{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UFHVY6YEHJAQJRK2MFOF6GPXWO","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":"fc9f5bf64217a0e1169cb4998c9beec818f8ba283debdeee843f79e5069c2498","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:14:09Z","title_canon_sha256":"1f44a80003bbf96049932f00c9509ce26b9d7ca04c25924e327bfe3311744df8"},"schema_version":"1.0","source":{"id":"2402.03686","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.03686","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"arxiv_version","alias_value":"2402.03686v3","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03686","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_12","alias_value":"UFHVY6YEHJAQ","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_16","alias_value":"UFHVY6YEHJAQJRK2","created_at":"2026-07-05T08:24:01Z"},{"alias_kind":"pith_short_8","alias_value":"UFHVY6YE","created_at":"2026-07-05T08:24:01Z"}],"graph_snapshots":[{"event_id":"sha256:8d456017b9113d0d14181ffd9e37870be92544b4c4849592ce5c850ff7395f25","target":"graph","created_at":"2026-07-05T08:24:01Z","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/2402.03686/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Making inferences in text comprehension to understand the meaning is essential in language processing. This work studies the entailment verification (EV) problem of multi-sentence premises that requires a system to make multiple inferences implicitly. Studying EV for such complex premises is important because modern NLP problems, such as detecting inconsistent model-generated rationales, require complex multi-hop reasoning. However, current textual inference datasets mostly contain short premises that only partially focus on these challenges. To address this, we compile an EV benchmark that in","authors_text":"Jiacheng Liu, Soumya Sanyal, Tianyi Xiao, Wenya Wang, Xiang Ren","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:14:09Z","title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03686","kind":"arxiv","version":3},"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":"sha256:056f780783ea331efbf113b1032424ba5de00e2b034108caa0be477e80870687","target":"record","created_at":"2026-07-05T08:24:01Z","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":"fc9f5bf64217a0e1169cb4998c9beec818f8ba283debdeee843f79e5069c2498","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:14:09Z","title_canon_sha256":"1f44a80003bbf96049932f00c9509ce26b9d7ca04c25924e327bfe3311744df8"},"schema_version":"1.0","source":{"id":"2402.03686","kind":"arxiv","version":3}},"canonical_sha256":"a14f5c7b043a4104c55a615c5f19f7b3aa563ffe4c9bd3d50833acaabdc65c52","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a14f5c7b043a4104c55a615c5f19f7b3aa563ffe4c9bd3d50833acaabdc65c52","first_computed_at":"2026-07-05T08:24:01.047777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:24:01.047777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"51Gsuc9D6xJedeEA/7+vtx2x6IHTXEQNr0Im8+9VDw5E78EMNDcbaCQMc+Ds54PE3Hiv1asr854j/otInE/2AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:24:01.048214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.03686","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:056f780783ea331efbf113b1032424ba5de00e2b034108caa0be477e80870687","sha256:8d456017b9113d0d14181ffd9e37870be92544b4c4849592ce5c850ff7395f25"],"state_sha256":"03ce3ce1d001c4d3fafb8871f706eeee1e79436d505a8fca710f0839254eaad1"}