{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZFDJUWI57LX66LRBJF7HTF5UN6","short_pith_number":"pith:ZFDJUWI5","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"},"canonical_sha256":"c9469a591dfaefef2e21497e7997b46fbec527cd56e54084a95bf7fd8ddbfa0e","source":{"kind":"arxiv","id":"2508.12149","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZFDJUWI57LX66LRBJF7HTF5UN6","target":"record","payload":{"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"},"canonical_sha256":"c9469a591dfaefef2e21497e7997b46fbec527cd56e54084a95bf7fd8ddbfa0e","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"},"source_kind":"arxiv","source_id":"2508.12149","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7HHRhabt3GKszqK4xYPPRvkmAovQCZWsxOPEecC49H7uN4gqYfmjgqHgt7f6kSan07UIi6VSZIRt1e91FTriDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:27:02.265137Z"},"content_sha256":"6ae74826acd0b1aeb3c32b6809e0e0368cc9aa6062ea9b843d8758ecc87f8cce","schema_version":"1.0","event_id":"sha256:6ae74826acd0b1aeb3c32b6809e0e0368cc9aa6062ea9b843d8758ecc87f8cce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZFDJUWI57LX66LRBJF7HTF5UN6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:55:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FM454HBauJFTjQCAkPweBOIorkSAiXMzy5cixgoh/24sXerzqac+870T9TFWyueU3hFh0gcg1BPSHdGxx+S7Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:27:02.266084Z"},"content_sha256":"580a5c9b6d6ae66d1855958f81aed928894948f04420d690564b6bc2cde8b2e9","schema_version":"1.0","event_id":"sha256:580a5c9b6d6ae66d1855958f81aed928894948f04420d690564b6bc2cde8b2e9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/bundle.json","state_url":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/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":"2026-08-17T13:27:02Z","links":{"resolver":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6","bundle":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/bundle.json","state":"https://pith.science/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZFDJUWI57LX66LRBJF7HTF5UN6/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Otv29Bcz2+rSywPjqvK/EM1hVKmWnqPSoH6g4VLqAMI7j6kMrrsQTa9eohTaEY0pIlOlmk1AmEytHt/iUVYBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:27:02.342918Z","bundle_sha256":"9fadf12d86aedf1233eba724a293ce4b2b8d39c6b23813da86a0da36871e8fd6"}}