{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZFDJUWI57LX66LRBJF7HTF5UN6","short_pith_number":"pith:ZFDJUWI5","schema_version":"1.0","canonical_sha256":"c9469a591dfaefef2e21497e7997b46fbec527cd56e54084a95bf7fd8ddbfa0e","source":{"kind":"arxiv","id":"2508.12149","version":1},"attestation_state":"computed","paper":{"title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baojing Liu, Haochen You","submitted_at":"2025-08-16T20:17:06Z","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"},"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":"2508.12149","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-16T20:17:06Z","cross_cats_sorted":[],"title_canon_sha256":"38a1b5dd481a5e6998c1f776550ff1358bb6b4388d889ee1567afb60de3749a7","abstract_canon_sha256":"54a92d7a651e26329e5fd1992325af6d131f8c27a5b1fe102d7c7bf01958a226"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:00.924880Z","signature_b64":"qqaYf/OacTsx4Mf72pYQy3BfJo2OJU0yuF0eGMr9G3y3+QMXaTokJulKEnRng+f3eWzTh9DexFB06mQ0oDfUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9469a591dfaefef2e21497e7997b46fbec527cd56e54084a95bf7fd8ddbfa0e","last_reissued_at":"2026-07-05T11:55:00.924462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:00.924462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MOVER: Multimodal Optimal Transport with Volume-based Embedding Regularization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Baojing Liu, Haochen You","submitted_at":"2025-08-16T20:17:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12149","kind":"arxiv","version":1},"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/2508.12149/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":"2508.12149","created_at":"2026-07-05T11:55:00.924518+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.12149v1","created_at":"2026-07-05T11:55:00.924518+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12149","created_at":"2026-07-05T11:55:00.924518+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFDJUWI57LX6","created_at":"2026-07-05T11:55:00.924518+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFDJUWI57LX66LRB","created_at":"2026-07-05T11:55:00.924518+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFDJUWI5","created_at":"2026-07-05T11:55:00.924518+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.17426","citing_title":"Modular MeanFlow: Towards Stable and Scalable One-Step Generative Modeling","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6","json":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6.json","graph_json":"https://pith.science/api/pith-number/ZFDJUWI57LX66LRBJF7HTF5UN6/graph.json","events_json":"https://pith.science/api/pith-number/ZFDJUWI57LX66LRBJF7HTF5UN6/events.json","paper":"https://pith.science/paper/ZFDJUWI5"},"agent_actions":{"view_html":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6","download_json":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6.json","view_paper":"https://pith.science/paper/ZFDJUWI5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.12149&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFDJUWI57LX66LRBJF7HTF5UN6/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFDJUWI57LX66LRBJF7HTF5UN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/action/storage_attestation","attest_author":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/action/author_attestation","sign_citation":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/action/citation_signature","submit_replication":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/action/replication_record"}},"created_at":"2026-07-05T11:55:00.924518+00:00","updated_at":"2026-07-05T11:55:00.924518+00:00"}