{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:L6UVHNQFDCEPLHKKCXGBWBPWRE","short_pith_number":"pith:L6UVHNQF","canonical_record":{"source":{"id":"2604.23321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T14:15:05Z","cross_cats_sorted":[],"title_canon_sha256":"678ff0458d9da90fb2f680c5e2661b6135e70cdd9e3e7fbe0f4a65a61a516e43","abstract_canon_sha256":"4f743aebd65f4c363e803bfa00b911bb7422b8406f87f1c69069e16f555368ce"},"schema_version":"1.0"},"canonical_sha256":"5fa953b6051888f59d4a15cc1b05f6891b79fdacc898c61c5550c4cd9b67ab40","source":{"kind":"arxiv","id":"2604.23321","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.23321","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2604.23321v2","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23321","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"L6UVHNQFDCEP","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"L6UVHNQFDCEPLHKK","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"L6UVHNQF","created_at":"2026-07-30T01:19:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:L6UVHNQFDCEPLHKKCXGBWBPWRE","target":"record","payload":{"canonical_record":{"source":{"id":"2604.23321","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T14:15:05Z","cross_cats_sorted":[],"title_canon_sha256":"678ff0458d9da90fb2f680c5e2661b6135e70cdd9e3e7fbe0f4a65a61a516e43","abstract_canon_sha256":"4f743aebd65f4c363e803bfa00b911bb7422b8406f87f1c69069e16f555368ce"},"schema_version":"1.0"},"canonical_sha256":"5fa953b6051888f59d4a15cc1b05f6891b79fdacc898c61c5550c4cd9b67ab40","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fa953b6051888f59d4a15cc1b05f6891b79fdacc898c61c5550c4cd9b67ab40","last_reissued_at":"2026-07-30T01:19:51.917729Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:19:51.917729Z"},"source_kind":"arxiv","source_id":"2604.23321","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":"2026-07-30T01:19:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIEvj3I/L5tOk23Exj2km/+Ohx8RggmdyP7DL8F3yjH5Ax58DeJ6G4DQVC8TEGDrO1Teuwsp9X/ylarJP7gDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:10:52.327086Z"},"content_sha256":"96cf3aee6c9789a6255c72cce81ed3d22a8c20e91c69aa8411cba268311db721","schema_version":"1.0","event_id":"sha256:96cf3aee6c9789a6255c72cce81ed3d22a8c20e91c69aa8411cba268311db721"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:L6UVHNQFDCEPLHKKCXGBWBPWRE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Multimodal embedding models cannot reliably enforce instructions to retrieve a target modality.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Haohang Huang, Kai Zou, Mingyi Su, Ping Nie, Rui Meng, Tomas Pfister, Wei Zhang, Wenhu Chen, Xiaoyu Shen, Xuan Lu, Xuan Zhang, Ziyan Jiang","submitted_at":"2026-04-25T14:15:05Z","abstract_excerpt":"Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain largely limited to partial modality coverage, making it difficult to systematically evaluate full-modality representation learning. In this work, we take a step toward the full-modality setting. We introduce MMEB-V3, a comprehensive benchmark that evaluates embeddings across text, image, video, audio, as well as agent-centric scenarios. To enable more fine-grained diagnosis, we further construct OmniSET (Omni-modalit"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Current multimodal embeddings are not yet capable of reliably enforcing modality constraints specified by instructions, and consequently fail to exhibit consistent modality-aware retrieval behavior.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the OmniSET tuples truly represent semantic equivalence across modalities without residual modality-specific cues that could explain the observed retrieval failures.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multimodal embedding models cannot reliably enforce instructions to retrieve a target modality.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"75d66dd98295e3823bbf0d421697ee30efe51f1e1dd626bdc70e4fb4bf1f3d1d"},"source":{"id":"2604.23321","kind":"arxiv","version":2},"verdict":{"id":"060feda4-d27e-49d7-9138-f5fd1fd11c5d","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T07:24:36.472390Z","strongest_claim":"Current multimodal embeddings are not yet capable of reliably enforcing modality constraints specified by instructions, and consequently fail to exhibit consistent modality-aware retrieval behavior.","one_line_summary":"MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the OmniSET tuples truly represent semantic equivalence across modalities without residual modality-specific cues that could explain the observed retrieval failures.","pith_extraction_headline":"Multimodal embedding models cannot reliably enforce instructions to retrieve a target modality."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.23321/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T09:35:15.146851Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:16:00.296303Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a8fc80721ae5b80c1df92d15597d70ef8c90364e9d2000a28de29fc25830d74e"},"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":"060feda4-d27e-49d7-9138-f5fd1fd11c5d"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:19:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QWKWObKxAvLMld4nxuGNLEQ3RO6L5/3K/WJE9Jl41Xx4UNN2J1f9dS9ZWX+oUoGjW3qwHj+HThXXaavj1yT4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T03:10:52.327773Z"},"content_sha256":"c255af40953a09252ff8fc69d0895f47f10b6cbf089566c1f367d9a7ffec4e87","schema_version":"1.0","event_id":"sha256:c255af40953a09252ff8fc69d0895f47f10b6cbf089566c1f367d9a7ffec4e87"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE/bundle.json","state_url":"https://pith.science/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE/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":"2026-08-06T03:10:52Z","links":{"resolver":"https://pith.science/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE","bundle":"https://pith.science/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE/bundle.json","state":"https://pith.science/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6UVHNQFDCEPLHKKCXGBWBPWRE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:L6UVHNQFDCEPLHKKCXGBWBPWRE","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":"4f743aebd65f4c363e803bfa00b911bb7422b8406f87f1c69069e16f555368ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T14:15:05Z","title_canon_sha256":"678ff0458d9da90fb2f680c5e2661b6135e70cdd9e3e7fbe0f4a65a61a516e43"},"schema_version":"1.0","source":{"id":"2604.23321","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.23321","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2604.23321v2","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.23321","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"L6UVHNQFDCEP","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"L6UVHNQFDCEPLHKK","created_at":"2026-07-30T01:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"L6UVHNQF","created_at":"2026-07-30T01:19:51Z"}],"graph_snapshots":[{"event_id":"sha256:c255af40953a09252ff8fc69d0895f47f10b6cbf089566c1f367d9a7ffec4e87","target":"graph","created_at":"2026-07-30T01:19:51Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Current multimodal embeddings are not yet capable of reliably enforcing modality constraints specified by instructions, and consequently fail to exhibit consistent modality-aware retrieval behavior."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the OmniSET tuples truly represent semantic equivalence across modalities without residual modality-specific cues that could explain the observed retrieval failures."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Multimodal embedding models cannot reliably enforce instructions to retrieve a target modality."}],"snapshot_sha256":"75d66dd98295e3823bbf0d421697ee30efe51f1e1dd626bdc70e4fb4bf1f3d1d"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-21T09:35:15.146851Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T23:16:00.296303Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2604.23321/integrity.json","findings":[],"snapshot_sha256":"a8fc80721ae5b80c1df92d15597d70ef8c90364e9d2000a28de29fc25830d74e","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal embedding models aim to map heterogeneous inputs, such as text, images, videos, and audio, into a shared semantic space. However, existing methods and benchmarks remain largely limited to partial modality coverage, making it difficult to systematically evaluate full-modality representation learning. In this work, we take a step toward the full-modality setting. We introduce MMEB-V3, a comprehensive benchmark that evaluates embeddings across text, image, video, audio, as well as agent-centric scenarios. To enable more fine-grained diagnosis, we further construct OmniSET (Omni-modalit","authors_text":"Haohang Huang, Kai Zou, Mingyi Su, Ping Nie, Rui Meng, Tomas Pfister, Wei Zhang, Wenhu Chen, Xiaoyu Shen, Xuan Lu, Xuan Zhang, Ziyan Jiang","cross_cats":[],"headline":"Multimodal embedding models cannot reliably enforce instructions to retrieve a target modality.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T14:15:05Z","title":"MMEB-V3: Measuring the Performance Gaps of Omni-Modality Embedding Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.23321","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-08T07:24:36.472390Z","id":"060feda4-d27e-49d7-9138-f5fd1fd11c5d","model_set":{"reader":"grok-4.3"},"one_line_summary":"MMEB-V3 benchmark shows omni-modality embedding models fail to enforce instruction-specified modality constraints and exhibit asymmetric, query-biased retrieval.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Multimodal embedding models cannot reliably enforce instructions to retrieve a target modality.","strongest_claim":"Current multimodal embeddings are not yet capable of reliably enforcing modality constraints specified by instructions, and consequently fail to exhibit consistent modality-aware retrieval behavior.","weakest_assumption":"That the OmniSET tuples truly represent semantic equivalence across modalities without residual modality-specific cues that could explain the observed retrieval failures."}},"verdict_id":"060feda4-d27e-49d7-9138-f5fd1fd11c5d"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:96cf3aee6c9789a6255c72cce81ed3d22a8c20e91c69aa8411cba268311db721","target":"record","created_at":"2026-07-30T01:19:51Z","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":"4f743aebd65f4c363e803bfa00b911bb7422b8406f87f1c69069e16f555368ce","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-25T14:15:05Z","title_canon_sha256":"678ff0458d9da90fb2f680c5e2661b6135e70cdd9e3e7fbe0f4a65a61a516e43"},"schema_version":"1.0","source":{"id":"2604.23321","kind":"arxiv","version":2}},"canonical_sha256":"5fa953b6051888f59d4a15cc1b05f6891b79fdacc898c61c5550c4cd9b67ab40","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5fa953b6051888f59d4a15cc1b05f6891b79fdacc898c61c5550c4cd9b67ab40","first_computed_at":"2026-07-30T01:19:51.917729Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:19:51.917729Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2604.23321","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96cf3aee6c9789a6255c72cce81ed3d22a8c20e91c69aa8411cba268311db721","sha256:c255af40953a09252ff8fc69d0895f47f10b6cbf089566c1f367d9a7ffec4e87"],"state_sha256":"a21a039259c2f52d2ec7c030aac327bb68035fa5a3719cf28896250fa9d4647a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JGQs/C3dgq08a3dTgZGaScUbSD1Gnyr+VfqaXbiL6SruQGUiTPEm1Pzt/rMUPT/1XqEwkcIQi31C7F0mVQ5XDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T03:10:52.333777Z","bundle_sha256":"65d07f834a81464ac045ae9840f69354db97afea78136497cf6aa83a193ca75f"}}