{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QXJ3JJXHCZQUORQZLSS6I55T5D","short_pith_number":"pith:QXJ3JJXH","schema_version":"1.0","canonical_sha256":"85d3b4a6e716614746195ca5e477b3e8c450d46e65a0c0fa5916f6646f44023b","source":{"kind":"arxiv","id":"2412.09263","version":2},"attestation_state":"computed","paper":{"title":"First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anush Mahajan, Ayushi Agarwal, Eishkaran Singh, Sourav Banerjee","submitted_at":"2024-12-12T13:21:09Z","abstract_excerpt":"Natural Language Inference (NLI) tasks require identifying the relationship between sentence pairs, typically classified as entailment, contradiction, or neutrality. While the current state-of-the-art (SOTA) model, Entailment Few-Shot Learning (EFL), achieves a 93.1% accuracy on the Stanford Natural Language Inference (SNLI) dataset, further advancements are constrained by the dataset's limitations. To address this, we propose a novel approach leveraging synthetic data augmentation to enhance dataset diversity and complexity. We present UnitedSynT5, an advanced extension of EFL that leverages "},"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":"2412.09263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-12T13:21:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"067d7bf37c1133c1886f395316e182e5610f64007c6e5c04e65a851f5f7c589c","abstract_canon_sha256":"5f0141d13a8d8eedc83e92febaaf8ac93b0799084bc006563543c88d6ff8763f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:38.857390Z","signature_b64":"6+X/d869S6xhXwRLHK6Zl41/gmU9KthCb/i1FOrAOJlOPIctp5PUOJe7a88VkTyI5Y99B4Q8AJs9IJlRgPUEAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85d3b4a6e716614746195ca5e477b3e8c450d46e65a0c0fa5916f6646f44023b","last_reissued_at":"2026-07-05T09:48:38.856944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:38.856944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"First Train to Generate, then Generate to Train: UnitedSynT5 for Few-Shot NLI","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anush Mahajan, Ayushi Agarwal, Eishkaran Singh, Sourav Banerjee","submitted_at":"2024-12-12T13:21:09Z","abstract_excerpt":"Natural Language Inference (NLI) tasks require identifying the relationship between sentence pairs, typically classified as entailment, contradiction, or neutrality. While the current state-of-the-art (SOTA) model, Entailment Few-Shot Learning (EFL), achieves a 93.1% accuracy on the Stanford Natural Language Inference (SNLI) dataset, further advancements are constrained by the dataset's limitations. To address this, we propose a novel approach leveraging synthetic data augmentation to enhance dataset diversity and complexity. We present UnitedSynT5, an advanced extension of EFL that leverages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09263","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/2412.09263/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":"2412.09263","created_at":"2026-07-05T09:48:38.857000+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.09263v2","created_at":"2026-07-05T09:48:38.857000+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09263","created_at":"2026-07-05T09:48:38.857000+00:00"},{"alias_kind":"pith_short_12","alias_value":"QXJ3JJXHCZQU","created_at":"2026-07-05T09:48:38.857000+00:00"},{"alias_kind":"pith_short_16","alias_value":"QXJ3JJXHCZQUORQZ","created_at":"2026-07-05T09:48:38.857000+00:00"},{"alias_kind":"pith_short_8","alias_value":"QXJ3JJXH","created_at":"2026-07-05T09:48:38.857000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20419","citing_title":"Survey of NLU Benchmarks Diagnosing Linguistic Phenomena: Why not Standardize Diagnostics Benchmarks?","ref_index":26,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D","json":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D.json","graph_json":"https://pith.science/api/pith-number/QXJ3JJXHCZQUORQZLSS6I55T5D/graph.json","events_json":"https://pith.science/api/pith-number/QXJ3JJXHCZQUORQZLSS6I55T5D/events.json","paper":"https://pith.science/paper/QXJ3JJXH"},"agent_actions":{"view_html":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D","download_json":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D.json","view_paper":"https://pith.science/paper/QXJ3JJXH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.09263&json=true","fetch_graph":"https://pith.science/api/pith-number/QXJ3JJXHCZQUORQZLSS6I55T5D/graph.json","fetch_events":"https://pith.science/api/pith-number/QXJ3JJXHCZQUORQZLSS6I55T5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D/action/storage_attestation","attest_author":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D/action/author_attestation","sign_citation":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D/action/citation_signature","submit_replication":"https://pith.science/pith/QXJ3JJXHCZQUORQZLSS6I55T5D/action/replication_record"}},"created_at":"2026-07-05T09:48:38.857000+00:00","updated_at":"2026-07-05T09:48:38.857000+00:00"}