{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TXLPBSXVXKFHCUCO6DFTVQP62H","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":"b15a8165f7ca06d224fb6f560a08de724c20edbb17a49429d313850969f34c67","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-11T12:59:02Z","title_canon_sha256":"24e2353ad296c4ea8abafbba36a0df231b302f8322ec338796bf02beb5af7a83"},"schema_version":"1.0","source":{"id":"2308.06112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.06112","created_at":"2026-07-05T06:40:23Z"},{"alias_kind":"arxiv_version","alias_value":"2308.06112v1","created_at":"2026-07-05T06:40:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.06112","created_at":"2026-07-05T06:40:23Z"},{"alias_kind":"pith_short_12","alias_value":"TXLPBSXVXKFH","created_at":"2026-07-05T06:40:23Z"},{"alias_kind":"pith_short_16","alias_value":"TXLPBSXVXKFHCUCO","created_at":"2026-07-05T06:40:23Z"},{"alias_kind":"pith_short_8","alias_value":"TXLPBSXV","created_at":"2026-07-05T06:40:23Z"}],"graph_snapshots":[{"event_id":"sha256:babec7282f59d32da737c515a199ef009cb5644da4627d0ed8700e2fb1394e22","target":"graph","created_at":"2026-07-05T06:40:23Z","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/2308.06112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Speech Recognition (VSR) differs from the common perception tasks as it requires deeper reasoning over the video sequence, even by human experts. Despite the recent advances in VSR, current approaches rely on labeled data to fully train or finetune their models predicting the target speech. This hinders their ability to generalize well beyond the training set and leads to performance degeneration under out-of-distribution challenging scenarios. Unlike previous works that involve auxiliary losses or complex training procedures and architectures, we propose a simple approach, named Lip2Ve","authors_text":"Ebtessam Almazrouei, Haithem Boussaid, Merouane Debbah, Sanath Narayan, Yasser Abdelaziz Dahou Djilali","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-11T12:59:02Z","title":"Lip2Vec: Efficient and Robust Visual Speech Recognition via Latent-to-Latent Visual to Audio Representation Mapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.06112","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":"sha256:6199bf7e1c0535a452dc1e03a7e36ef14bee939523b3285261317840f96b2ff8","target":"record","created_at":"2026-07-05T06:40:23Z","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":"b15a8165f7ca06d224fb6f560a08de724c20edbb17a49429d313850969f34c67","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-08-11T12:59:02Z","title_canon_sha256":"24e2353ad296c4ea8abafbba36a0df231b302f8322ec338796bf02beb5af7a83"},"schema_version":"1.0","source":{"id":"2308.06112","kind":"arxiv","version":1}},"canonical_sha256":"9dd6f0caf5ba8a71504ef0cb3ac1fed1e04fe560e50ca57c99a940efd04c7d24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dd6f0caf5ba8a71504ef0cb3ac1fed1e04fe560e50ca57c99a940efd04c7d24","first_computed_at":"2026-07-05T06:40:23.599984Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:40:23.599984Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FadQtenDmvdKsxPN0N+/ZlRWHuhkCgSrQwHkpowmKxHHeevh3rgZnLBMTrQJIgEOQklnIvIYc0iZzsYblFFuBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:40:23.600504Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.06112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6199bf7e1c0535a452dc1e03a7e36ef14bee939523b3285261317840f96b2ff8","sha256:babec7282f59d32da737c515a199ef009cb5644da4627d0ed8700e2fb1394e22"],"state_sha256":"955596ec14c37d743cef939fd789dfa4223bbbbefad538ee2b566ba88e14a23f"}