{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VBSHIDIP35YWV6UN7IBVMA2LPO","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":"e7f307787caaeb836e1ae5f445e907dd6518bff74fce03f357c4cbbd670f4cc0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T08:55:48Z","title_canon_sha256":"b0b847191250c7300ca14ba5933ad2caecafe3f251e4c5ca662c26847d7e775b"},"schema_version":"1.0","source":{"id":"2310.16477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16477","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16477v1","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16477","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_12","alias_value":"VBSHIDIP35YW","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_16","alias_value":"VBSHIDIP35YWV6UN","created_at":"2026-07-05T07:04:58Z"},{"alias_kind":"pith_short_8","alias_value":"VBSHIDIP","created_at":"2026-07-05T07:04:58Z"}],"graph_snapshots":[{"event_id":"sha256:763863f49406973415f5f703ebc293c418c9d971e71c99c63c6372c5fdcacba8","target":"graph","created_at":"2026-07-05T07:04:58Z","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/2310.16477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Auditory and visual signals usually present together and correlate with each other, not only in natural environments but also in clinical settings. However, the audio-visual modelling in the latter case can be more challenging, due to the different sources of audio/video signals and the noise (both signal-level and semantic-level) in auditory signals -- usually speech. In this paper, we consider audio-visual modelling in a clinical setting, providing a solution to learn medical representations that benefit various clinical tasks, without human expert annotation. A simple yet effective multi-mo","authors_text":"Andrew Zisserman, Aris T. Papageorghiou, J. Alison Noble, Jianbo Jiao, Lior Drukker, Mohammad Alsharid","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T08:55:48Z","title":"Show from Tell: Audio-Visual Modelling in Clinical Settings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16477","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":"sha256:6285a6437ce6677425f27d37cddb4ed37f69be252a01f791c384e2632e9f5075","target":"record","created_at":"2026-07-05T07:04:58Z","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":"e7f307787caaeb836e1ae5f445e907dd6518bff74fce03f357c4cbbd670f4cc0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-10-25T08:55:48Z","title_canon_sha256":"b0b847191250c7300ca14ba5933ad2caecafe3f251e4c5ca662c26847d7e775b"},"schema_version":"1.0","source":{"id":"2310.16477","kind":"arxiv","version":1}},"canonical_sha256":"a864740d0fdf716afa8dfa0356034b7b9437e7041657b54a174b4907d0dc0c19","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a864740d0fdf716afa8dfa0356034b7b9437e7041657b54a174b4907d0dc0c19","first_computed_at":"2026-07-05T07:04:58.039905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:58.039905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IckoN1Adf8ivNYzUFw3XTAZ3kw7G4+KxhMOxflnTu/rAet6jvRyei+zgcApRJQxdthzSYUHEpObzJoqDsr4DDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:58.040383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6285a6437ce6677425f27d37cddb4ed37f69be252a01f791c384e2632e9f5075","sha256:763863f49406973415f5f703ebc293c418c9d971e71c99c63c6372c5fdcacba8"],"state_sha256":"4bc2604daaf9bf30d619d2761ec0556de0ccf436bcf7d711e6bd5b5e395980eb"}