{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AQFIRS6X5JR6QLVJTX57U25F7J","short_pith_number":"pith:AQFIRS6X","schema_version":"1.0","canonical_sha256":"040a88cbd7ea63e82ea99dfbfa6ba5fa67b7af7b9d05fbe6600fe03cb1963013","source":{"kind":"arxiv","id":"2412.15557","version":4},"attestation_state":"computed","paper":{"title":"MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Aaron Guoxiang Guo, Aldeida Aleti, Chakkrit Tantithamthavorn, Neelofar Neelofar, Tsong Yueh Chen, Yuanyuan Qi","submitted_at":"2024-12-20T04:31:03Z","abstract_excerpt":"With the widespread application of LLM-based dialogue systems in daily life, quality assurance has become more important than ever. Recent research has successfully introduced methods to identify unexpected behaviour in single-turn testing scenarios. However, multi-turn interaction is the common real-world usage of dialogue systems, yet testing methods for such interactions remain underexplored. This is largely due to the oracle problem in multi-turn testing, which continues to pose a significant challenge for dialogue system developers and researchers. In this paper, we propose MORTAR, a meta"},"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":"2412.15557","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-12-20T04:31:03Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"32b1cfb71191991be7a2759b17aca27fd72018dc3a7677412473f617310fb4db","abstract_canon_sha256":"9ab711a08a7f240816416bf301a87a8741ef0c7530ec6479a7fe6bd239e98b6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:09.423985Z","signature_b64":"9052WQrMqHlIjN20LPhnyNZjwk8B5ssMse3QQS204DomUlji4mJI4N5DeidHbVmRmfJtOfKQndVyRP9L4YMeDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"040a88cbd7ea63e82ea99dfbfa6ba5fa67b7af7b9d05fbe6600fe03cb1963013","last_reissued_at":"2026-06-19T16:11:09.423559Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:09.423559Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MORTAR: Multi-turn Metamorphic Testing for LLM-based Dialogue Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SE","authors_text":"Aaron Guoxiang Guo, Aldeida Aleti, Chakkrit Tantithamthavorn, Neelofar Neelofar, Tsong Yueh Chen, Yuanyuan Qi","submitted_at":"2024-12-20T04:31:03Z","abstract_excerpt":"With the widespread application of LLM-based dialogue systems in daily life, quality assurance has become more important than ever. Recent research has successfully introduced methods to identify unexpected behaviour in single-turn testing scenarios. However, multi-turn interaction is the common real-world usage of dialogue systems, yet testing methods for such interactions remain underexplored. This is largely due to the oracle problem in multi-turn testing, which continues to pose a significant challenge for dialogue system developers and researchers. In this paper, we propose MORTAR, a meta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.15557","kind":"arxiv","version":4},"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/2412.15557/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":"2412.15557","created_at":"2026-06-19T16:11:09.423613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.15557v4","created_at":"2026-06-19T16:11:09.423613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.15557","created_at":"2026-06-19T16:11:09.423613+00:00"},{"alias_kind":"pith_short_12","alias_value":"AQFIRS6X5JR6","created_at":"2026-06-19T16:11:09.423613+00:00"},{"alias_kind":"pith_short_16","alias_value":"AQFIRS6X5JR6QLVJ","created_at":"2026-06-19T16:11:09.423613+00:00"},{"alias_kind":"pith_short_8","alias_value":"AQFIRS6X","created_at":"2026-06-19T16:11:09.423613+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13898","citing_title":"Bidirectional Empowerment of Metamorphic Testing and Large Language Models: A Systematic Survey","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J","json":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J.json","graph_json":"https://pith.science/api/pith-number/AQFIRS6X5JR6QLVJTX57U25F7J/graph.json","events_json":"https://pith.science/api/pith-number/AQFIRS6X5JR6QLVJTX57U25F7J/events.json","paper":"https://pith.science/paper/AQFIRS6X"},"agent_actions":{"view_html":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J","download_json":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J.json","view_paper":"https://pith.science/paper/AQFIRS6X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.15557&json=true","fetch_graph":"https://pith.science/api/pith-number/AQFIRS6X5JR6QLVJTX57U25F7J/graph.json","fetch_events":"https://pith.science/api/pith-number/AQFIRS6X5JR6QLVJTX57U25F7J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J/action/storage_attestation","attest_author":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J/action/author_attestation","sign_citation":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J/action/citation_signature","submit_replication":"https://pith.science/pith/AQFIRS6X5JR6QLVJTX57U25F7J/action/replication_record"}},"created_at":"2026-06-19T16:11:09.423613+00:00","updated_at":"2026-06-19T16:11:09.423613+00:00"}