{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JH4VDCKGZTFEKSV42D554J7UT2","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":"e684e1417e8261fa5e5c83f856d2aa57e99147a2158761191908a4aaa720f643","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-09T03:37:01Z","title_canon_sha256":"da592a6d6193ac0f0526a9db5aee7c968d7820fc03e797e64b137c2602e6c40c"},"schema_version":"1.0","source":{"id":"2502.05758","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.05758","created_at":"2026-07-05T10:11:42Z"},{"alias_kind":"arxiv_version","alias_value":"2502.05758v1","created_at":"2026-07-05T10:11:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05758","created_at":"2026-07-05T10:11:42Z"},{"alias_kind":"pith_short_12","alias_value":"JH4VDCKGZTFE","created_at":"2026-07-05T10:11:42Z"},{"alias_kind":"pith_short_16","alias_value":"JH4VDCKGZTFEKSV4","created_at":"2026-07-05T10:11:42Z"},{"alias_kind":"pith_short_8","alias_value":"JH4VDCKG","created_at":"2026-07-05T10:11:42Z"}],"graph_snapshots":[{"event_id":"sha256:020f7ff4252bbb8b72400a98233c51a2f01da6186a0ed08fdb800a24bbd874f6","target":"graph","created_at":"2026-07-05T10:11:42Z","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/2502.05758/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Lipreading is an important technique for facilitating human-computer interaction in noisy environments. Our previously developed self-supervised learning method, AV2vec, which leverages multimodal self-distillation, has demonstrated promising performance in speaker-independent lipreading on the English LRS3 dataset. However, AV2vec faces challenges such as high training costs and a potential scarcity of audio-visual data for lipreading in languages other than English, such as Chinese. Additionally, most studies concentrate on speakerindependent lipreading models, which struggle to account for ","authors_text":"Jing-Xuan Zhang, Jin Li, Lichen Zhang, Longjiang Guo, Tingzhi Mao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-09T03:37:01Z","title":"Target Speaker Lipreading by Audio-Visual Self-Distillation Pretraining and Speaker Adaptation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05758","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":"sha256:76a223495d1bfe20a158b9d6cb9a341a40ad8cf7adb976ca06f1ed258ced563c","target":"record","created_at":"2026-07-05T10:11:42Z","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":"e684e1417e8261fa5e5c83f856d2aa57e99147a2158761191908a4aaa720f643","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-09T03:37:01Z","title_canon_sha256":"da592a6d6193ac0f0526a9db5aee7c968d7820fc03e797e64b137c2602e6c40c"},"schema_version":"1.0","source":{"id":"2502.05758","kind":"arxiv","version":1}},"canonical_sha256":"49f9518946ccca454abcd0fbde27f49ebce042fd85c1f4070fbdc8b456293b72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"49f9518946ccca454abcd0fbde27f49ebce042fd85c1f4070fbdc8b456293b72","first_computed_at":"2026-07-05T10:11:42.963773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:42.963773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S/n6wbdd8EdPEdSnrRUoe4QS4Aghkbn4ef1hYSzC6A3hDsDXZmbnlVcfxO4qlJJT2sLKFW3c7hFGWWxf4YgbCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:42.964223Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.05758","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76a223495d1bfe20a158b9d6cb9a341a40ad8cf7adb976ca06f1ed258ced563c","sha256:020f7ff4252bbb8b72400a98233c51a2f01da6186a0ed08fdb800a24bbd874f6"],"state_sha256":"0d36b6d1de41a307b3668f56d319213b96ad83903a1c599d932e39802b868daa"}