{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6VDTYCEUZ6V35LVF7XFW55KNSC","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":"43bbd3d126a1464eb8491789a17fe254a734ae2e800ead619fd1d99b5fe0fa63","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T15:00:43Z","title_canon_sha256":"92c4c8420897dc512e2915f3ceb0f7316144a3239ab612b46e9ba5329e07f9b2"},"schema_version":"1.0","source":{"id":"2406.17614","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.17614","created_at":"2026-07-05T08:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"2406.17614v1","created_at":"2026-07-05T08:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.17614","created_at":"2026-07-05T08:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"6VDTYCEUZ6V3","created_at":"2026-07-05T08:36:37Z"},{"alias_kind":"pith_short_16","alias_value":"6VDTYCEUZ6V35LVF","created_at":"2026-07-05T08:36:37Z"},{"alias_kind":"pith_short_8","alias_value":"6VDTYCEU","created_at":"2026-07-05T08:36:37Z"}],"graph_snapshots":[{"event_id":"sha256:5e05383c656365a142b0e2dbef9650f7ba0c53acc331406022379f3de6f6475c","target":"graph","created_at":"2026-07-05T08:36:37Z","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/2406.17614/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained models have been a foundational approach in speech recognition, albeit with associated additional costs. In this study, we propose a regularization technique that facilitates the training of visual and audio-visual speech recognition models (VSR and AVSR) from scratch. This approach, abbreviated as \\textbf{MSRS} (Multimodal Speech Recognition from Scratch), introduces a sparse regularization that rapidly learns sparse structures within the dense model at the very beginning of training, which receives healthier gradient flow than the dense equivalent. Once the sparse mask stabilizes","authors_text":"Adriana Fernandez-Lopez, Honglie Chen, Lu Yin, Maja Pantic, Pingchuan Ma, Qiao Xiao, Shiwei Liu, Stavros Petridis","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T15:00:43Z","title":"MSRS: Training Multimodal Speech Recognition Models from Scratch with Sparse Mask Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.17614","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":"sha256:320000f9345032b6d21642c83ea5d11f610909ab5885edd7845c0ae39af115c8","target":"record","created_at":"2026-07-05T08:36:37Z","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":"43bbd3d126a1464eb8491789a17fe254a734ae2e800ead619fd1d99b5fe0fa63","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-25T15:00:43Z","title_canon_sha256":"92c4c8420897dc512e2915f3ceb0f7316144a3239ab612b46e9ba5329e07f9b2"},"schema_version":"1.0","source":{"id":"2406.17614","kind":"arxiv","version":1}},"canonical_sha256":"f5473c0894cfabbeaea5fdcb6ef54d908bf12dff8217e672f049b78240ed6b4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5473c0894cfabbeaea5fdcb6ef54d908bf12dff8217e672f049b78240ed6b4d","first_computed_at":"2026-07-05T08:36:37.817384Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:37.817384Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JHUhiKMMLtGAZum9KX92UITJ87AVEa+juP1VAa74r6l2s0iPbHycgJs54Y86AiCLFeDvSN0k4hZXYItD+HhkBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:37.817878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.17614","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:320000f9345032b6d21642c83ea5d11f610909ab5885edd7845c0ae39af115c8","sha256:5e05383c656365a142b0e2dbef9650f7ba0c53acc331406022379f3de6f6475c"],"state_sha256":"53ffa7ef96cc30073385b17f322f05ba7ba4505612fb48c3edbfbbb002a95df8"}