{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KUHNC2YRT7Y3FWQ5N5UQOZUMSD","short_pith_number":"pith:KUHNC2YR","schema_version":"1.0","canonical_sha256":"550ed16b119ff1b2da1d6f6907668c90dea7688b882be1dcfa93b89087298872","source":{"kind":"arxiv","id":"2607.10562","version":1},"attestation_state":"computed","paper":{"title":"CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"JuneHyoung Kwon, JungMin Yun, YoungBin Kim","submitted_at":"2026-07-12T04:40:02Z","abstract_excerpt":"Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge. Although current models achieve strong results on existing multi-hop question answering datasets, such performance often masks two critical vulnerabilities: (1) reliance on internal parametric knowledge rather than adherence to the provided context, and (2) exploitation of dataset shortcuts, such as single-document cues or type-matching, that diminish the need for genuine evidence aggregation across multiple documents. We introduce CRiT-QA (Counterfactual Reasoning with Traps), a dataset e"},"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":"2607.10562","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-12T04:40:02Z","cross_cats_sorted":[],"title_canon_sha256":"64ed53a547baadbeaf892d9551c57de809f0002f8ad9a07b1c6c132d91e0a82c","abstract_canon_sha256":"14e07d6aa9e4f7fc4664da2846d6a1588702f00a0fec7823831f4a999fc17a7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T01:21:21.464919Z","signature_b64":"BU8ZQy2RhgkuFh5IRVHJznOottAbc0eEu9PFDZvq/luwKAW2tDYq1CZ/XUF7vSW/0St4/SzDbDTKM+scc6GJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"550ed16b119ff1b2da1d6f6907668c90dea7688b882be1dcfa93b89087298872","last_reissued_at":"2026-07-14T01:21:21.464105Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T01:21:21.464105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"JuneHyoung Kwon, JungMin Yun, YoungBin Kim","submitted_at":"2026-07-12T04:40:02Z","abstract_excerpt":"Evaluating the multi-hop reasoning capabilities of large language models remains a significant challenge. Although current models achieve strong results on existing multi-hop question answering datasets, such performance often masks two critical vulnerabilities: (1) reliance on internal parametric knowledge rather than adherence to the provided context, and (2) exploitation of dataset shortcuts, such as single-document cues or type-matching, that diminish the need for genuine evidence aggregation across multiple documents. We introduce CRiT-QA (Counterfactual Reasoning with Traps), a dataset e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10562","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/2607.10562/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":"2607.10562","created_at":"2026-07-14T01:21:21.464528+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.10562v1","created_at":"2026-07-14T01:21:21.464528+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10562","created_at":"2026-07-14T01:21:21.464528+00:00"},{"alias_kind":"pith_short_12","alias_value":"KUHNC2YRT7Y3","created_at":"2026-07-14T01:21:21.464528+00:00"},{"alias_kind":"pith_short_16","alias_value":"KUHNC2YRT7Y3FWQ5","created_at":"2026-07-14T01:21:21.464528+00:00"},{"alias_kind":"pith_short_8","alias_value":"KUHNC2YR","created_at":"2026-07-14T01:21:21.464528+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/KUHNC2YRT7Y3FWQ5N5UQOZUMSD","json":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD.json","graph_json":"https://pith.science/api/pith-number/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/graph.json","events_json":"https://pith.science/api/pith-number/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/events.json","paper":"https://pith.science/paper/KUHNC2YR"},"agent_actions":{"view_html":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD","download_json":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD.json","view_paper":"https://pith.science/paper/KUHNC2YR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.10562&json=true","fetch_graph":"https://pith.science/api/pith-number/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/graph.json","fetch_events":"https://pith.science/api/pith-number/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/action/storage_attestation","attest_author":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/action/author_attestation","sign_citation":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/action/citation_signature","submit_replication":"https://pith.science/pith/KUHNC2YRT7Y3FWQ5N5UQOZUMSD/action/replication_record"}},"created_at":"2026-07-14T01:21:21.464528+00:00","updated_at":"2026-07-14T01:21:21.464528+00:00"}