{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:V3DADB3BLYHJCPVFLRWEDSP2EN","short_pith_number":"pith:V3DADB3B","canonical_record":{"source":{"id":"2203.03598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:52:13Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"2d8c46f4a631ecfe3d919f9545a7571d9e895de52ad110f3a60faa9bb7341995","abstract_canon_sha256":"d4882c2893dfa22999f26024fc289ddfce2451335575d00fc3264be452d1bbbf"},"schema_version":"1.0"},"canonical_sha256":"aec60187615e0e913ea55c6c41c9fa236e9fe672eaa42dd319a92b24ffe21b4f","source":{"kind":"arxiv","id":"2203.03598","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:V3DADB3BLYHJCPVFLRWEDSP2EN","target":"record","payload":{"canonical_record":{"source":{"id":"2203.03598","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-03-07T18:52:13Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"2d8c46f4a631ecfe3d919f9545a7571d9e895de52ad110f3a60faa9bb7341995","abstract_canon_sha256":"d4882c2893dfa22999f26024fc289ddfce2451335575d00fc3264be452d1bbbf"},"schema_version":"1.0"},"canonical_sha256":"aec60187615e0e913ea55c6c41c9fa236e9fe672eaa42dd319a92b24ffe21b4f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:11.761894Z","signature_b64":"9ax8MDAwXDkeWKWwew5ScrqGj61E6y4v3V142dILrqwbg/wQC+yF0jAoprtZWHJBtFboAJ3vAbgpCEW7S8rPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aec60187615e0e913ea55c6c41c9fa236e9fe672eaa42dd319a92b24ffe21b4f","last_reissued_at":"2026-07-05T04:11:11.761499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:11.761499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.03598","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:11:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rxzCxYDITPhL5/uc5peL7VH7CcHLMfmnVDAghLTSBosdoXXa+JwQPZ+6qQULCDPGaWGhpLJKW3BvS1gkFSItBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T06:32:51.456564Z"},"content_sha256":"73625f01fe7c38b7793e96c965580d88f69cc7f075cb0e4f07dddebe1ebd6e56","schema_version":"1.0","event_id":"sha256:73625f01fe7c38b7793e96c965580d88f69cc7f075cb0e4f07dddebe1ebd6e56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:V3DADB3BLYHJCPVFLRWEDSP2EN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Audio-visual Generalised Zero-shot Learning with Cross-modal Attention and Language","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.CV","authors_text":"A. Sophia Koepke, Lukas Riesch, Otniel-Bogdan Mercea, Zeynep Akata","submitted_at":"2022-03-07T18:52:13Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.03598","kind":"arxiv","version":2},"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/2203.03598/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":"2026-07-05T04:11:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PAvoFNwQacl4DY0RZ8C9l2SaKslu3KoKDcje8xnAVfAPM5fOHK4UBZ+RNKVNnXW+4QvlcGuO9kfAswANnWfIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T06:32:51.456937Z"},"content_sha256":"ff1da57d2261f63f77e6c1b4dd8fa56170c12d0ef2ab34e4dd578254bb4d3b70","schema_version":"1.0","event_id":"sha256:ff1da57d2261f63f77e6c1b4dd8fa56170c12d0ef2ab34e4dd578254bb4d3b70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V3DADB3BLYHJCPVFLRWEDSP2EN/bundle.json","state_url":"https://pith.science/pith/V3DADB3BLYHJCPVFLRWEDSP2EN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V3DADB3BLYHJCPVFLRWEDSP2EN/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":"2026-07-13T06:32:51Z","links":{"resolver":"https://pith.science/pith/V3DADB3BLYHJCPVFLRWEDSP2EN","bundle":"https://pith.science/pith/V3DADB3BLYHJCPVFLRWEDSP2EN/bundle.json","state":"https://pith.science/pith/V3DADB3BLYHJCPVFLRWEDSP2EN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V3DADB3BLYHJCPVFLRWEDSP2EN/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xxIU/BPsE4mUTOttq01LpOO6nGO6dB48sM+yFUUcnrBkLZUmQ6EMuDR+0i+jSNvMkA/ctDQShLQI4lEkacz+Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T06:32:51.459111Z","bundle_sha256":"74be885497aa7acf2515c291d8798e5150a76b7a443de50724ba11bd67b57c9d"}}