{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:D5RLPSWW6JOSQMSN3XMWJYE5B2","short_pith_number":"pith:D5RLPSWW","schema_version":"1.0","canonical_sha256":"1f62b7cad6f25d28324dddd964e09d0e8c8c05e7067314a197d111f04bf7c076","source":{"kind":"arxiv","id":"2506.06133","version":1},"attestation_state":"computed","paper":{"title":"Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Dumitrescu, Diana Inkpen, Raj Singh, Tara Azin","submitted_at":"2025-06-06T14:42:20Z","abstract_excerpt":"Natural Language Inference (NLI) is the task of determining whether a sentence pair represents entailment, contradiction, or a neutral relationship. While NLI models perform well on many inference tasks, their ability to handle fine-grained pragmatic inferences, particularly presupposition in conditionals, remains underexplored. In this study, we introduce CONFER, a novel dataset designed to evaluate how NLI models process inference in conditional sentences. We assess the performance of four NLI models, including two pre-trained models, to examine their generalization to conditional reasoning."},"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":"2506.06133","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T14:42:20Z","cross_cats_sorted":[],"title_canon_sha256":"31862e30ab8ed8256e63c1935039031adc44e690559c038855c17544af50bd61","abstract_canon_sha256":"32e54fb4724f896b50bd26fb76aadcc5e6de6393f7b6f198a169f03f41d689b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:26.264613Z","signature_b64":"3Pra317bYOcn4aEndQeNWsVnPos1ZM7osLKGnDd5lQ6SQFLWimPNgNaJ/C+d/p1OJ1SX9ljVG4B3COy3dUz5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f62b7cad6f25d28324dddd964e09d0e8c8c05e7067314a197d111f04bf7c076","last_reissued_at":"2026-07-05T11:17:26.264083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:26.264083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let's CONFER: A Dataset for Evaluating Natural Language Inference Models on CONditional InFERence and Presupposition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Daniel Dumitrescu, Diana Inkpen, Raj Singh, Tara Azin","submitted_at":"2025-06-06T14:42:20Z","abstract_excerpt":"Natural Language Inference (NLI) is the task of determining whether a sentence pair represents entailment, contradiction, or a neutral relationship. While NLI models perform well on many inference tasks, their ability to handle fine-grained pragmatic inferences, particularly presupposition in conditionals, remains underexplored. In this study, we introduce CONFER, a novel dataset designed to evaluate how NLI models process inference in conditional sentences. We assess the performance of four NLI models, including two pre-trained models, to examine their generalization to conditional reasoning."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06133","kind":"arxiv","version":1},"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/2506.06133/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":"2506.06133","created_at":"2026-07-05T11:17:26.264149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06133v1","created_at":"2026-07-05T11:17:26.264149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06133","created_at":"2026-07-05T11:17:26.264149+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5RLPSWW6JOS","created_at":"2026-07-05T11:17:26.264149+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5RLPSWW6JOSQMSN","created_at":"2026-07-05T11:17:26.264149+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5RLPSWW","created_at":"2026-07-05T11:17:26.264149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.18352","citing_title":"Presupposition and Reasoning in Conditionals: A Theory-Based Study of Humans and LLMs","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2","json":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2.json","graph_json":"https://pith.science/api/pith-number/D5RLPSWW6JOSQMSN3XMWJYE5B2/graph.json","events_json":"https://pith.science/api/pith-number/D5RLPSWW6JOSQMSN3XMWJYE5B2/events.json","paper":"https://pith.science/paper/D5RLPSWW"},"agent_actions":{"view_html":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2","download_json":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2.json","view_paper":"https://pith.science/paper/D5RLPSWW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06133&json=true","fetch_graph":"https://pith.science/api/pith-number/D5RLPSWW6JOSQMSN3XMWJYE5B2/graph.json","fetch_events":"https://pith.science/api/pith-number/D5RLPSWW6JOSQMSN3XMWJYE5B2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2/action/storage_attestation","attest_author":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2/action/author_attestation","sign_citation":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2/action/citation_signature","submit_replication":"https://pith.science/pith/D5RLPSWW6JOSQMSN3XMWJYE5B2/action/replication_record"}},"created_at":"2026-07-05T11:17:26.264149+00:00","updated_at":"2026-07-05T11:17:26.264149+00:00"}