{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:G2DYIAIYVQ2EFH6RETFGTPTXVF","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":"cfb06da3f20917d3e41b4a1c110359b759a89e933ee4c6389a829ef47c34132a","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-04T13:34:07Z","title_canon_sha256":"0e1088fa472a5f196413c9c21a2c0eec8c3b3c29c99e16fac143cc1cbc8e111e"},"schema_version":"1.0","source":{"id":"2205.02058","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.02058","created_at":"2026-07-05T04:48:50Z"},{"alias_kind":"arxiv_version","alias_value":"2205.02058v2","created_at":"2026-07-05T04:48:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.02058","created_at":"2026-07-05T04:48:50Z"},{"alias_kind":"pith_short_12","alias_value":"G2DYIAIYVQ2E","created_at":"2026-07-05T04:48:50Z"},{"alias_kind":"pith_short_16","alias_value":"G2DYIAIYVQ2EFH6R","created_at":"2026-07-05T04:48:50Z"},{"alias_kind":"pith_short_8","alias_value":"G2DYIAIY","created_at":"2026-07-05T04:48:50Z"}],"graph_snapshots":[{"event_id":"sha256:01d71b8acece79db7022ce1627b555d9edfb488fa58c2e4394d74b286e413388","target":"graph","created_at":"2026-07-05T04:48:50Z","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/2205.02058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-speech synthesis (also known as lip-to-speech) refers to the translation of silent lip movements into the corresponding audio. This task has received an increasing amount of attention due to its self-supervised nature (i.e., can be trained without manual labelling) combined with the ever-growing collection of audio-visual data available online. Despite these strong motivations, contemporary video-to-speech works focus mainly on small- to medium-sized corpora with substantial constraints in both vocabulary and setting. In this work, we introduce a scalable video-to-speech framework con","authors_text":"Alexandros Haliassos, Bj\\\"orn W. Schuller, Maja Pantic, Rodrigo Mira, Stavros Petridis","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-04T13:34:07Z","title":"SVTS: Scalable Video-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.02058","kind":"arxiv","version":2},"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":"sha256:909089ec0d3fcd7b7f267b8bb35cb432b8911020b045a1b5f3ffd71113e5d78e","target":"record","created_at":"2026-07-05T04:48:50Z","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":"cfb06da3f20917d3e41b4a1c110359b759a89e933ee4c6389a829ef47c34132a","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-05-04T13:34:07Z","title_canon_sha256":"0e1088fa472a5f196413c9c21a2c0eec8c3b3c29c99e16fac143cc1cbc8e111e"},"schema_version":"1.0","source":{"id":"2205.02058","kind":"arxiv","version":2}},"canonical_sha256":"3687840118ac34429fd124ca69be77a9692c7a87501596215e049724a35c5258","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3687840118ac34429fd124ca69be77a9692c7a87501596215e049724a35c5258","first_computed_at":"2026-07-05T04:48:50.340333Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:48:50.340333Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UDIotL5ILcGRAXBTc7/j690d52gFaOoe7wZRNXd5xKpThRjhc4ZklGBND3YBGP8Eeivw1hQqjcVJThMOrZV3CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:48:50.340738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.02058","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:909089ec0d3fcd7b7f267b8bb35cb432b8911020b045a1b5f3ffd71113e5d78e","sha256:01d71b8acece79db7022ce1627b555d9edfb488fa58c2e4394d74b286e413388"],"state_sha256":"2bdce2e6d5d7401a64cc152b7bba2a838cd8af4895019f0d765c96b0ea4babfb"}