{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:V3DADB3BLYHJCPVFLRWEDSP2EN","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":"d4882c2893dfa22999f26024fc289ddfce2451335575d00fc3264be452d1bbbf","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:52:13Z","title_canon_sha256":"2d8c46f4a631ecfe3d919f9545a7571d9e895de52ad110f3a60faa9bb7341995"},"schema_version":"1.0","source":{"id":"2203.03598","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.03598","created_at":"2026-07-05T04:11:11Z"},{"alias_kind":"arxiv_version","alias_value":"2203.03598v2","created_at":"2026-07-05T04:11:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.03598","created_at":"2026-07-05T04:11:11Z"},{"alias_kind":"pith_short_12","alias_value":"V3DADB3BLYHJ","created_at":"2026-07-05T04:11:11Z"},{"alias_kind":"pith_short_16","alias_value":"V3DADB3BLYHJCPVF","created_at":"2026-07-05T04:11:11Z"},{"alias_kind":"pith_short_8","alias_value":"V3DADB3B","created_at":"2026-07-05T04:11:11Z"}],"graph_snapshots":[{"event_id":"sha256:ff1da57d2261f63f77e6c1b4dd8fa56170c12d0ef2ab34e4dd578254bb4d3b70","target":"graph","created_at":"2026-07-05T04:11:11Z","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/2203.03598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to classify video data from classes not included in the training data, i.e. video-based zero-shot learning, is challenging. We conjecture that the natural alignment between the audio and visual modalities in video data provides a rich training signal for learning discriminative multi-modal representations. Focusing on the relatively underexplored task of audio-visual zero-shot learning, we propose to learn multi-modal representations from audio-visual data using cross-modal attention and exploit textual label embeddings for transferring knowledge from seen classes to unseen classes. T","authors_text":"A. Sophia Koepke, Lukas Riesch, Otniel-Bogdan Mercea, Zeynep Akata","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:52:13Z","title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03598","kind":"arxiv","version":2},"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":"sha256:73625f01fe7c38b7793e96c965580d88f69cc7f075cb0e4f07dddebe1ebd6e56","target":"record","created_at":"2026-07-05T04:11:11Z","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":"d4882c2893dfa22999f26024fc289ddfce2451335575d00fc3264be452d1bbbf","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:52:13Z","title_canon_sha256":"2d8c46f4a631ecfe3d919f9545a7571d9e895de52ad110f3a60faa9bb7341995"},"schema_version":"1.0","source":{"id":"2203.03598","kind":"arxiv","version":2}},"canonical_sha256":"aec60187615e0e913ea55c6c41c9fa236e9fe672eaa42dd319a92b24ffe21b4f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aec60187615e0e913ea55c6c41c9fa236e9fe672eaa42dd319a92b24ffe21b4f","first_computed_at":"2026-07-05T04:11:11.761499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:11.761499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ax8MDAwXDkeWKWwew5ScrqGj61E6y4v3V142dILrqwbg/wQC+yF0jAoprtZWHJBtFboAJ3vAbgpCEW7S8rPAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:11.761894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.03598","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73625f01fe7c38b7793e96c965580d88f69cc7f075cb0e4f07dddebe1ebd6e56","sha256:ff1da57d2261f63f77e6c1b4dd8fa56170c12d0ef2ab34e4dd578254bb4d3b70"],"state_sha256":"08cefaf3090462333b2ce28516e2dde4941fb15e51454f09ab79b954c38d007c"}