{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MQPDIBZ2GJL3RGC7ZC7KL2JLPR","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":"f7050442a7f95144751640bcfe4034c22d4a9fb33a74b404cdeaa8e9428092eb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-26T07:29:12Z","title_canon_sha256":"de9eeff82d02743a814a97fc114bbf009af9ef4d09143cb5b22712db108b007f"},"schema_version":"1.0","source":{"id":"2504.18827","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18827","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18827v3","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18827","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"MQPDIBZ2GJL3","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"MQPDIBZ2GJL3RGC7","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"MQPDIBZ2","created_at":"2026-07-05T12:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:5fd80f1126ae02b66e47f54582720b02b9d64d372835ce8bbcbfabcc0a515f17","target":"graph","created_at":"2026-07-05T12:06:09Z","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/2504.18827/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chaiyong Ragkhitwetsagul, Chommakorn Sontesadisai, Teeradaj Racharak, Thanwadee Sunetnanta","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-26T07:29:12Z","title":"Test It Before You Trust It: Applying Software Testing for Trustworthy In-context Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18827","kind":"arxiv","version":3},"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":"sha256:5da8e32e8abbe4cd03e659aabcc39583f3a3057ef1c444c234fe6c5af1e045e8","target":"record","created_at":"2026-07-05T12:06:09Z","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":"f7050442a7f95144751640bcfe4034c22d4a9fb33a74b404cdeaa8e9428092eb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-04-26T07:29:12Z","title_canon_sha256":"de9eeff82d02743a814a97fc114bbf009af9ef4d09143cb5b22712db108b007f"},"schema_version":"1.0","source":{"id":"2504.18827","kind":"arxiv","version":3}},"canonical_sha256":"641e34073a3257b8985fc8bea5e92b7c51a1d8f10c5dacef24fd96cae98515c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"641e34073a3257b8985fc8bea5e92b7c51a1d8f10c5dacef24fd96cae98515c7","first_computed_at":"2026-07-05T12:06:09.922372Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:09.922372Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qdl5TRqnHqVwuJvkKqxW4dLjalJnQpUupjLP5REWyoq2AMP4JxpzDODOuODY+9X/OommKkErJTamNauh6PQnCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:09.922917Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18827","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5da8e32e8abbe4cd03e659aabcc39583f3a3057ef1c444c234fe6c5af1e045e8","sha256:5fd80f1126ae02b66e47f54582720b02b9d64d372835ce8bbcbfabcc0a515f17"],"state_sha256":"89126b0d873b43fdf5b40e60b3eb31231eefd40b2808125f87c4526935972720"}