{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JQH43LAQ4GDACJEJTVD6XGAMOQ","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":"3e4cc4f3017bb2ae12a7c6a73a606185256cad2981f6e4856caea33cf1b3e759","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:20:57Z","title_canon_sha256":"d634eeed1666cbc51e7cd282018f60e4d90dbfe4e973e4d8dff4d5d99fd85751"},"schema_version":"1.0","source":{"id":"2504.18376","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18376","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18376v2","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18376","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"JQH43LAQ4GDA","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"JQH43LAQ4GDACJEJ","created_at":"2026-07-05T10:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"JQH43LAQ","created_at":"2026-07-05T10:59:09Z"}],"graph_snapshots":[{"event_id":"sha256:18632724a83c192fecd1864dccf6a65c9bb1c4ac038b1a3c302dd40bbf08ce9c","target":"graph","created_at":"2026-07-05T10:59:09Z","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/2504.18376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Alejandro Mart\\'in, David Camacho, Javier Huertas-Tato, Pablo Miralles-Gonz\\'alez","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:20:57Z","title":"Pushing the boundary on Natural Language Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18376","kind":"arxiv","version":2},"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":"sha256:515ad0f2dff6296c035b9e4a45f24a8ff459f9b0c0cdb784faada424b7a891d2","target":"record","created_at":"2026-07-05T10:59:09Z","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":"3e4cc4f3017bb2ae12a7c6a73a606185256cad2981f6e4856caea33cf1b3e759","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T14:20:57Z","title_canon_sha256":"d634eeed1666cbc51e7cd282018f60e4d90dbfe4e973e4d8dff4d5d99fd85751"},"schema_version":"1.0","source":{"id":"2504.18376","kind":"arxiv","version":2}},"canonical_sha256":"4c0fcdac10e1860124899d47eb980c74114c2c1d994fd31541f7cdb6b8c86e25","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c0fcdac10e1860124899d47eb980c74114c2c1d994fd31541f7cdb6b8c86e25","first_computed_at":"2026-07-05T10:59:09.727294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:09.727294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"kbJjK4lXA3ivrZ+vEafDzmhIsTn1P+HVA0vZmmmwOpajVlFa26QHYqfoodvI6VrvzYXf9HJBBK1DkMdcDBpuCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:09.727747Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18376","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:515ad0f2dff6296c035b9e4a45f24a8ff459f9b0c0cdb784faada424b7a891d2","sha256:18632724a83c192fecd1864dccf6a65c9bb1c4ac038b1a3c302dd40bbf08ce9c"],"state_sha256":"b54cad2232e53114525672dc08aa7f96081087969cb7102ca440a4ab719975aa"}