{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:C4Y7AZSJMKO4R3224MTDEDEZPK","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":"9316b96e5f03f1a74285a643f092b272949f20815692a9c927e9e3c79b677439","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T11:44:01Z","title_canon_sha256":"4b95b7e687c367ad70596e69b5b3a6bbb00bcacfe91a0ef8706faef76df248ef"},"schema_version":"1.0","source":{"id":"2605.21059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21059","created_at":"2026-05-21T01:05:34Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21059v1","created_at":"2026-05-21T01:05:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21059","created_at":"2026-05-21T01:05:34Z"},{"alias_kind":"pith_short_12","alias_value":"C4Y7AZSJMKO4","created_at":"2026-05-21T01:05:34Z"},{"alias_kind":"pith_short_16","alias_value":"C4Y7AZSJMKO4R322","created_at":"2026-05-21T01:05:34Z"},{"alias_kind":"pith_short_8","alias_value":"C4Y7AZSJ","created_at":"2026-05-21T01:05:34Z"}],"graph_snapshots":[{"event_id":"sha256:80497fb2355e777e7e5a137533d5b7c77302525da26fd181cd2d1b45c2c6d696","target":"graph","created_at":"2026-05-21T01:05:34Z","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/2605.21059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive results achieved by multimodal large language models (MLLMs), their training typically relies on jointly curated multimodal data, requiring substantial human effort to construct multi-way aligned datasets and thereby limiting scalability across domains. In this work, we explore training MLLMs by only leveraging multiple paired modalities as a surrogate for the full joint multimodal distribution. Specifically, we first provide a theoretical analysis of the conditions under which the representations are identifiable with only observing pairwise modalities. Building on this","authors_text":"Gongxu Luo, Guangyi Chen, Kun Zhang, Yan Li, Yuewen Sun, Yunlong Deng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T11:44:01Z","title":"Multimodal LLMs under Pairwise Modalities"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21059","kind":"arxiv","version":1},"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":"sha256:5626097a1c70e7d8139ce4969433d58d899d8781719e65f456a556308abe45ec","target":"record","created_at":"2026-05-21T01:05:34Z","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":"9316b96e5f03f1a74285a643f092b272949f20815692a9c927e9e3c79b677439","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T11:44:01Z","title_canon_sha256":"4b95b7e687c367ad70596e69b5b3a6bbb00bcacfe91a0ef8706faef76df248ef"},"schema_version":"1.0","source":{"id":"2605.21059","kind":"arxiv","version":1}},"canonical_sha256":"1731f06649629dc8ef5ae326320c997a8a32c786d3b5e010e293a7093eed99e6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1731f06649629dc8ef5ae326320c997a8a32c786d3b5e010e293a7093eed99e6","first_computed_at":"2026-05-21T01:05:34.556371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:34.556371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vc+XsQQM6B9aln/oc+mN2tL1TeMtK6+C0oWhJlmtj+s3u3KNnOBcGmip2+C5fOUc4OhRQ7HAO1JZIiSoVsuPBQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:34.557578Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5626097a1c70e7d8139ce4969433d58d899d8781719e65f456a556308abe45ec","sha256:80497fb2355e777e7e5a137533d5b7c77302525da26fd181cd2d1b45c2c6d696"],"state_sha256":"a22b7592ad61a7dad76c53290f36462d5d4ac18811dbd1b8624a13e6b83db794"}