{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:YCEO4UEAIN27HSK57UMW65T7NP","short_pith_number":"pith:YCEO4UEA","schema_version":"1.0","canonical_sha256":"c088ee50804375f3c95dfd196f767f6bf08a93ee950e4f58b28215c1b710f87d","source":{"kind":"arxiv","id":"2412.11715","version":1},"attestation_state":"computed","paper":{"title":"Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aiwen Sun, Mengren Zheng, RunLin Yu, Wenrui Li, Yipu Gong","submitted_at":"2024-12-16T12:35:56Z","abstract_excerpt":"Audio-visual Zero-Shot Learning (ZSL) has attracted significant attention for its ability to identify unseen classes and perform well in video classification tasks. However, modal imbalance in (G)ZSL leads to over-reliance on the optimal modality, reducing discriminative capabilities for unseen classes. Some studies have attempted to address this issue by modifying parameter gradients, but two challenges still remain: (a) Quality discrepancies, where modalities offer differing quantities and qualities of information for the same concept. (b) Content discrepancies, where sample contributions wi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2412.11715","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T12:35:56Z","cross_cats_sorted":["cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"d5337ef5b6d528a4769a3dc587d90701b334d1d4bac40a54b9eb0b0bab45141c","abstract_canon_sha256":"df831b7d5c6c939006b28c04fd6c5a015e4701955efa27ad4c800262da92a6d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:49:50.620411Z","signature_b64":"W++PAnKGaIrD4xS52f+DsXbWNijBySdFg1JdWVJRIlz3e8get4W+ACl2DDCzeIgScinVFw7EEjwrM1gppVFfCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c088ee50804375f3c95dfd196f767f6bf08a93ee950e4f58b28215c1b710f87d","last_reissued_at":"2026-07-05T09:49:50.619890Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:49:50.619890Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discrepancy-Aware Attention Network for Enhanced Audio-Visual Zero-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aiwen Sun, Mengren Zheng, RunLin Yu, Wenrui Li, Yipu Gong","submitted_at":"2024-12-16T12:35:56Z","abstract_excerpt":"Audio-visual Zero-Shot Learning (ZSL) has attracted significant attention for its ability to identify unseen classes and perform well in video classification tasks. However, modal imbalance in (G)ZSL leads to over-reliance on the optimal modality, reducing discriminative capabilities for unseen classes. Some studies have attempted to address this issue by modifying parameter gradients, but two challenges still remain: (a) Quality discrepancies, where modalities offer differing quantities and qualities of information for the same concept. (b) Content discrepancies, where sample contributions wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11715","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/2412.11715/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2412.11715","created_at":"2026-07-05T09:49:50.619950+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.11715v1","created_at":"2026-07-05T09:49:50.619950+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11715","created_at":"2026-07-05T09:49:50.619950+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCEO4UEAIN27","created_at":"2026-07-05T09:49:50.619950+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCEO4UEAIN27HSK5","created_at":"2026-07-05T09:49:50.619950+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCEO4UEA","created_at":"2026-07-05T09:49:50.619950+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP","json":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP.json","graph_json":"https://pith.science/api/pith-number/YCEO4UEAIN27HSK57UMW65T7NP/graph.json","events_json":"https://pith.science/api/pith-number/YCEO4UEAIN27HSK57UMW65T7NP/events.json","paper":"https://pith.science/paper/YCEO4UEA"},"agent_actions":{"view_html":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP","download_json":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP.json","view_paper":"https://pith.science/paper/YCEO4UEA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.11715&json=true","fetch_graph":"https://pith.science/api/pith-number/YCEO4UEAIN27HSK57UMW65T7NP/graph.json","fetch_events":"https://pith.science/api/pith-number/YCEO4UEAIN27HSK57UMW65T7NP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP/action/storage_attestation","attest_author":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP/action/author_attestation","sign_citation":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP/action/citation_signature","submit_replication":"https://pith.science/pith/YCEO4UEAIN27HSK57UMW65T7NP/action/replication_record"}},"created_at":"2026-07-05T09:49:50.619950+00:00","updated_at":"2026-07-05T09:49:50.619950+00:00"}