{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZFDJUWI57LX66LRBJF7HTF5UN6","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":"54a92d7a651e26329e5fd1992325af6d131f8c27a5b1fe102d7c7bf01958a226","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-16T20:17:06Z","title_canon_sha256":"38a1b5dd481a5e6998c1f776550ff1358bb6b4388d889ee1567afb60de3749a7"},"schema_version":"1.0","source":{"id":"2508.12149","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12149","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12149v1","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12149","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_12","alias_value":"ZFDJUWI57LX6","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_16","alias_value":"ZFDJUWI57LX66LRB","created_at":"2026-07-05T11:55:00Z"},{"alias_kind":"pith_short_8","alias_value":"ZFDJUWI5","created_at":"2026-07-05T11:55:00Z"}],"graph_snapshots":[{"event_id":"sha256:580a5c9b6d6ae66d1855958f81aed928894948f04420d690564b6bc2cde8b2e9","target":"graph","created_at":"2026-07-05T11:55:00Z","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/2508.12149/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in multimodal learning have largely relied on pairwise contrastive objectives to align different modalities, such as text, video, and audio, in a shared embedding space. While effective in bi-modal setups, these approaches struggle to generalize across multiple modalities and often lack semantic structure in high-dimensional spaces. In this paper, we propose MOVER, a novel framework that combines optimal transport-based soft alignment with volume-based geometric regularization to build semantically aligned and structured multimodal representations. By integrating a transport-gu","authors_text":"Baojing Liu, Haochen You","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-16T20:17:06Z","title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12149","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":"sha256:6ae74826acd0b1aeb3c32b6809e0e0368cc9aa6062ea9b843d8758ecc87f8cce","target":"record","created_at":"2026-07-05T11:55:00Z","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":"54a92d7a651e26329e5fd1992325af6d131f8c27a5b1fe102d7c7bf01958a226","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-16T20:17:06Z","title_canon_sha256":"38a1b5dd481a5e6998c1f776550ff1358bb6b4388d889ee1567afb60de3749a7"},"schema_version":"1.0","source":{"id":"2508.12149","kind":"arxiv","version":1}},"canonical_sha256":"c9469a591dfaefef2e21497e7997b46fbec527cd56e54084a95bf7fd8ddbfa0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9469a591dfaefef2e21497e7997b46fbec527cd56e54084a95bf7fd8ddbfa0e","first_computed_at":"2026-07-05T11:55:00.924462Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:00.924462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qqaYf/OacTsx4Mf72pYQy3BfJo2OJU0yuF0eGMr9G3y3+QMXaTokJulKEnRng+f3eWzTh9DexFB06mQ0oDfUDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:00.924880Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12149","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ae74826acd0b1aeb3c32b6809e0e0368cc9aa6062ea9b843d8758ecc87f8cce","sha256:580a5c9b6d6ae66d1855958f81aed928894948f04420d690564b6bc2cde8b2e9"],"state_sha256":"906a9bec8288c0b5796adfa1a54aab43818bfa76f865d20e0f686840e9ce0c51"}