{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HXX4ILSECS32BB47LAS3FCVSBA","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":"dd082b9f4dbd8a42ea2fcfccfaa9c38d29c46829f048f5875239ceb8a6e41266","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T19:48:50Z","title_canon_sha256":"146381a61e654c8084c61a0a038c753e5e2cb381703cddbbfe3cd3abc83c231a"},"schema_version":"1.0","source":{"id":"2210.10860","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.10860","created_at":"2026-07-05T05:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2210.10860v1","created_at":"2026-07-05T05:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.10860","created_at":"2026-07-05T05:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"HXX4ILSECS32","created_at":"2026-07-05T05:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"HXX4ILSECS32BB47","created_at":"2026-07-05T05:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"HXX4ILSE","created_at":"2026-07-05T05:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:919908bef4e7d908a5bd3ea21ccc2646f7e389cd3c4948be731521b6b27f2b45","target":"graph","created_at":"2026-07-05T05:08:32Z","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/2210.10860/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The use of language-model-based question-answering systems to aid humans in completing difficult tasks is limited, in part, by the unreliability of the text these systems generate. Using hard multiple-choice reading comprehension questions as a testbed, we assess whether presenting humans with arguments for two competing answer options, where one is correct and the other is incorrect, allows human judges to perform more accurately, even when one of the arguments is unreliable and deceptive. If this is helpful, we may be able to increase our justified trust in language-model-based systems by as","authors_text":"Alicia Parrish, Amanpreet Singh Saimbhi, Harsh Trivedi, Jason Phang, Nikita Nangia, Samuel R. Bowman, Vishakh Padmakumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T19:48:50Z","title":"Two-Turn Debate Doesn't Help Humans Answer Hard Reading Comprehension Questions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.10860","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":"sha256:4dab3dbb4ac8d4f95b48e819b44454a662822cd069cc7ae9f2b4bb5ce96b153a","target":"record","created_at":"2026-07-05T05:08:32Z","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":"dd082b9f4dbd8a42ea2fcfccfaa9c38d29c46829f048f5875239ceb8a6e41266","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-10-19T19:48:50Z","title_canon_sha256":"146381a61e654c8084c61a0a038c753e5e2cb381703cddbbfe3cd3abc83c231a"},"schema_version":"1.0","source":{"id":"2210.10860","kind":"arxiv","version":1}},"canonical_sha256":"3defc42e4414b7a0879f5825b28ab2081a3d665fa23724b4d6465f6e7b0e3a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3defc42e4414b7a0879f5825b28ab2081a3d665fa23724b4d6465f6e7b0e3a6f","first_computed_at":"2026-07-05T05:08:32.710347Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:08:32.710347Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QlZl+18qDPHBsbDad9d+zo5cUNhX189tBW+BweANVmLzGscx5f8M4m6UM4uULrNVkVyS7zj36QizDgow8lYxAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:08:32.710894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.10860","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4dab3dbb4ac8d4f95b48e819b44454a662822cd069cc7ae9f2b4bb5ce96b153a","sha256:919908bef4e7d908a5bd3ea21ccc2646f7e389cd3c4948be731521b6b27f2b45"],"state_sha256":"b5b7f9081ed7cb977bfee8cc89ebcf52f3019bfdf99b981840f64775a43090bc"}