{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:O5BANN5LL6WMSX7X5H365AWKMJ","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":"28adb4d3f878e8eeb64065cc797345cbd92c4583aae73ed2dd88283e5c57dc91","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:05:08Z","title_canon_sha256":"1734f9f2a87d493090c00d2831324b5cbc5549b38c52d32595ebdddfba275cf8"},"schema_version":"1.0","source":{"id":"2303.09455","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.09455","created_at":"2026-07-05T05:51:53Z"},{"alias_kind":"arxiv_version","alias_value":"2303.09455v1","created_at":"2026-07-05T05:51:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09455","created_at":"2026-07-05T05:51:53Z"},{"alias_kind":"pith_short_12","alias_value":"O5BANN5LL6WM","created_at":"2026-07-05T05:51:53Z"},{"alias_kind":"pith_short_16","alias_value":"O5BANN5LL6WMSX7X","created_at":"2026-07-05T05:51:53Z"},{"alias_kind":"pith_short_8","alias_value":"O5BANN5L","created_at":"2026-07-05T05:51:53Z"}],"graph_snapshots":[{"event_id":"sha256:e38dcef04985c84828889f2328a7e5777984e912e22e5333186be358e7e960bd","target":"graph","created_at":"2026-07-05T05:51:53Z","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/2303.09455/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised visual representation learning. We use the recently-proposed Raw Audio-Visual Speech Encoders (RAVEn) framework to pre-train an audio-visual model with unlabelled multilingual data, and then fine-tune the visual model on labelled transcriptions. Our experiments show that: (1) multi-lingual models with more data outperform monolingual ones, but, when keeping th","authors_text":"Alexandros Haliassos, Andreas Zinonos, Maja Pantic, Pingchuan Ma, Stavros Petridis","cross_cats":["cs.CV","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:05:08Z","title":"Learning Cross-lingual Visual Speech Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09455","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:aa44c9dc849807211c069730396602dff87b97155582a0079f62878b8205e522","target":"record","created_at":"2026-07-05T05:51:53Z","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":"28adb4d3f878e8eeb64065cc797345cbd92c4583aae73ed2dd88283e5c57dc91","cross_cats_sorted":["cs.CV","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-14T17:05:08Z","title_canon_sha256":"1734f9f2a87d493090c00d2831324b5cbc5549b38c52d32595ebdddfba275cf8"},"schema_version":"1.0","source":{"id":"2303.09455","kind":"arxiv","version":1}},"canonical_sha256":"774206b7ab5facc95ff7e9f7ee82ca6272967cade9d7943f2bc6069e3fff2d9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"774206b7ab5facc95ff7e9f7ee82ca6272967cade9d7943f2bc6069e3fff2d9c","first_computed_at":"2026-07-05T05:51:53.725498Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:51:53.725498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZODSmwETjhvaeJdmM1hyh9kVYTQqJiTg/8CYOADWGdNH31wJkRb0UWI+aGdBVTKmSgaffAAT57KM+zZCKuhJBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:51:53.725984Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.09455","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa44c9dc849807211c069730396602dff87b97155582a0079f62878b8205e522","sha256:e38dcef04985c84828889f2328a7e5777984e912e22e5333186be358e7e960bd"],"state_sha256":"db1b9f49991270397cdfca4e64e559dbb6d70639b8a9b9cd4ca15ff743b7a4cd"}