{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MQPDIBZ2GJL3RGC7ZC7KL2JLPR","short_pith_number":"pith:MQPDIBZ2","schema_version":"1.0","canonical_sha256":"641e34073a3257b8985fc8bea5e92b7c51a1d8f10c5dacef24fd96cae98515c7","source":{"kind":"arxiv","id":"2504.18827","version":3},"attestation_state":"computed","paper":{"title":"Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chaiyong Ragkhitwetsagul, Chommakorn Sontesadisai, Teeradaj Racharak, Thanwadee Sunetnanta","submitted_at":"2025-04-26T07:29:12Z","abstract_excerpt":"In-context learning (ICL) has emerged as a powerful capability of large language models (LLMs), enabling them to perform new tasks based on a few provided examples without explicit fine-tuning. Despite their impressive adaptability, these models remain vulnerable to subtle adversarial perturbations and exhibit unpredictable behavior when faced with linguistic variations. Inspired by software testing principles, we introduce a software testing-inspired framework, called MMT4NL, for evaluating the trustworthiness of in-context learning by utilizing adversarial perturbations and software testing "},"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":"2504.18827","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-26T07:29:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"de9eeff82d02743a814a97fc114bbf009af9ef4d09143cb5b22712db108b007f","abstract_canon_sha256":"f7050442a7f95144751640bcfe4034c22d4a9fb33a74b404cdeaa8e9428092eb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:09.922917Z","signature_b64":"qdl5TRqnHqVwuJvkKqxW4dLjalJnQpUupjLP5REWyoq2AMP4JxpzDODOuODY+9X/OommKkErJTamNauh6PQnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"641e34073a3257b8985fc8bea5e92b7c51a1d8f10c5dacef24fd96cae98515c7","last_reissued_at":"2026-07-05T12:06:09.922372Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:09.922372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Chaiyong Ragkhitwetsagul, Chommakorn Sontesadisai, Teeradaj Racharak, Thanwadee Sunetnanta","submitted_at":"2025-04-26T07:29:12Z","abstract_excerpt":"In-context learning (ICL) has emerged as a powerful capability of large language models (LLMs), enabling them to perform new tasks based on a few provided examples without explicit fine-tuning. Despite their impressive adaptability, these models remain vulnerable to subtle adversarial perturbations and exhibit unpredictable behavior when faced with linguistic variations. Inspired by software testing principles, we introduce a software testing-inspired framework, called MMT4NL, for evaluating the trustworthiness of in-context learning by utilizing adversarial perturbations and software testing "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18827","kind":"arxiv","version":3},"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/2504.18827/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":"2504.18827","created_at":"2026-07-05T12:06:09.922438+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18827v3","created_at":"2026-07-05T12:06:09.922438+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18827","created_at":"2026-07-05T12:06:09.922438+00:00"},{"alias_kind":"pith_short_12","alias_value":"MQPDIBZ2GJL3","created_at":"2026-07-05T12:06:09.922438+00:00"},{"alias_kind":"pith_short_16","alias_value":"MQPDIBZ2GJL3RGC7","created_at":"2026-07-05T12:06:09.922438+00:00"},{"alias_kind":"pith_short_8","alias_value":"MQPDIBZ2","created_at":"2026-07-05T12:06:09.922438+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/MQPDIBZ2GJL3RGC7ZC7KL2JLPR","json":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR.json","graph_json":"https://pith.science/api/pith-number/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/graph.json","events_json":"https://pith.science/api/pith-number/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/events.json","paper":"https://pith.science/paper/MQPDIBZ2"},"agent_actions":{"view_html":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR","download_json":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR.json","view_paper":"https://pith.science/paper/MQPDIBZ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18827&json=true","fetch_graph":"https://pith.science/api/pith-number/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/graph.json","fetch_events":"https://pith.science/api/pith-number/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/action/storage_attestation","attest_author":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/action/author_attestation","sign_citation":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/action/citation_signature","submit_replication":"https://pith.science/pith/MQPDIBZ2GJL3RGC7ZC7KL2JLPR/action/replication_record"}},"created_at":"2026-07-05T12:06:09.922438+00:00","updated_at":"2026-07-05T12:06:09.922438+00:00"}