{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:KITKBZ4KXASOFF24LKHUVK4UNW","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":"db338ca29162ca7dc5cf8f9fb8f404cf4196faef5cc84a2bbe83af695c22cc9f","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T23:20:06Z","title_canon_sha256":"f49ee7c7d3f7bf2452fea69508b945b5e0c58d4db543bf6dd88c291d82e8e6d1"},"schema_version":"1.0","source":{"id":"2106.09171","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.09171","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"arxiv_version","alias_value":"2106.09171v1","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.09171","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"pith_short_12","alias_value":"KITKBZ4KXASO","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"pith_short_16","alias_value":"KITKBZ4KXASOFF24","created_at":"2026-07-05T02:50:13Z"},{"alias_kind":"pith_short_8","alias_value":"KITKBZ4K","created_at":"2026-07-05T02:50:13Z"}],"graph_snapshots":[{"event_id":"sha256:763009737d7e23f3c8440e8a283ef719fc6894f20695e47c36c989742cdae2f3","target":"graph","created_at":"2026-07-05T02:50:13Z","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/2106.09171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac","authors_text":"Bj\\\"orn W. Schuller, Maja Pantic, Pingchuan Ma, Rodrigo Mira, Stavros Petridis","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T23:20:06Z","title":"LiRA: Learning Visual Speech Representations from Audio through Self-supervision"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.09171","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:caf61a47bddc43ff9d079dedc1591286a134f2cc95ac752d62a860f7affb7e79","target":"record","created_at":"2026-07-05T02:50:13Z","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":"db338ca29162ca7dc5cf8f9fb8f404cf4196faef5cc84a2bbe83af695c22cc9f","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-06-16T23:20:06Z","title_canon_sha256":"f49ee7c7d3f7bf2452fea69508b945b5e0c58d4db543bf6dd88c291d82e8e6d1"},"schema_version":"1.0","source":{"id":"2106.09171","kind":"arxiv","version":1}},"canonical_sha256":"5226a0e78ab824e2975c5a8f4aab946db57fd60ca04f4b6e3576b8a500122d24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5226a0e78ab824e2975c5a8f4aab946db57fd60ca04f4b6e3576b8a500122d24","first_computed_at":"2026-07-05T02:50:13.016606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:50:13.016606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nArqiO9UhkBijlF4EyRCcZZjhFqGQJf8V+4qYU7B5b/xlnlI5TwW2XMl6qiaE/nUeHzcg8hx7o7lfPr5I4kfAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:50:13.017081Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.09171","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:caf61a47bddc43ff9d079dedc1591286a134f2cc95ac752d62a860f7affb7e79","sha256:763009737d7e23f3c8440e8a283ef719fc6894f20695e47c36c989742cdae2f3"],"state_sha256":"359c6e56cabe351fef2c3b97278032d2d8061e9e7523453d5de4ef5670ed5f50"}