbb72443de44cb6e27aedbc2ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:21.361144Z","signature_b64":"OGYsy2iEGIzi0O7sR0lzZUyPiyA/dx9lHw+kP9v70NWs8F/bzfLmaE3pEtV5pj2iOGFiLbXCHhgJ7mc92fBQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a67a66faf854c93fbb9b14f72d2c71e668cd2565c8cdd8ab79406499cf42663","last_reissued_at":"2026-07-05T07:58:21.360586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:21.360586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Piecing Together Clues: A Benchmark for Evaluating the Detective Skills of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haoning Ye, Hongwei Feng, Jiangjie Chen, Lin Zhang, Xiaoxuan Zhu, Yan Gao, Yanghua Xiao, Yao Hu, Zheyu Ye, Zhouhong Gu, Zihan Li","submitted_at":"2023-07-11T08:45:46Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.05113","kind":"arxiv","version":3},"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/2307.05113/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2307.05113","created_at":"2026-07-05T07:58:21.360651+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.05113v3","created_at":"2026-07-05T07:58:21.360651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.05113","created_at":"2026-07-05T07:58:21.360651+00:00"},{"alias_kind":"pith_short_12","alias_value":"LJT2M35PQVGJ","created_at":"2026-07-05T07:58:21.360651+00:00"},{"alias_kind":"pith_short_16","alias_value":"LJT2M35PQVGJH65Z","created_at":"2026-07-05T07:58:21.360651+00:00"},{"alias_kind":"pith_short_8","alias_value":"LJT2M35P","created_at":"2026-07-05T07:58:21.360651+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ","json":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ.json","graph_json":"https://pith.science/api/pith-number/LJT2M35PQVGJH65ZWFHXFUWHDZ/graph.json","events_json":"https://pith.science/api/pith-number/LJT2M35PQVGJH65ZWFHXFUWHDZ/events.json","paper":"https://pith.science/paper/LJT2M35P"},"agent_actions":{"view_html":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ","download_json":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ.json","view_paper":"https://pith.science/paper/LJT2M35P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.05113&json=true","fetch_graph":"https://pith.science/api/pith-number/LJT2M35PQVGJH65ZWFHXFUWHDZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LJT2M35PQVGJH65ZWFHXFUWHDZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ/action/storage_attestation","attest_author":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ/action/author_attestation","sign_citation":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ/action/citation_signature","submit_replication":"https://pith.science/pith/LJT2M35PQVGJH65ZWFHXFUWHDZ/action/replication_record"}},"created_at":"2026-07-05T07:58:21.360651+00:00","updated_at":"2026-07-05T07:58:21.360651+00:00"}