{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4FQXNLIV6QCDMHPCU2LDVON4LL","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":"a118e201316b6914278956e13b456f66fdde2a3cb3a84430e752674ab53ecbb0","cross_cats_sorted":["cs.SD","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-11-08T21:26:17Z","title_canon_sha256":"9b3df93cc9552e6d45ad86594c2a8135541ec8ef8ccff1ef1f91a8cb48a069f4"},"schema_version":"1.0","source":{"id":"2011.04084","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.04084","created_at":"2026-07-05T01:50:02Z"},{"alias_kind":"arxiv_version","alias_value":"2011.04084v1","created_at":"2026-07-05T01:50:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.04084","created_at":"2026-07-05T01:50:02Z"},{"alias_kind":"pith_short_12","alias_value":"4FQXNLIV6QCD","created_at":"2026-07-05T01:50:02Z"},{"alias_kind":"pith_short_16","alias_value":"4FQXNLIV6QCDMHPC","created_at":"2026-07-05T01:50:02Z"},{"alias_kind":"pith_short_8","alias_value":"4FQXNLIV","created_at":"2026-07-05T01:50:02Z"}],"graph_snapshots":[{"event_id":"sha256:fa67dcfae5120a437ebae6c22d6f9bb3484d81d19cd83c1527e6c9719d5ba049","target":"graph","created_at":"2026-07-05T01:50:02Z","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/2011.04084/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we try to address the problem of leveraging visual signals to improve Automatic Speech Recognition (ASR), also known as visual context-aware ASR (VC-ASR). We explore novel VC-ASR approaches to leverage video and text representations extracted by a self-supervised pre-trained text-video embedding model. Firstly, we propose a multi-stream attention architecture to leverage signals from both audio and video modalities. This architecture consists of separate encoders for the two modalities and a single decoder that attends over them. We show that this architecture is better than fus","authors_text":"Jinyu Li, Shahram Ghorbani, Yashesh Gaur, Yu Shi","cross_cats":["cs.SD","eess.IV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-11-08T21:26:17Z","title":"Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04084","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:e5f1a961f1483478175788a0afe17f8d6e0d0db4b7413460520878c2bece0382","target":"record","created_at":"2026-07-05T01:50:02Z","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":"a118e201316b6914278956e13b456f66fdde2a3cb3a84430e752674ab53ecbb0","cross_cats_sorted":["cs.SD","eess.IV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-11-08T21:26:17Z","title_canon_sha256":"9b3df93cc9552e6d45ad86594c2a8135541ec8ef8ccff1ef1f91a8cb48a069f4"},"schema_version":"1.0","source":{"id":"2011.04084","kind":"arxiv","version":1}},"canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","first_computed_at":"2026-07-05T01:50:02.230478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:50:02.230478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fGnA9tfGrCi+qPprjU8yhFANO7cZvXrIhchO8gxEC0L6rR3WP/QsP1+dm5v9MA9+HYi16rG2YwVG+FGVC4VWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:50:02.230858Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.04084","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5f1a961f1483478175788a0afe17f8d6e0d0db4b7413460520878c2bece0382","sha256:fa67dcfae5120a437ebae6c22d6f9bb3484d81d19cd83c1527e6c9719d5ba049"],"state_sha256":"22c54e464279c228ef6541fb8edcfa147d8007ad8d9187b9200672d57d14665a"}