{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TQ53QLXTCD62KPIC2YA5YUUNK5","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":"e20214ee71b8465fcdd3a92020595a7ad17617f84dec6a8ba766366b5ec43e25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T15:19:30Z","title_canon_sha256":"f2fdc378fbb9c2943ccfc4a373d4f51f3491c82a62bb0d8b14cdfe8ace8efa46"},"schema_version":"1.0","source":{"id":"2207.09966","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.09966","created_at":"2026-07-05T04:42:09Z"},{"alias_kind":"arxiv_version","alias_value":"2207.09966v1","created_at":"2026-07-05T04:42:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.09966","created_at":"2026-07-05T04:42:09Z"},{"alias_kind":"pith_short_12","alias_value":"TQ53QLXTCD62","created_at":"2026-07-05T04:42:09Z"},{"alias_kind":"pith_short_16","alias_value":"TQ53QLXTCD62KPIC","created_at":"2026-07-05T04:42:09Z"},{"alias_kind":"pith_short_8","alias_value":"TQ53QLXT","created_at":"2026-07-05T04:42:09Z"}],"graph_snapshots":[{"event_id":"sha256:bcfa6b54f650ebe701395ed19ea33cd7351894a1420570c63345abf027fc8e6d","target":"graph","created_at":"2026-07-05T04:42:09Z","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/2207.09966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio-visual generalised zero-shot learning for video classification requires understanding the relations between the audio and visual information in order to be able to recognise samples from novel, previously unseen classes at test time. The natural semantic and temporal alignment between audio and visual data in video data can be exploited to learn powerful representations that generalise to unseen classes at test time. We propose a multi-modal and Temporal Cross-attention Framework (\\modelName) for audio-visual generalised zero-shot learning. Its inputs are temporally aligned audio and vis","authors_text":"A. Sophia Koepke, Otniel-Bogdan Mercea, Thomas Hummel, Zeynep Akata","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T15:19:30Z","title":"Temporal and cross-modal attention for audio-visual zero-shot learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.09966","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":"sha256:53482002173d0161aea647fdd5e3dd98923510328b281b2f962ebc3bbf26359b","target":"record","created_at":"2026-07-05T04:42:09Z","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":"e20214ee71b8465fcdd3a92020595a7ad17617f84dec6a8ba766366b5ec43e25","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-07-20T15:19:30Z","title_canon_sha256":"f2fdc378fbb9c2943ccfc4a373d4f51f3491c82a62bb0d8b14cdfe8ace8efa46"},"schema_version":"1.0","source":{"id":"2207.09966","kind":"arxiv","version":1}},"canonical_sha256":"9c3bb82ef310fda53d02d601dc528d5768975f26ccce65e8090e94641d0dd55c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9c3bb82ef310fda53d02d601dc528d5768975f26ccce65e8090e94641d0dd55c","first_computed_at":"2026-07-05T04:42:09.900835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:42:09.900835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vyPWLC5GHP8zmEi9HjfOm19PgzkqgaCMm3E/4fvBPdvPUlzwJgbOqlCYEtmJ8U1MtqUVvMMg/fgfg2J+J5odDA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:42:09.901264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.09966","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53482002173d0161aea647fdd5e3dd98923510328b281b2f962ebc3bbf26359b","sha256:bcfa6b54f650ebe701395ed19ea33cd7351894a1420570c63345abf027fc8e6d"],"state_sha256":"6a9d03aaf6feb9f770f02573e0655e7bd1674ecb8250c4da70491d81127c6567"}