{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JQH43LAQ4GDACJEJTVD6XGAMOQ","short_pith_number":"pith:JQH43LAQ","schema_version":"1.0","canonical_sha256":"4c0fcdac10e1860124899d47eb980c74114c2c1d994fd31541f7cdb6b8c86e25","source":{"kind":"arxiv","id":"2504.18376","version":2},"attestation_state":"computed","paper":{"title":"Pushing the boundary on Natural Language Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alejandro Mart\\'in, David Camacho, Javier Huertas-Tato, Pablo Miralles-Gonz\\'alez","submitted_at":"2025-04-25T14:20:57Z","abstract_excerpt":"Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, and information retrieval. Despite its importance, current NLI systems heavily rely on supervised learning with datasets that often contain annotation artifacts and biases, limiting generalization and real-world applicability. In this work, we apply a reinforcement learning-based approach using Group Relative Policy Optimization (GRPO) for Chain-of-Thought (CoT) learning in NLI, eliminating the need for labeled rationales and enabling this type of trainin"},"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":"2504.18376","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:20:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d634eeed1666cbc51e7cd282018f60e4d90dbfe4e973e4d8dff4d5d99fd85751","abstract_canon_sha256":"3e4cc4f3017bb2ae12a7c6a73a606185256cad2981f6e4856caea33cf1b3e759"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:09.727747Z","signature_b64":"kbJjK4lXA3ivrZ+vEafDzmhIsTn1P+HVA0vZmmmwOpajVlFa26QHYqfoodvI6VrvzYXf9HJBBK1DkMdcDBpuCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c0fcdac10e1860124899d47eb980c74114c2c1d994fd31541f7cdb6b8c86e25","last_reissued_at":"2026-07-05T10:59:09.727294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:09.727294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pushing the boundary on Natural Language Inference","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alejandro Mart\\'in, David Camacho, Javier Huertas-Tato, Pablo Miralles-Gonz\\'alez","submitted_at":"2025-04-25T14:20:57Z","abstract_excerpt":"Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, and information retrieval. Despite its importance, current NLI systems heavily rely on supervised learning with datasets that often contain annotation artifacts and biases, limiting generalization and real-world applicability. In this work, we apply a reinforcement learning-based approach using Group Relative Policy Optimization (GRPO) for Chain-of-Thought (CoT) learning in NLI, eliminating the need for labeled rationales and enabling this type of trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18376","kind":"arxiv","version":2},"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/2504.18376/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":"2504.18376","created_at":"2026-07-05T10:59:09.727361+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18376v2","created_at":"2026-07-05T10:59:09.727361+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18376","created_at":"2026-07-05T10:59:09.727361+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQH43LAQ4GDA","created_at":"2026-07-05T10:59:09.727361+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQH43LAQ4GDACJEJ","created_at":"2026-07-05T10:59:09.727361+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQH43LAQ","created_at":"2026-07-05T10:59:09.727361+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2510.24295","citing_title":"MERGE: Minimal Expression-Replacement GEneralization Test for Natural Language Inference","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ","json":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ.json","graph_json":"https://pith.science/api/pith-number/JQH43LAQ4GDACJEJTVD6XGAMOQ/graph.json","events_json":"https://pith.science/api/pith-number/JQH43LAQ4GDACJEJTVD6XGAMOQ/events.json","paper":"https://pith.science/paper/JQH43LAQ"},"agent_actions":{"view_html":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ","download_json":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ.json","view_paper":"https://pith.science/paper/JQH43LAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18376&json=true","fetch_graph":"https://pith.science/api/pith-number/JQH43LAQ4GDACJEJTVD6XGAMOQ/graph.json","fetch_events":"https://pith.science/api/pith-number/JQH43LAQ4GDACJEJTVD6XGAMOQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ/action/storage_attestation","attest_author":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ/action/author_attestation","sign_citation":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ/action/citation_signature","submit_replication":"https://pith.science/pith/JQH43LAQ4GDACJEJTVD6XGAMOQ/action/replication_record"}},"created_at":"2026-07-05T10:59:09.727361+00:00","updated_at":"2026-07-05T10:59:09.727361+00:00"}