{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KUHNC2YRT7Y3FWQ5N5UQOZUMSD","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":"14e07d6aa9e4f7fc4664da2846d6a1588702f00a0fec7823831f4a999fc17a7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-12T04:40:02Z","title_canon_sha256":"64ed53a547baadbeaf892d9551c57de809f0002f8ad9a07b1c6c132d91e0a82c"},"schema_version":"1.0","source":{"id":"2607.10562","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.10562","created_at":"2026-07-14T01:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.10562v1","created_at":"2026-07-14T01:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.10562","created_at":"2026-07-14T01:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"KUHNC2YRT7Y3","created_at":"2026-07-14T01:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"KUHNC2YRT7Y3FWQ5","created_at":"2026-07-14T01:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"KUHNC2YR","created_at":"2026-07-14T01:21:21Z"}],"graph_snapshots":[{"event_id":"sha256:141bfc8cd3a7aadd1821ee800fc7b1104e913a0c9ce6e9a8c698210d79fcb040","target":"graph","created_at":"2026-07-14T01:21:21Z","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/2607.10562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"JuneHyoung Kwon, JungMin Yun, YoungBin Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-12T04:40:02Z","title":"CRiT-QA: Evaluating Multi-hop Reasoning with Counterfactual Chains and Distractor Traps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.10562","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":"sha256:14dd654caf2561dab7c50334397e12d150ddc328b6f08d959e153dbb688d8a11","target":"record","created_at":"2026-07-14T01:21:21Z","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":"14e07d6aa9e4f7fc4664da2846d6a1588702f00a0fec7823831f4a999fc17a7c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-12T04:40:02Z","title_canon_sha256":"64ed53a547baadbeaf892d9551c57de809f0002f8ad9a07b1c6c132d91e0a82c"},"schema_version":"1.0","source":{"id":"2607.10562","kind":"arxiv","version":1}},"canonical_sha256":"550ed16b119ff1b2da1d6f6907668c90dea7688b882be1dcfa93b89087298872","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"550ed16b119ff1b2da1d6f6907668c90dea7688b882be1dcfa93b89087298872","first_computed_at":"2026-07-14T01:21:21.464105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T01:21:21.464105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BU8ZQy2RhgkuFh5IRVHJznOottAbc0eEu9PFDZvq/luwKAW2tDYq1CZ/XUF7vSW/0St4/SzDbDTKM+scc6GJBg==","signature_status":"signed_v1","signed_at":"2026-07-14T01:21:21.464919Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.10562","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:14dd654caf2561dab7c50334397e12d150ddc328b6f08d959e153dbb688d8a11","sha256:141bfc8cd3a7aadd1821ee800fc7b1104e913a0c9ce6e9a8c698210d79fcb040"],"state_sha256":"9c544c5b658ec44027dc9e1e82bea40c14b1f1c70fbd50b95497b587cde17f6f"}