{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LMJB5RN2CHXIHSEMENANLANED5","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":"70444648a487632d8220eeb8000f511d450306ba23c58eb533428d28810a3658","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T04:54:53Z","title_canon_sha256":"15857970aa7cbb9241e0828260366d8fef9b90afe6a94afdd71f486056c775e6"},"schema_version":"1.0","source":{"id":"2607.08112","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.08112","created_at":"2026-07-10T01:19:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.08112v1","created_at":"2026-07-10T01:19:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.08112","created_at":"2026-07-10T01:19:26Z"},{"alias_kind":"pith_short_12","alias_value":"LMJB5RN2CHXI","created_at":"2026-07-10T01:19:26Z"},{"alias_kind":"pith_short_16","alias_value":"LMJB5RN2CHXIHSEM","created_at":"2026-07-10T01:19:26Z"},{"alias_kind":"pith_short_8","alias_value":"LMJB5RN2","created_at":"2026-07-10T01:19:26Z"}],"graph_snapshots":[{"event_id":"sha256:d04afa9fe1f93edf2ac705f9070665683aced71836b520eabb6021d008ed3d4d","target":"graph","created_at":"2026-07-10T01:19:26Z","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/2607.08112/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VSRo-200, the first large-scale dataset for visual speech recognition (lip reading) in Romanian, comprising 200 hours of real-world podcast videos. All samples are annotated with pseudo-labels generated by a fine-tuned Romanian ASR model, while a subset of 100 hours is additionally transcribed by humans, enabling controlled analysis of supervision quality under a unified framework. Building on this dataset, we establish a benchmark for visual speech recognition in low-resource settings. We systematically study the impact of supervision quality, showing that while human annotations","authors_text":"Alexandra Diaconu, Bogdan Alexe, Iulia-Maria Udrea","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T04:54:53Z","title":"VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.08112","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:cf1241949b160f856b21d1c041241224bfd59f7247eb01974407f869f2bd5b8c","target":"record","created_at":"2026-07-10T01:19:26Z","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":"70444648a487632d8220eeb8000f511d450306ba23c58eb533428d28810a3658","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-09T04:54:53Z","title_canon_sha256":"15857970aa7cbb9241e0828260366d8fef9b90afe6a94afdd71f486056c775e6"},"schema_version":"1.0","source":{"id":"2607.08112","kind":"arxiv","version":1}},"canonical_sha256":"5b121ec5ba11ee83c88c2340d581a41f7913ca6fce8e2f4d2575f7ec3e994f6b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b121ec5ba11ee83c88c2340d581a41f7913ca6fce8e2f4d2575f7ec3e994f6b","first_computed_at":"2026-07-10T01:19:26.369802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-10T01:19:26.369802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uUjrjaEIBXCzl4pj7gI0BW2pHkSH81YGwRkB0GqRwqeRIam7VAb3PQSUaUlGJoasc6dspKdAKnggCNqllAtqBA==","signature_status":"signed_v1","signed_at":"2026-07-10T01:19:26.370232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.08112","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cf1241949b160f856b21d1c041241224bfd59f7247eb01974407f869f2bd5b8c","sha256:d04afa9fe1f93edf2ac705f9070665683aced71836b520eabb6021d008ed3d4d"],"state_sha256":"e6d1e396e28be3f7319f72ba082d5e6e7d044a400f356788a819334e6f7b9e01"}