{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MH37KOEWQ3CKUMTTLXZ2VSJYAW","short_pith_number":"pith:MH37KOEW","schema_version":"1.0","canonical_sha256":"61f7f5389686c4aa32735df3aac93805b95eacb6d6f9a598f289ea0d5618dfed","source":{"kind":"arxiv","id":"2403.03788","version":1},"attestation_state":"computed","paper":{"title":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Nan Duan, Yaobo Liang, Yiduo Guo, Zekai Zhang","submitted_at":"2024-03-06T15:33:32Z","abstract_excerpt":"The growing dependence on Large Language Models (LLMs) for finishing user instructions necessitates a comprehensive understanding of their robustness to complex task completion in real-world situations. To address this critical need, we propose the PowerPoint Task Completion Robustness benchmark (PPTC-R) to measure LLMs' robustness to the user PPT task instruction and software version. Specifically, we construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. To assess the robustness of Language Models to software versions, we vary"},"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":"2403.03788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-06T15:33:32Z","cross_cats_sorted":[],"title_canon_sha256":"96d9ddfd618163e25087a85f7791848e06e16b619a6cd70eb89205ba29437570","abstract_canon_sha256":"42855c5e6a6eb95d3bac3ca76d010eb41d49d615788f648354d6e9fa9f393538"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:53:01.571903Z","signature_b64":"hejE2HZkx8583ff/nmLcyKrMyjC+n6b3LG4y+UCs6a+g4qN3pdT3bXlSvFzDe8JzWvKNBBJdbnSGtN6blfGLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61f7f5389686c4aa32735df3aac93805b95eacb6d6f9a598f289ea0d5618dfed","last_reissued_at":"2026-07-05T07:53:01.571552Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:53:01.571552Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PPTC-R benchmark: Towards Evaluating the Robustness of Large Language Models for PowerPoint Task Completion","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Nan Duan, Yaobo Liang, Yiduo Guo, Zekai Zhang","submitted_at":"2024-03-06T15:33:32Z","abstract_excerpt":"The growing dependence on Large Language Models (LLMs) for finishing user instructions necessitates a comprehensive understanding of their robustness to complex task completion in real-world situations. To address this critical need, we propose the PowerPoint Task Completion Robustness benchmark (PPTC-R) to measure LLMs' robustness to the user PPT task instruction and software version. Specifically, we construct adversarial user instructions by attacking user instructions at sentence, semantic, and multi-language levels. To assess the robustness of Language Models to software versions, we vary"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.03788","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/2403.03788/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":"2403.03788","created_at":"2026-07-05T07:53:01.571613+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03788v1","created_at":"2026-07-05T07:53:01.571613+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03788","created_at":"2026-07-05T07:53:01.571613+00:00"},{"alias_kind":"pith_short_12","alias_value":"MH37KOEWQ3CK","created_at":"2026-07-05T07:53:01.571613+00:00"},{"alias_kind":"pith_short_16","alias_value":"MH37KOEWQ3CKUMTT","created_at":"2026-07-05T07:53:01.571613+00:00"},{"alias_kind":"pith_short_8","alias_value":"MH37KOEW","created_at":"2026-07-05T07:53:01.571613+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/MH37KOEWQ3CKUMTTLXZ2VSJYAW","json":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW.json","graph_json":"https://pith.science/api/pith-number/MH37KOEWQ3CKUMTTLXZ2VSJYAW/graph.json","events_json":"https://pith.science/api/pith-number/MH37KOEWQ3CKUMTTLXZ2VSJYAW/events.json","paper":"https://pith.science/paper/MH37KOEW"},"agent_actions":{"view_html":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW","download_json":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW.json","view_paper":"https://pith.science/paper/MH37KOEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03788&json=true","fetch_graph":"https://pith.science/api/pith-number/MH37KOEWQ3CKUMTTLXZ2VSJYAW/graph.json","fetch_events":"https://pith.science/api/pith-number/MH37KOEWQ3CKUMTTLXZ2VSJYAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW/action/storage_attestation","attest_author":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW/action/author_attestation","sign_citation":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW/action/citation_signature","submit_replication":"https://pith.science/pith/MH37KOEWQ3CKUMTTLXZ2VSJYAW/action/replication_record"}},"created_at":"2026-07-05T07:53:01.571613+00:00","updated_at":"2026-07-05T07:53:01.571613+00:00"}