{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:763KA24VTIQG2ZMQEVDTVPWWS5","short_pith_number":"pith:763KA24V","schema_version":"1.0","canonical_sha256":"ffb6a06b959a206d659025473abed6976a1b47e2b7c80734c4b2b7468b29a0dd","source":{"kind":"arxiv","id":"2412.00083","version":3},"attestation_state":"computed","paper":{"title":"Visual Error Patterns in Multi-Modal AI: A Statistical Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.AP"],"primary_cat":"cs.LG","authors_text":"Ching-Yi Wang","submitted_at":"2024-11-27T01:20:08Z","abstract_excerpt":"Multi-modal large language models (MLLMs), such as GPT-4o, excel at integrating text and visual data but face systematic challenges when interpreting ambiguous or incomplete visual stimuli. This study leverages statistical modeling to analyze the factors driving these errors, using a dataset of geometric stimuli characterized by features like 3D, rotation, and missing face/side. We applied parametric methods, non-parametric methods, and ensemble techniques to predict classification errors, with the non-linear gradient boosting model achieving the highest performance (AUC=0.85) during cross-val"},"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":"2412.00083","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-27T01:20:08Z","cross_cats_sorted":["cs.AI","cs.CV","stat.AP"],"title_canon_sha256":"ae3eae7182e216d38a046e5cd2c01a3c0c30b198638bc4d17566523bfa692f78","abstract_canon_sha256":"23978386f38fa0755b936c59876c862a1c098e97a5d9c202ef9fac8419f52595"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:16.781942Z","signature_b64":"sChur2VdWIZOfvz2OTQooX7ztFZ2EYo+Cz1XEMBCDmcACY35vC4wNTzPolsKtGFeXrYRL5eeiSt4J7ro0pEcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffb6a06b959a206d659025473abed6976a1b47e2b7c80734c4b2b7468b29a0dd","last_reissued_at":"2026-07-05T09:45:16.781556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:16.781556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Error Patterns in Multi-Modal AI: A Statistical Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.AP"],"primary_cat":"cs.LG","authors_text":"Ching-Yi Wang","submitted_at":"2024-11-27T01:20:08Z","abstract_excerpt":"Multi-modal large language models (MLLMs), such as GPT-4o, excel at integrating text and visual data but face systematic challenges when interpreting ambiguous or incomplete visual stimuli. This study leverages statistical modeling to analyze the factors driving these errors, using a dataset of geometric stimuli characterized by features like 3D, rotation, and missing face/side. We applied parametric methods, non-parametric methods, and ensemble techniques to predict classification errors, with the non-linear gradient boosting model achieving the highest performance (AUC=0.85) during cross-val"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00083","kind":"arxiv","version":3},"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/2412.00083/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":"2412.00083","created_at":"2026-07-05T09:45:16.781607+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00083v3","created_at":"2026-07-05T09:45:16.781607+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00083","created_at":"2026-07-05T09:45:16.781607+00:00"},{"alias_kind":"pith_short_12","alias_value":"763KA24VTIQG","created_at":"2026-07-05T09:45:16.781607+00:00"},{"alias_kind":"pith_short_16","alias_value":"763KA24VTIQG2ZMQ","created_at":"2026-07-05T09:45:16.781607+00:00"},{"alias_kind":"pith_short_8","alias_value":"763KA24V","created_at":"2026-07-05T09:45:16.781607+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/763KA24VTIQG2ZMQEVDTVPWWS5","json":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5.json","graph_json":"https://pith.science/api/pith-number/763KA24VTIQG2ZMQEVDTVPWWS5/graph.json","events_json":"https://pith.science/api/pith-number/763KA24VTIQG2ZMQEVDTVPWWS5/events.json","paper":"https://pith.science/paper/763KA24V"},"agent_actions":{"view_html":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5","download_json":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5.json","view_paper":"https://pith.science/paper/763KA24V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00083&json=true","fetch_graph":"https://pith.science/api/pith-number/763KA24VTIQG2ZMQEVDTVPWWS5/graph.json","fetch_events":"https://pith.science/api/pith-number/763KA24VTIQG2ZMQEVDTVPWWS5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5/action/storage_attestation","attest_author":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5/action/author_attestation","sign_citation":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5/action/citation_signature","submit_replication":"https://pith.science/pith/763KA24VTIQG2ZMQEVDTVPWWS5/action/replication_record"}},"created_at":"2026-07-05T09:45:16.781607+00:00","updated_at":"2026-07-05T09:45:16.781607+00:00"}