{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KVG2R2BRDODI6SGZOWNY6TX3JD","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":"eb8bd3aa57c15d95fa8bfdfc3b67a3f0982b2c326386d174ef4d794b64173d48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T00:46:32Z","title_canon_sha256":"70a03f5643aaa221c86753504ed18b20eae07e1f2d14a403b0a26f41b98806ac"},"schema_version":"1.0","source":{"id":"2608.07838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.07838","created_at":"2026-08-11T01:18:38Z"},{"alias_kind":"arxiv_version","alias_value":"2608.07838v1","created_at":"2026-08-11T01:18:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.07838","created_at":"2026-08-11T01:18:38Z"},{"alias_kind":"pith_short_12","alias_value":"KVG2R2BRDODI","created_at":"2026-08-11T01:18:38Z"},{"alias_kind":"pith_short_16","alias_value":"KVG2R2BRDODI6SGZ","created_at":"2026-08-11T01:18:38Z"},{"alias_kind":"pith_short_8","alias_value":"KVG2R2BR","created_at":"2026-08-11T01:18:38Z"}],"graph_snapshots":[{"event_id":"sha256:ccf9e609aedf27fcbed640c86632e6c12c966985018ec3f2d3bafb0d47a2f9d1","target":"graph","created_at":"2026-08-11T01:18:38Z","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/2608.07838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have increasingly supported response generation grounded in user-provided knowledge spanning heterogeneous structures. However, existing benchmarks provide limited assessment of whether LLMs can faithfully perform multi-hop reasoning chains across such knowledge contexts while remaining robust to variations in their input order. We introduce TKFQA, a factuality consistency benchmark comprising 10,130 question-answering (QA) pairs grounded in tables, texts, and knowledge graphs (KGs). Each example is constructed from an explicit counterfactual reasoning chain, enabl","authors_text":"Haofen Wang, Lianghua He, Shibo Chu, Tiehua Zhang, Yuze Liu, Zhijun Ding, Zhishu Shen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T00:46:32Z","title":"Counterfactual Benchmarking and Training for Factuality Consistency and Order-Robust Grounded Reasoning in LLMs over Heterogeneous Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.07838","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":"sha256:6bf446c124be762552d0525ec29a3e62b693aec8a8fdfa377666f64e3ef2ce1c","target":"record","created_at":"2026-08-11T01:18:38Z","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":"eb8bd3aa57c15d95fa8bfdfc3b67a3f0982b2c326386d174ef4d794b64173d48","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-08T00:46:32Z","title_canon_sha256":"70a03f5643aaa221c86753504ed18b20eae07e1f2d14a403b0a26f41b98806ac"},"schema_version":"1.0","source":{"id":"2608.07838","kind":"arxiv","version":1}},"canonical_sha256":"554da8e8311b868f48d9759b8f4efb48e5c1912c23c3e717a378e866f2b7e05f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"554da8e8311b868f48d9759b8f4efb48e5c1912c23c3e717a378e866f2b7e05f","first_computed_at":"2026-08-11T01:18:38.955677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-11T01:18:38.955677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ICgiZkX8esGotRsmQYe1dGWVW/JqIU2jNDolp1FwOI3SKwu4cFO7KKnE8uHbxVwqaUc0EhjOzNY7HmvFynlTDA==","signature_status":"signed_v1","signed_at":"2026-08-11T01:18:38.958213Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.07838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6bf446c124be762552d0525ec29a3e62b693aec8a8fdfa377666f64e3ef2ce1c","sha256:ccf9e609aedf27fcbed640c86632e6c12c966985018ec3f2d3bafb0d47a2f9d1"],"state_sha256":"8f973ccb83b6e24618e096fc9b5654ac703f9b891b58ad6ce3df57e0f16f6017"}