{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OWURPIBN5BVMUEQSJAGLEHT53P","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":"d5dfdc408593abedc20bf5b33ace5d1ab5525ae3dee4eb32edfceff1c55e3426","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T16:48:20Z","title_canon_sha256":"34da20055420a9ec5266d23802c5e09d033106ed1d5da95dd5a07a7dbb3e53f6"},"schema_version":"1.0","source":{"id":"2404.02098","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02098","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02098v1","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02098","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"pith_short_12","alias_value":"OWURPIBN5BVM","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"pith_short_16","alias_value":"OWURPIBN5BVMUEQS","created_at":"2026-07-05T08:03:35Z"},{"alias_kind":"pith_short_8","alias_value":"OWURPIBN","created_at":"2026-07-05T08:03:35Z"}],"graph_snapshots":[{"event_id":"sha256:2e03dcee3c9c08da70b3b671ddd81fd8003ed3969015df81c85a782d8525afb8","target":"graph","created_at":"2026-07-05T08:03:35Z","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/2404.02098/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Self-supervision has recently shown great promise for learning visual and auditory speech representations from unlabelled data. In this work, we propose BRAVEn, an extension to the recent RAVEn method, which learns speech representations entirely from raw audio-visual data. Our modifications to RAVEn enable BRAVEn to achieve state-of-the-art results among self-supervised methods in various settings. Moreover, we observe favourable scaling behaviour by increasing the amount of unlabelled data well beyond other self-supervised works. In particular, we achieve 20.0% / 1.7% word error rate for VSR","authors_text":"Alexandros Haliassos, Andreas Zinonos, Maja Pantic, Rodrigo Mira, Stavros Petridis","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T16:48:20Z","title":"BRAVEn: Improving Self-Supervised Pre-training for Visual and Auditory Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02098","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":"sha256:8a3d9d1f52573503488c44a1bf4e690db82c6e32fb0190cd0ed4f47352676e6c","target":"record","created_at":"2026-07-05T08:03:35Z","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":"d5dfdc408593abedc20bf5b33ace5d1ab5525ae3dee4eb32edfceff1c55e3426","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T16:48:20Z","title_canon_sha256":"34da20055420a9ec5266d23802c5e09d033106ed1d5da95dd5a07a7dbb3e53f6"},"schema_version":"1.0","source":{"id":"2404.02098","kind":"arxiv","version":1}},"canonical_sha256":"75a917a02de86aca1212480cb21e7ddbe79fb6b9998d775ac2209a7779b41e4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75a917a02de86aca1212480cb21e7ddbe79fb6b9998d775ac2209a7779b41e4f","first_computed_at":"2026-07-05T08:03:35.832117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:35.832117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tLLcm41elT0wSGJMNyV9zTPdsiZ7b2f1XAcubao3f0HjfYVyggDvqoH+i1Ov33JynorS5wX5Cr11owDGTbc6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:35.832603Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02098","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a3d9d1f52573503488c44a1bf4e690db82c6e32fb0190cd0ed4f47352676e6c","sha256:2e03dcee3c9c08da70b3b671ddd81fd8003ed3969015df81c85a782d8525afb8"],"state_sha256":"3342e70a00f6b0bc1d3f9784c86fd2fb23bcfae251fe3a87ba4e51b3c377a47d"}