{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4FQXNLIV6QCDMHPCU2LDVON4LL","short_pith_number":"pith:4FQXNLIV","canonical_record":{"source":{"id":"2011.04084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-11-08T21:26:17Z","cross_cats_sorted":["cs.SD","eess.IV"],"title_canon_sha256":"9b3df93cc9552e6d45ad86594c2a8135541ec8ef8ccff1ef1f91a8cb48a069f4","abstract_canon_sha256":"a118e201316b6914278956e13b456f66fdde2a3cb3a84430e752674ab53ecbb0"},"schema_version":"1.0"},"canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","source":{"kind":"arxiv","id":"2011.04084","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4FQXNLIV6QCDMHPCU2LDVON4LL","target":"record","payload":{"canonical_record":{"source":{"id":"2011.04084","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2020-11-08T21:26:17Z","cross_cats_sorted":["cs.SD","eess.IV"],"title_canon_sha256":"9b3df93cc9552e6d45ad86594c2a8135541ec8ef8ccff1ef1f91a8cb48a069f4","abstract_canon_sha256":"a118e201316b6914278956e13b456f66fdde2a3cb3a84430e752674ab53ecbb0"},"schema_version":"1.0"},"canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:50:02.230858Z","signature_b64":"fGnA9tfGrCi+qPprjU8yhFANO7cZvXrIhchO8gxEC0L6rR3WP/QsP1+dm5v9MA9+HYi16rG2YwVG+FGVC4VWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e16176ad15f404361de2a6963ab9bc5aed91c40cf5f495cef532725e72234c17","last_reissued_at":"2026-07-05T01:50:02.230478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:50:02.230478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.04084","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ugv/hhYgu5/Z99/P+Qf/An//1ui/aWzJqvvVbVyNIpbDs2RUm1xpEWQUPF8kRQ/57jD8akkrA+ScMxpItPSABA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:59:55.871321Z"},"content_sha256":"e5f1a961f1483478175788a0afe17f8d6e0d0db4b7413460520878c2bece0382","schema_version":"1.0","event_id":"sha256:e5f1a961f1483478175788a0afe17f8d6e0d0db4b7413460520878c2bece0382"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4FQXNLIV6QCDMHPCU2LDVON4LL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Listen, Look and Deliberate: Visual context-aware speech recognition using pre-trained text-video representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.IV"],"primary_cat":"eess.AS","authors_text":"Jinyu Li, Shahram Ghorbani, Yashesh Gaur, Yu Shi","submitted_at":"2020-11-08T21:26:17Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.04084","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2011.04084/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:50:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uWcahQva2H6mJE+1AUWua6X82jTZGnjYblmpBgB3O7m5CGrQENYSYTw6jQbymd6JAXMEaIcbh7hF99s1AQ6ZAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T21:59:55.871937Z"},"content_sha256":"fa67dcfae5120a437ebae6c22d6f9bb3484d81d19cd83c1527e6c9719d5ba049","schema_version":"1.0","event_id":"sha256:fa67dcfae5120a437ebae6c22d6f9bb3484d81d19cd83c1527e6c9719d5ba049"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/bundle.json","state_url":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T21:59:55Z","links":{"resolver":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL","bundle":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/bundle.json","state":"https://pith.science/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FQXNLIV6QCDMHPCU2LDVON4LL/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LNW88kM6CpWYTZkDH0FZRUI0gZzbuDrjJwfs1bKAmfF9cu8QTy2LSj6z0dy/vW+Du1fcSbZBX64TzN6TxOxSAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T21:59:55.876723Z","bundle_sha256":"e0f1854efa4195a4578b71b920d112740a715e3a455197abbd167c47f92c12ed"}}