{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:F7KATXEXKKWDFY3P67PRVVDDWC","short_pith_number":"pith:F7KATXEX","canonical_record":{"source":{"id":"2411.02256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T16:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"8350adae52bd0278efd9833a6a68826d83f10a0d161fb561cfb7cef6c74d3589","abstract_canon_sha256":"cd81b1941f8b08a404083e9c8cfa2846818ddaf9225af8be40bc30cc1518282e"},"schema_version":"1.0"},"canonical_sha256":"2fd409dc9752ac32e36ff7df1ad463b0b43499ce4766fee2458f96b5b39ad578","source":{"kind":"arxiv","id":"2411.02256","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02256","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02256v1","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02256","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"pith_short_12","alias_value":"F7KATXEXKKWD","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"F7KATXEXKKWDFY3P","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"F7KATXEX","created_at":"2026-07-05T09:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:F7KATXEXKKWDFY3P67PRVVDDWC","target":"record","payload":{"canonical_record":{"source":{"id":"2411.02256","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T16:46:53Z","cross_cats_sorted":[],"title_canon_sha256":"8350adae52bd0278efd9833a6a68826d83f10a0d161fb561cfb7cef6c74d3589","abstract_canon_sha256":"cd81b1941f8b08a404083e9c8cfa2846818ddaf9225af8be40bc30cc1518282e"},"schema_version":"1.0"},"canonical_sha256":"2fd409dc9752ac32e36ff7df1ad463b0b43499ce4766fee2458f96b5b39ad578","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:51.128353Z","signature_b64":"Uhm4LMpR7pffBDP7sYJuFAGp3o0lKGkL/7jJawAD6jN+D2QGpSFkszvWjrg76o1pHuD4oEWErMMKYFvnUI1dAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2fd409dc9752ac32e36ff7df1ad463b0b43499ce4766fee2458f96b5b39ad578","last_reissued_at":"2026-07-05T09:30:51.127802Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:51.127802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.02256","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":"2026-07-05T09:30:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MrWxMQsvaOHvlDZPfTV0r3nuA/ChK1m+dls7gkROgWSZw2d0HVxFUptc95/A8sSt3zJ58I4GZEsEhUg4XuqkCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:00:52.627217Z"},"content_sha256":"1781f01b67c400f8c4f2ea6f873fa80df5ff5b9c2a10e0f50efde68e474882eb","schema_version":"1.0","event_id":"sha256:1781f01b67c400f8c4f2ea6f873fa80df5ff5b9c2a10e0f50efde68e474882eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:F7KATXEXKKWDFY3P67PRVVDDWC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alexandros Haliassos, Honglie Chen, Maja Pantic, Rodrigo Mira, Stavros Petridis, Zoe Landgraf","submitted_at":"2024-11-04T16:46:53Z","abstract_excerpt":"Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to yield separate models, leading to disjoint inference pipelines with increased memory requirements and redundancies. This paper proposes unified training strategies for these systems. We demonstrate that training a single model for all three tasks enhances VSR and AVSR performance, overcoming typical optimisation challenges when training from scratch. Moreov"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02256","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/2411.02256/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":"2026-07-05T09:30:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GXYeny/DdUfnvC+ZNvUCEQMtNC/N4DfjLlFHEYZhzH26mDlrZU538xB9qMdkiPidul8Y2QJFiglsx6JFgOw6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:00:52.627614Z"},"content_sha256":"ea60c0f2d3df160205666e42ef3f21fb821bdb924fe7ec0370522b02864d0d3b","schema_version":"1.0","event_id":"sha256:ea60c0f2d3df160205666e42ef3f21fb821bdb924fe7ec0370522b02864d0d3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F7KATXEXKKWDFY3P67PRVVDDWC/bundle.json","state_url":"https://pith.science/pith/F7KATXEXKKWDFY3P67PRVVDDWC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F7KATXEXKKWDFY3P67PRVVDDWC/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":"2026-07-06T19:00:52Z","links":{"resolver":"https://pith.science/pith/F7KATXEXKKWDFY3P67PRVVDDWC","bundle":"https://pith.science/pith/F7KATXEXKKWDFY3P67PRVVDDWC/bundle.json","state":"https://pith.science/pith/F7KATXEXKKWDFY3P67PRVVDDWC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F7KATXEXKKWDFY3P67PRVVDDWC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F7KATXEXKKWDFY3P67PRVVDDWC","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":"cd81b1941f8b08a404083e9c8cfa2846818ddaf9225af8be40bc30cc1518282e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T16:46:53Z","title_canon_sha256":"8350adae52bd0278efd9833a6a68826d83f10a0d161fb561cfb7cef6c74d3589"},"schema_version":"1.0","source":{"id":"2411.02256","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.02256","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"arxiv_version","alias_value":"2411.02256v1","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02256","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"pith_short_12","alias_value":"F7KATXEXKKWD","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"F7KATXEXKKWDFY3P","created_at":"2026-07-05T09:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"F7KATXEX","created_at":"2026-07-05T09:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:ea60c0f2d3df160205666e42ef3f21fb821bdb924fe7ec0370522b02864d0d3b","target":"graph","created_at":"2026-07-05T09:30:51Z","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/2411.02256/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Research in auditory, visual, and audiovisual speech recognition (ASR, VSR, and AVSR, respectively) has traditionally been conducted independently. Even recent self-supervised studies addressing two or all three tasks simultaneously tend to yield separate models, leading to disjoint inference pipelines with increased memory requirements and redundancies. This paper proposes unified training strategies for these systems. We demonstrate that training a single model for all three tasks enhances VSR and AVSR performance, overcoming typical optimisation challenges when training from scratch. Moreov","authors_text":"Alexandros Haliassos, Honglie Chen, Maja Pantic, Rodrigo Mira, Stavros Petridis, Zoe Landgraf","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T16:46:53Z","title":"Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02256","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":"sha256:1781f01b67c400f8c4f2ea6f873fa80df5ff5b9c2a10e0f50efde68e474882eb","target":"record","created_at":"2026-07-05T09:30:51Z","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":"cd81b1941f8b08a404083e9c8cfa2846818ddaf9225af8be40bc30cc1518282e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-04T16:46:53Z","title_canon_sha256":"8350adae52bd0278efd9833a6a68826d83f10a0d161fb561cfb7cef6c74d3589"},"schema_version":"1.0","source":{"id":"2411.02256","kind":"arxiv","version":1}},"canonical_sha256":"2fd409dc9752ac32e36ff7df1ad463b0b43499ce4766fee2458f96b5b39ad578","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fd409dc9752ac32e36ff7df1ad463b0b43499ce4766fee2458f96b5b39ad578","first_computed_at":"2026-07-05T09:30:51.127802Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:30:51.127802Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Uhm4LMpR7pffBDP7sYJuFAGp3o0lKGkL/7jJawAD6jN+D2QGpSFkszvWjrg76o1pHuD4oEWErMMKYFvnUI1dAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:30:51.128353Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.02256","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1781f01b67c400f8c4f2ea6f873fa80df5ff5b9c2a10e0f50efde68e474882eb","sha256:ea60c0f2d3df160205666e42ef3f21fb821bdb924fe7ec0370522b02864d0d3b"],"state_sha256":"21db7253f6105cba944c34eb6d46ee8881929456a7d67d03eab8227914bb1600"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dDrVHs3BstVDiLTZHwc6xgr0vqzFCNkwauBvG7zuS+wcGUJIiQJqrSUixkxDxX7Koo7E4Co2uritOKwDByI6CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:00:52.629572Z","bundle_sha256":"6ed738775b409cd27020b946812a967a105af47a542b62b724eb1a5b47eb7dce"}}