{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:U2OJ2JABOCDNOAN6EZJJS6XNAC","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":"5cb4c310be2b5e108b2e5ee4e790a4f07a186191471cbc465469b87060777c0d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T13:55:15Z","title_canon_sha256":"fa1f5a998541ecf9716f67bf89cc7ed8ba9dce6b79b6f1c19717f01d16b392ec"},"schema_version":"1.0","source":{"id":"2208.11553","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.11553","created_at":"2026-07-05T06:53:31Z"},{"alias_kind":"arxiv_version","alias_value":"2208.11553v7","created_at":"2026-07-05T06:53:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.11553","created_at":"2026-07-05T06:53:31Z"},{"alias_kind":"pith_short_12","alias_value":"U2OJ2JABOCDN","created_at":"2026-07-05T06:53:31Z"},{"alias_kind":"pith_short_16","alias_value":"U2OJ2JABOCDNOAN6","created_at":"2026-07-05T06:53:31Z"},{"alias_kind":"pith_short_8","alias_value":"U2OJ2JAB","created_at":"2026-07-05T06:53:31Z"}],"graph_snapshots":[{"event_id":"sha256:918f13b680d8280ad292c973d0a2c26db993aaf6bd01cddbcd9e4512a046759e","target":"graph","created_at":"2026-07-05T06:53:31Z","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/2208.11553/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal retrieval has seen tremendous progress with the development of vision-language models. However, further improving these models require additional labelled data which is a huge manual effort. In this paper, we propose a framework MuMUR, that utilizes knowledge transfer from a multilingual model to boost the performance of multi-modal (image and video) retrieval. We first use state-of-the-art machine translation models to construct pseudo ground-truth multilingual visual-text pairs. We then use this data to learn a joint vision-text representation where English and non-English text q","authors_text":"Avinash Madasu, Estelle Aflalo, Gabriela Ben Melech Stan, Gedas Bertasius, Shachar Rosenman, Shao-Yen Tseng, Vasudev Lal","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T13:55:15Z","title":"MuMUR : Multilingual Multimodal Universal Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.11553","kind":"arxiv","version":7},"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":"sha256:310d2c84119902171e65e6b4e3f8571bc32a6b53f3fe2e9bad0bba3fa1b1a333","target":"record","created_at":"2026-07-05T06:53:31Z","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":"5cb4c310be2b5e108b2e5ee4e790a4f07a186191471cbc465469b87060777c0d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-08-24T13:55:15Z","title_canon_sha256":"fa1f5a998541ecf9716f67bf89cc7ed8ba9dce6b79b6f1c19717f01d16b392ec"},"schema_version":"1.0","source":{"id":"2208.11553","kind":"arxiv","version":7}},"canonical_sha256":"a69c9d24017086d701be2652997aed00ab0b0be9e796b66241e474494113b112","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a69c9d24017086d701be2652997aed00ab0b0be9e796b66241e474494113b112","first_computed_at":"2026-07-05T06:53:31.053795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:53:31.053795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NnK+qKOQ4wNVt/k8gq8vVjKYVnp07x6Iz+phnGBxGW49qsFD0vA44V57nv0Z4CwIvUipFsDyHLjpgyPiC07fCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:53:31.054202Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.11553","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:310d2c84119902171e65e6b4e3f8571bc32a6b53f3fe2e9bad0bba3fa1b1a333","sha256:918f13b680d8280ad292c973d0a2c26db993aaf6bd01cddbcd9e4512a046759e"],"state_sha256":"5cf99109d04fb427151a93e3e7d305bcc6ea3468d6a85c780f05155ec9c63860"}