{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LS2XCLJ4F55UILEXCRSPCUPA65","short_pith_number":"pith:LS2XCLJ4","schema_version":"1.0","canonical_sha256":"5cb5712d3c2f7b442c971464f151e0f7598f06240408f684b62e68d95370f945","source":{"kind":"arxiv","id":"2603.23118","version":2},"attestation_state":"computed","paper":{"title":"SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jinzhe Tu, Junxiao Yang, Minlie Huang, Ruilei Guo, Shiyao Cui, Zihan Guo","submitted_at":"2026-03-24T12:15:31Z","abstract_excerpt":"Recent works have shown that multimodal large language models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden content is imperceptible to models but obvious to humans. This deficiency highlights a perceptual misalignment between current MLLMs and humans, and also introduces potential safety concerns. To systematically investigate this failure, we introduce IlluChar, a comprehensive and challenging illusion dataset, and uncover a key underlying mechanism for the models' failure: high-frequency attention bias, where the models are easily distracted by high-freq"},"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":"2603.23118","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-03-24T12:15:31Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"8d072ccb48edb2811186efe1a19f7fe1a3c9256c6241003bf2969cc105862d0f","abstract_canon_sha256":"9192d02f8fdcc1c4e7376a21c5a2522de51073ffde2a9eb76bfddb8b12cdfbd4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5cb5712d3c2f7b442c971464f151e0f7598f06240408f684b62e68d95370f945","last_reissued_at":"2026-07-30T01:19:43.572160Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:43.572160Z"},"graph_snapshot":{"paper":{"title":"SMSP: A Plug-and-Play Strategy of Multi-Scale Perception for MLLMs to Perceive Visual Illusions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Jinzhe Tu, Junxiao Yang, Minlie Huang, Ruilei Guo, Shiyao Cui, Zihan Guo","submitted_at":"2026-03-24T12:15:31Z","abstract_excerpt":"Recent works have shown that multimodal large language models (MLLMs) are highly vulnerable to hidden-pattern visual illusions, where the hidden content is imperceptible to models but obvious to humans. This deficiency highlights a perceptual misalignment between current MLLMs and humans, and also introduces potential safety concerns. To systematically investigate this failure, we introduce IlluChar, a comprehensive and challenging illusion dataset, and uncover a key underlying mechanism for the models' failure: high-frequency attention bias, where the models are easily distracted by high-freq"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.23118","kind":"arxiv","version":2},"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/2603.23118/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":"2603.23118","created_at":"2026-07-30T01:19:43.577320+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.23118v2","created_at":"2026-07-30T01:19:43.577320+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.23118","created_at":"2026-07-30T01:19:43.577320+00:00"},{"alias_kind":"pith_short_12","alias_value":"LS2XCLJ4F55U","created_at":"2026-07-30T01:19:43.577320+00:00"},{"alias_kind":"pith_short_16","alias_value":"LS2XCLJ4F55UILEX","created_at":"2026-07-30T01:19:43.577320+00:00"},{"alias_kind":"pith_short_8","alias_value":"LS2XCLJ4","created_at":"2026-07-30T01:19:43.577320+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/LS2XCLJ4F55UILEXCRSPCUPA65","json":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65.json","graph_json":"https://pith.science/api/pith-number/LS2XCLJ4F55UILEXCRSPCUPA65/graph.json","events_json":"https://pith.science/api/pith-number/LS2XCLJ4F55UILEXCRSPCUPA65/events.json","paper":"https://pith.science/paper/LS2XCLJ4"},"agent_actions":{"view_html":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65","download_json":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65.json","view_paper":"https://pith.science/paper/LS2XCLJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.23118&json=true","fetch_graph":"https://pith.science/api/pith-number/LS2XCLJ4F55UILEXCRSPCUPA65/graph.json","fetch_events":"https://pith.science/api/pith-number/LS2XCLJ4F55UILEXCRSPCUPA65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65/action/storage_attestation","attest_author":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65/action/author_attestation","sign_citation":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65/action/citation_signature","submit_replication":"https://pith.science/pith/LS2XCLJ4F55UILEXCRSPCUPA65/action/replication_record"}},"created_at":"2026-07-30T01:19:43.577320+00:00","updated_at":"2026-07-30T01:19:43.577320+00:00"}