{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STLCNAFANCLVZD7C63MJB7C263","short_pith_number":"pith:STLCNAFA","schema_version":"1.0","canonical_sha256":"94d62680a068975c8fe2f6d890fc5af6e2bde2734f491b1064d241532d19112c","source":{"kind":"arxiv","id":"2401.11943","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Large Multimodal Models against Common Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CV","cs.MM"],"primary_cat":"cs.LG","authors_text":"Bo Li, Chao Du, Jiawei Zhang, Min Lin, Tianyu Pang, Yi Ren","submitted_at":"2024-01-22T13:33:53Z","abstract_excerpt":"This technical report aims to fill a deficiency in the assessment of large multimodal models (LMMs) by specifically examining the self-consistency of their outputs when subjected to common corruptions. We investigate the cross-modal interactions between text, image, and speech, encompassing four essential generation tasks: text-to-image, image-to-text, text-to-speech, and speech-to-text. We create a comprehensive benchmark, named MMCBench, that covers more than 100 popular LMMs (totally over 150 model checkpoints). A thorough evaluation under common corruptions is critical for practical deploy"},"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":"2401.11943","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-22T13:33:53Z","cross_cats_sorted":["cs.CL","cs.CR","cs.CV","cs.MM"],"title_canon_sha256":"0d618f1e6dd3e66f1c7be80bdaf77ef8d47a9a455e4fa6ffe76c964b1471f638","abstract_canon_sha256":"d1bd7ed21d80f7b4f757ab06c8da3ddc364224eecee64113cf11550d8ba1ea9a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:12.604253Z","signature_b64":"CB8LdNyAX9oSvwAEOzzsvy39cwvAkQpRRp5Bw3PNChetGFgB2GG0qviPEjGuqFkojrypSt25PD68ILldE81yCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94d62680a068975c8fe2f6d890fc5af6e2bde2734f491b1064d241532d19112c","last_reissued_at":"2026-07-05T07:36:12.603769Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:12.603769Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Large Multimodal Models against Common Corruptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CR","cs.CV","cs.MM"],"primary_cat":"cs.LG","authors_text":"Bo Li, Chao Du, Jiawei Zhang, Min Lin, Tianyu Pang, Yi Ren","submitted_at":"2024-01-22T13:33:53Z","abstract_excerpt":"This technical report aims to fill a deficiency in the assessment of large multimodal models (LMMs) by specifically examining the self-consistency of their outputs when subjected to common corruptions. We investigate the cross-modal interactions between text, image, and speech, encompassing four essential generation tasks: text-to-image, image-to-text, text-to-speech, and speech-to-text. We create a comprehensive benchmark, named MMCBench, that covers more than 100 popular LMMs (totally over 150 model checkpoints). A thorough evaluation under common corruptions is critical for practical deploy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11943","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/2401.11943/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":"2401.11943","created_at":"2026-07-05T07:36:12.603826+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.11943v1","created_at":"2026-07-05T07:36:12.603826+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11943","created_at":"2026-07-05T07:36:12.603826+00:00"},{"alias_kind":"pith_short_12","alias_value":"STLCNAFANCLV","created_at":"2026-07-05T07:36:12.603826+00:00"},{"alias_kind":"pith_short_16","alias_value":"STLCNAFANCLVZD7C","created_at":"2026-07-05T07:36:12.603826+00:00"},{"alias_kind":"pith_short_8","alias_value":"STLCNAFA","created_at":"2026-07-05T07:36:12.603826+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26904","citing_title":"Confidence-Aware Tool Orchestration for Robust Video Understanding","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09269","citing_title":"DeltaRubric: Generative Multimodal Reward Modeling via Joint Planning and Verification","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263","json":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263.json","graph_json":"https://pith.science/api/pith-number/STLCNAFANCLVZD7C63MJB7C263/graph.json","events_json":"https://pith.science/api/pith-number/STLCNAFANCLVZD7C63MJB7C263/events.json","paper":"https://pith.science/paper/STLCNAFA"},"agent_actions":{"view_html":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263","download_json":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263.json","view_paper":"https://pith.science/paper/STLCNAFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.11943&json=true","fetch_graph":"https://pith.science/api/pith-number/STLCNAFANCLVZD7C63MJB7C263/graph.json","fetch_events":"https://pith.science/api/pith-number/STLCNAFANCLVZD7C63MJB7C263/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263/action/storage_attestation","attest_author":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263/action/author_attestation","sign_citation":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263/action/citation_signature","submit_replication":"https://pith.science/pith/STLCNAFANCLVZD7C63MJB7C263/action/replication_record"}},"created_at":"2026-07-05T07:36:12.603826+00:00","updated_at":"2026-07-05T07:36:12.603826+00:00"}