{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JCUMHOG5HOVVV7E6DERDOGJGPU","short_pith_number":"pith:JCUMHOG5","schema_version":"1.0","canonical_sha256":"48a8c3b8dd3bab5afc9e19223719267d2b58531acb34844acdfe2733a8675e49","source":{"kind":"arxiv","id":"2602.15278","version":2},"attestation_state":"computed","paper":{"title":"Visual Persuasion: What Influences Decisions of Vision-Language Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Manuel Cherep, Nikhil Singh, Pattie Maes, Pranav M R","submitted_at":"2026-02-17T00:33:53Z","abstract_excerpt":"The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controlled image-based choice tasks and systematically perturbing their inputs. Our key idea is to treat the agent's decision function as a latent visual utility that can be inferred through revealed preference: choices between syste"},"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":"2602.15278","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-17T00:33:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"059d50a6fd55a4e283629fb878b6f50d58defbf82f6f4d57665ed03fc33d2ec8","abstract_canon_sha256":"e92834b83de259deb12d1cfd81a5b66b76f6adb702a6493ba912358768bbe5d8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:43.538821Z","signature_b64":"Hit22GhvXHTQQETS3Ycgrme/palL4K/eVn42OqfiG9dCfdKBOCkqU+ETW+zH7arlF4aQKCrEtGyf5/W3cvOiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"48a8c3b8dd3bab5afc9e19223719267d2b58531acb34844acdfe2733a8675e49","last_reissued_at":"2026-06-02T01:03:43.538331Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:43.538331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Visual Persuasion: What Influences Decisions of Vision-Language Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Manuel Cherep, Nikhil Singh, Pattie Maes, Pranav M R","submitted_at":"2026-02-17T00:33:53Z","abstract_excerpt":"The web is littered with images, once created for human consumption and now increasingly interpreted by agents using vision-language models (VLMs). These agents make visual decisions at scale, deciding what to click, recommend, or buy. Yet, we know little about the structure of their visual preferences. We introduce a framework for studying this by placing VLMs in controlled image-based choice tasks and systematically perturbing their inputs. Our key idea is to treat the agent's decision function as a latent visual utility that can be inferred through revealed preference: choices between syste"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15278","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/2602.15278/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":"2602.15278","created_at":"2026-06-02T01:03:43.538387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.15278v2","created_at":"2026-06-02T01:03:43.538387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15278","created_at":"2026-06-02T01:03:43.538387+00:00"},{"alias_kind":"pith_short_12","alias_value":"JCUMHOG5HOVV","created_at":"2026-06-02T01:03:43.538387+00:00"},{"alias_kind":"pith_short_16","alias_value":"JCUMHOG5HOVVV7E6","created_at":"2026-06-02T01:03:43.538387+00:00"},{"alias_kind":"pith_short_8","alias_value":"JCUMHOG5","created_at":"2026-06-02T01:03:43.538387+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/JCUMHOG5HOVVV7E6DERDOGJGPU","json":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU.json","graph_json":"https://pith.science/api/pith-number/JCUMHOG5HOVVV7E6DERDOGJGPU/graph.json","events_json":"https://pith.science/api/pith-number/JCUMHOG5HOVVV7E6DERDOGJGPU/events.json","paper":"https://pith.science/paper/JCUMHOG5"},"agent_actions":{"view_html":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU","download_json":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU.json","view_paper":"https://pith.science/paper/JCUMHOG5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.15278&json=true","fetch_graph":"https://pith.science/api/pith-number/JCUMHOG5HOVVV7E6DERDOGJGPU/graph.json","fetch_events":"https://pith.science/api/pith-number/JCUMHOG5HOVVV7E6DERDOGJGPU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU/action/storage_attestation","attest_author":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU/action/author_attestation","sign_citation":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU/action/citation_signature","submit_replication":"https://pith.science/pith/JCUMHOG5HOVVV7E6DERDOGJGPU/action/replication_record"}},"created_at":"2026-06-02T01:03:43.538387+00:00","updated_at":"2026-06-02T01:03:43.538387+00:00"}