{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MN3AHHEKAD2LYY2XZQPEZ32SML","short_pith_number":"pith:MN3AHHEK","schema_version":"1.0","canonical_sha256":"6376039c8a00f4bc6357cc1e4cef5262df0df028edffdf325c8ece99f333821e","source":{"kind":"arxiv","id":"2506.03035","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Christophe Servan, Pierre Lepagnol, Sahar Ghannay, Sophie Rosset, Thomas Gerald","submitted_at":"2025-06-03T16:18:45Z","abstract_excerpt":"Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the reliability of the considered system. Current State-of-the-Art SLU techniques rely on large amounts of training data; however, only limited annotated examples are available for specific tasks or languages.\n  In the meantime, instruction-tuned large language models (LLMs) have shown exceptional performance on unseen tasks in a few-shot setting when provided with ad"},"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":"2506.03035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-03T16:18:45Z","cross_cats_sorted":["cs.AI","cs.IR"],"title_canon_sha256":"a55d83ff6e2328dd1f4e8e12e412ebb1cbea32c5002301743e0305d3c2c94474","abstract_canon_sha256":"20c51ce4cfb9ba2f34175aa1ffca418a9e81914f6491c11000a6f157662dacf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:13.678890Z","signature_b64":"HaDdVDvk8xuiiGqYOBgEqF1G/Rn+jinNlii0ZcBJvnv6a7ueGtQ7xCfnaarBNpCCc8wI0MkXQspybpa9DLwlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6376039c8a00f4bc6357cc1e4cef5262df0df028edffdf325c8ece99f333821e","last_reissued_at":"2026-07-05T11:15:13.678394Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:13.678394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.IR"],"primary_cat":"cs.CL","authors_text":"Christophe Servan, Pierre Lepagnol, Sahar Ghannay, Sophie Rosset, Thomas Gerald","submitted_at":"2025-06-03T16:18:45Z","abstract_excerpt":"Understanding user queries is fundamental in many applications, such as home assistants, booking systems, or recommendations. Accordingly, it is crucial to develop accurate Spoken Language Understanding (SLU) approaches to ensure the reliability of the considered system. Current State-of-the-Art SLU techniques rely on large amounts of training data; however, only limited annotated examples are available for specific tasks or languages.\n  In the meantime, instruction-tuned large language models (LLMs) have shown exceptional performance on unseen tasks in a few-shot setting when provided with ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.03035","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/2506.03035/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":"2506.03035","created_at":"2026-07-05T11:15:13.678453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.03035v1","created_at":"2026-07-05T11:15:13.678453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.03035","created_at":"2026-07-05T11:15:13.678453+00:00"},{"alias_kind":"pith_short_12","alias_value":"MN3AHHEKAD2L","created_at":"2026-07-05T11:15:13.678453+00:00"},{"alias_kind":"pith_short_16","alias_value":"MN3AHHEKAD2LYY2X","created_at":"2026-07-05T11:15:13.678453+00:00"},{"alias_kind":"pith_short_8","alias_value":"MN3AHHEK","created_at":"2026-07-05T11:15:13.678453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.03035","citing_title":"Leveraging Information Retrieval to Enhance Spoken Language Understanding Prompts in Few-Shot Learning","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML","json":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML.json","graph_json":"https://pith.science/api/pith-number/MN3AHHEKAD2LYY2XZQPEZ32SML/graph.json","events_json":"https://pith.science/api/pith-number/MN3AHHEKAD2LYY2XZQPEZ32SML/events.json","paper":"https://pith.science/paper/MN3AHHEK"},"agent_actions":{"view_html":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML","download_json":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML.json","view_paper":"https://pith.science/paper/MN3AHHEK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.03035&json=true","fetch_graph":"https://pith.science/api/pith-number/MN3AHHEKAD2LYY2XZQPEZ32SML/graph.json","fetch_events":"https://pith.science/api/pith-number/MN3AHHEKAD2LYY2XZQPEZ32SML/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML/action/storage_attestation","attest_author":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML/action/author_attestation","sign_citation":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML/action/citation_signature","submit_replication":"https://pith.science/pith/MN3AHHEKAD2LYY2XZQPEZ32SML/action/replication_record"}},"created_at":"2026-07-05T11:15:13.678453+00:00","updated_at":"2026-07-05T11:15:13.678453+00:00"}