{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:R356WUSXSC4QNEILV2IUDKTEYS","short_pith_number":"pith:R356WUSX","schema_version":"1.0","canonical_sha256":"8efbeb525790b906910bae9141aa64c4bd7a563dbcdf1d851bb15f97133cf286","source":{"kind":"arxiv","id":"2412.17032","version":3},"attestation_state":"computed","paper":{"title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jeff Z. Pan, Jiaoyan Chen, Jie He, Nan Hu, Wanqiu Long","submitted_at":"2024-12-22T14:17:12Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks but face significant challenges with complex, knowledge-intensive multi-hop queries, particularly those involving new or long-tail knowledge. Existing benchmarks often fail to fully address these challenges. To bridge this gap, we introduce MINTQA (Multi-hop Question Answering on New and Tail Knowledge), a comprehensive benchmark to evaluate LLMs' capabilities in multi-hop reasoning across four critical dimensions: question handling strategy, sub-question generation, retrieval-augmented generation"},"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":"2412.17032","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T14:17:12Z","cross_cats_sorted":[],"title_canon_sha256":"55870cee40caf9bffd87ea84491123ab070b62bf6bea7bfffaf381463645f557","abstract_canon_sha256":"7eb393f02bdda499b49ecfaeb7ab8e3cc2f18e2d7adb1496d35865e3665d2b5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:33.656013Z","signature_b64":"uG1dYn+6B3SAOXjzCgi4Sczyinz+SyqQrv8L4WFnXUl81EhXIpIiXHTO2RWsKJiFNau5X+BOfKrisTMKx4rZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8efbeb525790b906910bae9141aa64c4bd7a563dbcdf1d851bb15f97133cf286","last_reissued_at":"2026-07-05T11:57:33.655481Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:33.655481Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MINTQA: A Multi-Hop Question Answering Benchmark for Evaluating LLMs on New and Tail Knowledge","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jeff Z. Pan, Jiaoyan Chen, Jie He, Nan Hu, Wanqiu Long","submitted_at":"2024-12-22T14:17:12Z","abstract_excerpt":"Large language models (LLMs) have demonstrated impressive capabilities in various reasoning tasks but face significant challenges with complex, knowledge-intensive multi-hop queries, particularly those involving new or long-tail knowledge. Existing benchmarks often fail to fully address these challenges. To bridge this gap, we introduce MINTQA (Multi-hop Question Answering on New and Tail Knowledge), a comprehensive benchmark to evaluate LLMs' capabilities in multi-hop reasoning across four critical dimensions: question handling strategy, sub-question generation, retrieval-augmented generation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17032","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/2412.17032/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":"2412.17032","created_at":"2026-07-05T11:57:33.655540+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17032v3","created_at":"2026-07-05T11:57:33.655540+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17032","created_at":"2026-07-05T11:57:33.655540+00:00"},{"alias_kind":"pith_short_12","alias_value":"R356WUSXSC4Q","created_at":"2026-07-05T11:57:33.655540+00:00"},{"alias_kind":"pith_short_16","alias_value":"R356WUSXSC4QNEIL","created_at":"2026-07-05T11:57:33.655540+00:00"},{"alias_kind":"pith_short_8","alias_value":"R356WUSX","created_at":"2026-07-05T11:57:33.655540+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12087","citing_title":"FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":89,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS","json":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS.json","graph_json":"https://pith.science/api/pith-number/R356WUSXSC4QNEILV2IUDKTEYS/graph.json","events_json":"https://pith.science/api/pith-number/R356WUSXSC4QNEILV2IUDKTEYS/events.json","paper":"https://pith.science/paper/R356WUSX"},"agent_actions":{"view_html":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS","download_json":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS.json","view_paper":"https://pith.science/paper/R356WUSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17032&json=true","fetch_graph":"https://pith.science/api/pith-number/R356WUSXSC4QNEILV2IUDKTEYS/graph.json","fetch_events":"https://pith.science/api/pith-number/R356WUSXSC4QNEILV2IUDKTEYS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS/action/storage_attestation","attest_author":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS/action/author_attestation","sign_citation":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS/action/citation_signature","submit_replication":"https://pith.science/pith/R356WUSXSC4QNEILV2IUDKTEYS/action/replication_record"}},"created_at":"2026-07-05T11:57:33.655540+00:00","updated_at":"2026-07-05T11:57:33.655540+00:00"}