{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KHFS3LDJLIH3R2KZ7TLAH5OD5D","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":"d902f6215f4e32b3b5041fcff81407fb86653cac1dc23834b5294ec0e013b84f","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-24T22:13:21Z","title_canon_sha256":"7d88a75553371e1a0ff2560dfb9ba594e41977947161c0b00b510084f54a126c"},"schema_version":"1.0","source":{"id":"2012.05107","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05107","created_at":"2026-07-05T01:58:18Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05107v1","created_at":"2026-07-05T01:58:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05107","created_at":"2026-07-05T01:58:18Z"},{"alias_kind":"pith_short_12","alias_value":"KHFS3LDJLIH3","created_at":"2026-07-05T01:58:18Z"},{"alias_kind":"pith_short_16","alias_value":"KHFS3LDJLIH3R2KZ","created_at":"2026-07-05T01:58:18Z"},{"alias_kind":"pith_short_8","alias_value":"KHFS3LDJ","created_at":"2026-07-05T01:58:18Z"}],"graph_snapshots":[{"event_id":"sha256:a96b0ca190131f8dea99b00eb773f83cb1fb92dd383abe32650248974d81dedd","target":"graph","created_at":"2026-07-05T01:58:18Z","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/2012.05107/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been a recent spike in interest in multi-modal Language and Vision problems. On the language side, most of these models primarily focus on English since most multi-modal datasets are monolingual. We try to bridge this gap with a zero-shot approach for learning multi-modal representations using cross-lingual pre-training on the text side. We present a simple yet practical approach for building a cross-lingual image retrieval model which trains on a monolingual training dataset but can be used in a zero-shot cross-lingual fashion during inference. We also introduce a new objective func","authors_text":"Ajinkya Kale, Pranav Aggarwal","cross_cats":["cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-24T22:13:21Z","title":"Towards Zero-shot Cross-lingual Image Retrieval"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05107","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":"sha256:6f2f2b101d1d62bfa8b693ce436ad87afb570945e422f754d66fbea425d94128","target":"record","created_at":"2026-07-05T01:58:18Z","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":"d902f6215f4e32b3b5041fcff81407fb86653cac1dc23834b5294ec0e013b84f","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-24T22:13:21Z","title_canon_sha256":"7d88a75553371e1a0ff2560dfb9ba594e41977947161c0b00b510084f54a126c"},"schema_version":"1.0","source":{"id":"2012.05107","kind":"arxiv","version":1}},"canonical_sha256":"51cb2dac695a0fb8e959fcd603f5c3e8c5a620d3ce37a4a730d413fa591fc173","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"51cb2dac695a0fb8e959fcd603f5c3e8c5a620d3ce37a4a730d413fa591fc173","first_computed_at":"2026-07-05T01:58:18.864203Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:18.864203Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PgNi3D3+gT0RJG1WM5a7pWbMlA4QQ9rS7QqJY6FQZ7+Y5DdrI2ft3IA8Dd9uiWAHfI0qfnt3PvC+RLPv456MDg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:18.864610Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05107","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f2f2b101d1d62bfa8b693ce436ad87afb570945e422f754d66fbea425d94128","sha256:a96b0ca190131f8dea99b00eb773f83cb1fb92dd383abe32650248974d81dedd"],"state_sha256":"3711e314cd290ca51b163670d0ad6ceee08380bebd18527ed11e5a655e4da7aa"}