{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SMS45R55I7EMCH6TNAWHHYYZIK","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":"89b1d0900b64ac6280fe0ef7fa5e0e7df7dbf8eaedf6dc2b7bbdad193233935c","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-15T04:48:41Z","title_canon_sha256":"78d99ce68562ce0b9f19ac6ea169c5cb9d801bdf596ee552b809781b2c593269"},"schema_version":"1.0","source":{"id":"2205.07180","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.07180","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"arxiv_version","alias_value":"2205.07180v2","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.07180","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_12","alias_value":"SMS45R55I7EM","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_16","alias_value":"SMS45R55I7EMCH6T","created_at":"2026-07-05T04:40:27Z"},{"alias_kind":"pith_short_8","alias_value":"SMS45R55","created_at":"2026-07-05T04:40:27Z"}],"graph_snapshots":[{"event_id":"sha256:96e4edd792933900115a437bea348263c0046d235a2c3b78acda7399725f45dc","target":"graph","created_at":"2026-07-05T04:40:27Z","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/2205.07180/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper investigates self-supervised pre-training for audio-visual speaker representation learning where a visual stream showing the speaker's mouth area is used alongside speech as inputs. Our study focuses on the Audio-Visual Hidden Unit BERT (AV-HuBERT) approach, a recently developed general-purpose audio-visual speech pre-training framework. We conducted extensive experiments probing the effectiveness of pre-training and visual modality. Experimental results suggest that AV-HuBERT generalizes decently to speaker related downstream tasks, improving label efficiency by roughly ten fold fo","authors_text":"Abdelrahman Mohamed, Bowen Shi, Wei-Ning Hsu","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-15T04:48:41Z","title":"Learning Lip-Based Audio-Visual Speaker Embeddings with AV-HuBERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.07180","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":"sha256:7a414b2fdf25dd0c5fc1f3bc5c71bc4489167077b0f260aa762bf10cf68a182b","target":"record","created_at":"2026-07-05T04:40:27Z","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":"89b1d0900b64ac6280fe0ef7fa5e0e7df7dbf8eaedf6dc2b7bbdad193233935c","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2022-05-15T04:48:41Z","title_canon_sha256":"78d99ce68562ce0b9f19ac6ea169c5cb9d801bdf596ee552b809781b2c593269"},"schema_version":"1.0","source":{"id":"2205.07180","kind":"arxiv","version":2}},"canonical_sha256":"9325cec7bd47c8c11fd3682c73e31942b6a6d7ed470106462d24b30b83e876b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9325cec7bd47c8c11fd3682c73e31942b6a6d7ed470106462d24b30b83e876b9","first_computed_at":"2026-07-05T04:40:27.303865Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:40:27.303865Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aNjEH1duuduRspgbW2qbo8UfjqeuG05aYP66b4zWN7s6eeFcRSlMcqwwxL7OVk9CezcyabdikGVQ7VsbbS8eBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:40:27.304364Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.07180","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a414b2fdf25dd0c5fc1f3bc5c71bc4489167077b0f260aa762bf10cf68a182b","sha256:96e4edd792933900115a437bea348263c0046d235a2c3b78acda7399725f45dc"],"state_sha256":"464c61778c6437a6287bb89068d548520bfec14ac298b7a6864ab38de5940693"}