{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:INOIRIM42RPRCJOBZSOIJQC6NR","short_pith_number":"pith:INOIRIM4","schema_version":"1.0","canonical_sha256":"435c88a19cd45f1125c1cc9c84c05e6c758b5ae32302d61289712be8f9a90623","source":{"kind":"arxiv","id":"2606.05181","version":1},"attestation_state":"computed","paper":{"title":"Multi-Granularity Reasoning for Natural Language Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunling Xi, Di Liang","submitted_at":"2026-04-18T16:19:32Z","abstract_excerpt":"Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a premise and a hypothesis. Despite the remarkable success of transformer-based pre-trained models, most existing approaches primarily rely on the final-layer token representations, which are often insufficient for capturing the complex and hierarchical semantic interactions required for effective reasoning. In particular, fine-grained lexical cues, phrasal compositions, and higher-level contextual semantics are typically entangled or diluted in a "},"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":"2606.05181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-18T16:19:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7d613d1a7b9fa5cc9d019712c0b1c5dfd691704b662f266133d264d3d352fae","abstract_canon_sha256":"3cd329798988d7e99daedbdde0d771481feabefc0f3d3f90983caa95b9ad2d78"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T00:13:47.989025Z","signature_b64":"S31b2HZfYxSZrZhYA1PiQXLtYkOP30lt/+v6WOXB4Q68CcrOOfFn0nIdsATavqeF/3eUv0G5tC5P2eSsGdb2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"435c88a19cd45f1125c1cc9c84c05e6c758b5ae32302d61289712be8f9a90623","last_reissued_at":"2026-06-05T00:13:47.988162Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T00:13:47.988162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Granularity Reasoning for Natural Language Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chunling Xi, Di Liang","submitted_at":"2026-04-18T16:19:32Z","abstract_excerpt":"Natural Language Inference (NLI) is a fundamental task in natural language understanding that requires determining the logical relationship between a premise and a hypothesis. Despite the remarkable success of transformer-based pre-trained models, most existing approaches primarily rely on the final-layer token representations, which are often insufficient for capturing the complex and hierarchical semantic interactions required for effective reasoning. In particular, fine-grained lexical cues, phrasal compositions, and higher-level contextual semantics are typically entangled or diluted in a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05181","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/2606.05181/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":"2606.05181","created_at":"2026-06-05T00:13:47.988277+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05181v1","created_at":"2026-06-05T00:13:47.988277+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05181","created_at":"2026-06-05T00:13:47.988277+00:00"},{"alias_kind":"pith_short_12","alias_value":"INOIRIM42RPR","created_at":"2026-06-05T00:13:47.988277+00:00"},{"alias_kind":"pith_short_16","alias_value":"INOIRIM42RPRCJOB","created_at":"2026-06-05T00:13:47.988277+00:00"},{"alias_kind":"pith_short_8","alias_value":"INOIRIM4","created_at":"2026-06-05T00:13:47.988277+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR","json":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR.json","graph_json":"https://pith.science/api/pith-number/INOIRIM42RPRCJOBZSOIJQC6NR/graph.json","events_json":"https://pith.science/api/pith-number/INOIRIM42RPRCJOBZSOIJQC6NR/events.json","paper":"https://pith.science/paper/INOIRIM4"},"agent_actions":{"view_html":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR","download_json":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR.json","view_paper":"https://pith.science/paper/INOIRIM4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05181&json=true","fetch_graph":"https://pith.science/api/pith-number/INOIRIM42RPRCJOBZSOIJQC6NR/graph.json","fetch_events":"https://pith.science/api/pith-number/INOIRIM42RPRCJOBZSOIJQC6NR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR/action/storage_attestation","attest_author":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR/action/author_attestation","sign_citation":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR/action/citation_signature","submit_replication":"https://pith.science/pith/INOIRIM42RPRCJOBZSOIJQC6NR/action/replication_record"}},"created_at":"2026-06-05T00:13:47.988277+00:00","updated_at":"2026-06-05T00:13:47.988277+00:00"}