{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UV7MQPAYYQEXZPQL7DSGUC2QXV","short_pith_number":"pith:UV7MQPAY","canonical_record":{"source":{"id":"2601.12263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-18T04:58:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b1e03d0e564dd2e20f20e147b5ded9315b53a76cd10fd329d7cfc86a5ea6b7d8","abstract_canon_sha256":"1beacebb9f50f08a5856fe6718a504e34522a1b077fd75b01d0c6ca3bb564568"},"schema_version":"1.0"},"canonical_sha256":"a57ec83c18c4097cbe0bf8e46a0b50bd63e0dd98832ba5e3162b1ba014768176","source":{"kind":"arxiv","id":"2601.12263","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12263","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12263v2","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12263","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"UV7MQPAYYQEX","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"pith_short_16","alias_value":"UV7MQPAYYQEXZPQL","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"pith_short_8","alias_value":"UV7MQPAY","created_at":"2026-06-09T02:07:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UV7MQPAYYQEXZPQL7DSGUC2QXV","target":"record","payload":{"canonical_record":{"source":{"id":"2601.12263","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-18T04:58:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b1e03d0e564dd2e20f20e147b5ded9315b53a76cd10fd329d7cfc86a5ea6b7d8","abstract_canon_sha256":"1beacebb9f50f08a5856fe6718a504e34522a1b077fd75b01d0c6ca3bb564568"},"schema_version":"1.0"},"canonical_sha256":"a57ec83c18c4097cbe0bf8e46a0b50bd63e0dd98832ba5e3162b1ba014768176","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:07:17.571758Z","signature_b64":"qs4f1eMNA+cbtT90uDxjC27eQ93bhbXMzo1RRUf3cPxLLq5E/hhL893b4qiXl2+yEexSApOmDORQm3g0Y39GAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a57ec83c18c4097cbe0bf8e46a0b50bd63e0dd98832ba5e3162b1ba014768176","last_reissued_at":"2026-06-09T02:07:17.570745Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:07:17.570745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2601.12263","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:07:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aKWnh/dlYF7Kb5yIjaRrpmys0ddmqakd6p8l+muS+XqC5QQfr3vVH4DhDRvyA1uNdLu3u5ISPtnsTmFQza6OCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:58:11.142679Z"},"content_sha256":"076cf0fe36f64d7085fd606813e300ce853f8b5e6d240259dfab7ff7b07ca13d","schema_version":"1.0","event_id":"sha256:076cf0fe36f64d7085fd606813e300ce853f8b5e6d240259dfab7ff7b07ca13d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UV7MQPAYYQEXZPQL7DSGUC2QXV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenxiao Yu, Haoyan Xu, Xiyang Hu, Yixuan Du, Yue Zhao, Ziyi Wang","submitted_at":"2026-01-18T04:58:28Z","abstract_excerpt":"Vision-Language Models (VLMs) integrate visual and textual knowledge into unified representations that increasingly underpin modern retrieval and recommendation systems. However, it remains unclear how reliably these models utilize their cross-modal knowledge when ranking multimodal items, and whether their knowledge grounding can be subverted. In this paper, we expose a fundamental vulnerability in how VLMs apply multimodal knowledge for product ranking: through Multimodal Generative Engine Optimization (MGEO), we show that an adversary can manipulate a VLM's ranking decisions by jointly craf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12263","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/2601.12263/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-09T02:07:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0evPnNjMCJstx14XrEH121L8ssY4PhKCmvoeEUF/3RZEJ+0TIeTqjE4pDNCF+R88k3YOZN+lmSXEk6jX40eRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T03:58:11.143073Z"},"content_sha256":"289a662c24b8f06f70fcaa860c704912db8182ab71c5bc4ff092de13c908a985","schema_version":"1.0","event_id":"sha256:289a662c24b8f06f70fcaa860c704912db8182ab71c5bc4ff092de13c908a985"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV/bundle.json","state_url":"https://pith.science/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T03:58:11Z","links":{"resolver":"https://pith.science/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV","bundle":"https://pith.science/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV/bundle.json","state":"https://pith.science/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UV7MQPAYYQEXZPQL7DSGUC2QXV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UV7MQPAYYQEXZPQL7DSGUC2QXV","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1beacebb9f50f08a5856fe6718a504e34522a1b077fd75b01d0c6ca3bb564568","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-18T04:58:28Z","title_canon_sha256":"b1e03d0e564dd2e20f20e147b5ded9315b53a76cd10fd329d7cfc86a5ea6b7d8"},"schema_version":"1.0","source":{"id":"2601.12263","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.12263","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"arxiv_version","alias_value":"2601.12263v2","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12263","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"pith_short_12","alias_value":"UV7MQPAYYQEX","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"pith_short_16","alias_value":"UV7MQPAYYQEXZPQL","created_at":"2026-06-09T02:07:17Z"},{"alias_kind":"pith_short_8","alias_value":"UV7MQPAY","created_at":"2026-06-09T02:07:17Z"}],"graph_snapshots":[{"event_id":"sha256:289a662c24b8f06f70fcaa860c704912db8182ab71c5bc4ff092de13c908a985","target":"graph","created_at":"2026-06-09T02:07:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.12263/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) integrate visual and textual knowledge into unified representations that increasingly underpin modern retrieval and recommendation systems. However, it remains unclear how reliably these models utilize their cross-modal knowledge when ranking multimodal items, and whether their knowledge grounding can be subverted. In this paper, we expose a fundamental vulnerability in how VLMs apply multimodal knowledge for product ranking: through Multimodal Generative Engine Optimization (MGEO), we show that an adversary can manipulate a VLM's ranking decisions by jointly craf","authors_text":"Chenxiao Yu, Haoyan Xu, Xiyang Hu, Yixuan Du, Yue Zhao, Ziyi Wang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-18T04:58:28Z","title":"Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12263","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:076cf0fe36f64d7085fd606813e300ce853f8b5e6d240259dfab7ff7b07ca13d","target":"record","created_at":"2026-06-09T02:07:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1beacebb9f50f08a5856fe6718a504e34522a1b077fd75b01d0c6ca3bb564568","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-01-18T04:58:28Z","title_canon_sha256":"b1e03d0e564dd2e20f20e147b5ded9315b53a76cd10fd329d7cfc86a5ea6b7d8"},"schema_version":"1.0","source":{"id":"2601.12263","kind":"arxiv","version":2}},"canonical_sha256":"a57ec83c18c4097cbe0bf8e46a0b50bd63e0dd98832ba5e3162b1ba014768176","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a57ec83c18c4097cbe0bf8e46a0b50bd63e0dd98832ba5e3162b1ba014768176","first_computed_at":"2026-06-09T02:07:17.570745Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:07:17.570745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qs4f1eMNA+cbtT90uDxjC27eQ93bhbXMzo1RRUf3cPxLLq5E/hhL893b4qiXl2+yEexSApOmDORQm3g0Y39GAA==","signature_status":"signed_v1","signed_at":"2026-06-09T02:07:17.571758Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.12263","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:076cf0fe36f64d7085fd606813e300ce853f8b5e6d240259dfab7ff7b07ca13d","sha256:289a662c24b8f06f70fcaa860c704912db8182ab71c5bc4ff092de13c908a985"],"state_sha256":"9ed29cf8f9c7d9976d730454e46b50673e7e4b7ae54a44e34d88064b42bd056a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sJW9i8SVqmXIm5tSEZFSXK1S11Sh6K3/N8P4IlxzvaSj6cpZB4OwdAdJ0D4q4UYckqMurGr15Zpg8nT2jOOTAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T03:58:11.145550Z","bundle_sha256":"9f821a48adce0716fbefa98cc4cb0e9fd5abeddebc107e5a2f18fdddf9d55009"}}