{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:QZGFNDMC5KRA6MP6PDLH67Q3YV","short_pith_number":"pith:QZGFNDMC","canonical_record":{"source":{"id":"2507.05565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-08T01:11:27Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"5f4143ded74055591fd53ec8cb8dc69ae4a86695c124b53c4f15f958ce7eb562","abstract_canon_sha256":"3c37f4be29bf32be76f26765136200a2c00d3f72a67e62b9adb7908589c59031"},"schema_version":"1.0"},"canonical_sha256":"864c568d82eaa20f31fe78d67f7e1bc575dcf268fc370bd3e77429cc79f9e167","source":{"kind":"arxiv","id":"2507.05565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05565","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05565v1","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05565","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"QZGFNDMC5KRA","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"pith_short_16","alias_value":"QZGFNDMC5KRA6MP6","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"pith_short_8","alias_value":"QZGFNDMC","created_at":"2026-07-05T11:33:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:QZGFNDMC5KRA6MP6PDLH67Q3YV","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05565","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-08T01:11:27Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"5f4143ded74055591fd53ec8cb8dc69ae4a86695c124b53c4f15f958ce7eb562","abstract_canon_sha256":"3c37f4be29bf32be76f26765136200a2c00d3f72a67e62b9adb7908589c59031"},"schema_version":"1.0"},"canonical_sha256":"864c568d82eaa20f31fe78d67f7e1bc575dcf268fc370bd3e77429cc79f9e167","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:32.557293Z","signature_b64":"UsZEulIy81j5/upUP4/VTiLlk78MBInzWmkjXT95yLXNAGT1EsJ1eK0LmnIKcLWi4L7lPq0gRgYhHwvHQo9QAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"864c568d82eaa20f31fe78d67f7e1bc575dcf268fc370bd3e77429cc79f9e167","last_reissued_at":"2026-07-05T11:33:32.556918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:32.556918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05565","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jziHzoo1ayb0w7vPrG+blYXx/D0gE8NegybHc2fOLco00/QQeYIDdv9uv0GfiHsZsJeNZSLn0cxUUrQu/lwQAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:54:17.020355Z"},"content_sha256":"90ea62b480635cf279a47586e05937d3f97599401bcbea9fea3000182fce4e39","schema_version":"1.0","event_id":"sha256:90ea62b480635cf279a47586e05937d3f97599401bcbea9fea3000182fce4e39"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:QZGFNDMC5KRA6MP6PDLH67Q3YV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Search-based Selection of Metamorphic Relations for Optimized Robustness Testing of Large Language Models","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.SE","authors_text":"M. Ali Babar, Sangwon Hyun, Shaukat Ali","submitted_at":"2025-07-08T01:11:27Z","abstract_excerpt":"Assessing the trustworthiness of Large Language Models (LLMs), such as robustness, has garnered significant attention. Recently, metamorphic testing that defines Metamorphic Relations (MRs) has been widely applied to evaluate the robustness of LLM executions. However, the MR-based robustness testing still requires a scalable number of MRs, thereby necessitating the optimization of selecting MRs. Most extant LLM testing studies are limited to automatically generating test cases (i.e., MRs) to enhance failure detection. Additionally, most studies only considered a limited test space of single pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05565","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/2507.05565/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gZlMt3X5TM5xWXpBEbZTs6TmYTc18V3uE/QtFcZ7osnamYltHi381117YnUTQONGQ4iDh627x7JzxpSbAfqABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:54:17.021081Z"},"content_sha256":"bc12c625cc9dccea8e8c8e700cd2d90d4098ffb12e68028c2b8768ee8ba1813c","schema_version":"1.0","event_id":"sha256:bc12c625cc9dccea8e8c8e700cd2d90d4098ffb12e68028c2b8768ee8ba1813c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV/bundle.json","state_url":"https://pith.science/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T06:54:17Z","links":{"resolver":"https://pith.science/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV","bundle":"https://pith.science/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV/bundle.json","state":"https://pith.science/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZGFNDMC5KRA6MP6PDLH67Q3YV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QZGFNDMC5KRA6MP6PDLH67Q3YV","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":"3c37f4be29bf32be76f26765136200a2c00d3f72a67e62b9adb7908589c59031","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-08T01:11:27Z","title_canon_sha256":"5f4143ded74055591fd53ec8cb8dc69ae4a86695c124b53c4f15f958ce7eb562"},"schema_version":"1.0","source":{"id":"2507.05565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05565","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05565v1","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05565","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"QZGFNDMC5KRA","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"pith_short_16","alias_value":"QZGFNDMC5KRA6MP6","created_at":"2026-07-05T11:33:32Z"},{"alias_kind":"pith_short_8","alias_value":"QZGFNDMC","created_at":"2026-07-05T11:33:32Z"}],"graph_snapshots":[{"event_id":"sha256:bc12c625cc9dccea8e8c8e700cd2d90d4098ffb12e68028c2b8768ee8ba1813c","target":"graph","created_at":"2026-07-05T11:33:32Z","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/2507.05565/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Assessing the trustworthiness of Large Language Models (LLMs), such as robustness, has garnered significant attention. Recently, metamorphic testing that defines Metamorphic Relations (MRs) has been widely applied to evaluate the robustness of LLM executions. However, the MR-based robustness testing still requires a scalable number of MRs, thereby necessitating the optimization of selecting MRs. Most extant LLM testing studies are limited to automatically generating test cases (i.e., MRs) to enhance failure detection. Additionally, most studies only considered a limited test space of single pe","authors_text":"M. Ali Babar, Sangwon Hyun, Shaukat Ali","cross_cats":["cs.AI","cs.NE"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-08T01:11:27Z","title":"Search-based Selection of Metamorphic Relations for Optimized Robustness Testing of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05565","kind":"arxiv","version":1},"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":"sha256:90ea62b480635cf279a47586e05937d3f97599401bcbea9fea3000182fce4e39","target":"record","created_at":"2026-07-05T11:33:32Z","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":"3c37f4be29bf32be76f26765136200a2c00d3f72a67e62b9adb7908589c59031","cross_cats_sorted":["cs.AI","cs.NE"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2025-07-08T01:11:27Z","title_canon_sha256":"5f4143ded74055591fd53ec8cb8dc69ae4a86695c124b53c4f15f958ce7eb562"},"schema_version":"1.0","source":{"id":"2507.05565","kind":"arxiv","version":1}},"canonical_sha256":"864c568d82eaa20f31fe78d67f7e1bc575dcf268fc370bd3e77429cc79f9e167","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"864c568d82eaa20f31fe78d67f7e1bc575dcf268fc370bd3e77429cc79f9e167","first_computed_at":"2026-07-05T11:33:32.556918Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:32.556918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UsZEulIy81j5/upUP4/VTiLlk78MBInzWmkjXT95yLXNAGT1EsJ1eK0LmnIKcLWi4L7lPq0gRgYhHwvHQo9QAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:32.557293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90ea62b480635cf279a47586e05937d3f97599401bcbea9fea3000182fce4e39","sha256:bc12c625cc9dccea8e8c8e700cd2d90d4098ffb12e68028c2b8768ee8ba1813c"],"state_sha256":"b7ff62487251ce12318ff0cc666a9913459840ed075a5ecbd4a428994364bd33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJMySkXvNWWDdNdsLEDEPJdPzsWfe+STyLNT01IZaXgB+RuiB2fO9i36FobX7El8sW33PKgIVwajwEDAjeziDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:54:17.024542Z","bundle_sha256":"0a49f6e865bd1ac11ba3bdda66bc9f71b5f791060ffb8470885b4004d7aeadc4"}}