{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UFHVY6YEHJAQJRK2MFOF6GPXWO","short_pith_number":"pith:UFHVY6YE","schema_version":"1.0","canonical_sha256":"a14f5c7b043a4104c55a615c5f19f7b3aa563ffe4c9bd3d50833acaabdc65c52","source":{"kind":"arxiv","id":"2402.03686","version":3},"attestation_state":"computed","paper":{"title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiacheng Liu, Soumya Sanyal, Tianyi Xiao, Wenya Wang, Xiang Ren","submitted_at":"2024-02-06T04:14:09Z","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"},"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":"2402.03686","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-06T04:14:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1f44a80003bbf96049932f00c9509ce26b9d7ca04c25924e327bfe3311744df8","abstract_canon_sha256":"fc9f5bf64217a0e1169cb4998c9beec818f8ba283debdeee843f79e5069c2498"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:24:01.048214Z","signature_b64":"51Gsuc9D6xJedeEA/7+vtx2x6IHTXEQNr0Im8+9VDw5E78EMNDcbaCQMc+Ds54PE3Hiv1asr854j/otInE/2AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a14f5c7b043a4104c55a615c5f19f7b3aa563ffe4c9bd3d50833acaabdc65c52","last_reissued_at":"2026-07-05T08:24:01.047777Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:24:01.047777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Are Machines Better at Complex Reasoning? Unveiling Human-Machine Inference Gaps in Entailment Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jiacheng Liu, Soumya Sanyal, Tianyi Xiao, Wenya Wang, Xiang Ren","submitted_at":"2024-02-06T04:14:09Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.03686","kind":"arxiv","version":3},"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/2402.03686/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":"2402.03686","created_at":"2026-07-05T08:24:01.047841+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.03686v3","created_at":"2026-07-05T08:24:01.047841+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.03686","created_at":"2026-07-05T08:24:01.047841+00:00"},{"alias_kind":"pith_short_12","alias_value":"UFHVY6YEHJAQ","created_at":"2026-07-05T08:24:01.047841+00:00"},{"alias_kind":"pith_short_16","alias_value":"UFHVY6YEHJAQJRK2","created_at":"2026-07-05T08:24:01.047841+00:00"},{"alias_kind":"pith_short_8","alias_value":"UFHVY6YE","created_at":"2026-07-05T08:24:01.047841+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.13163","citing_title":"Unlocking Historical Clinical Trial Data with ALIGN: A Compositional Large Language Model System for Medical Coding","ref_index":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO","json":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO.json","graph_json":"https://pith.science/api/pith-number/UFHVY6YEHJAQJRK2MFOF6GPXWO/graph.json","events_json":"https://pith.science/api/pith-number/UFHVY6YEHJAQJRK2MFOF6GPXWO/events.json","paper":"https://pith.science/paper/UFHVY6YE"},"agent_actions":{"view_html":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO","download_json":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO.json","view_paper":"https://pith.science/paper/UFHVY6YE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.03686&json=true","fetch_graph":"https://pith.science/api/pith-number/UFHVY6YEHJAQJRK2MFOF6GPXWO/graph.json","fetch_events":"https://pith.science/api/pith-number/UFHVY6YEHJAQJRK2MFOF6GPXWO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO/action/storage_attestation","attest_author":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO/action/author_attestation","sign_citation":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO/action/citation_signature","submit_replication":"https://pith.science/pith/UFHVY6YEHJAQJRK2MFOF6GPXWO/action/replication_record"}},"created_at":"2026-07-05T08:24:01.047841+00:00","updated_at":"2026-07-05T08:24:01.047841+00:00"}