{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:S3BIREVG5ODZQWHVIL5EAWQWOQ","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":"b4af3d290ac73db7ca9fe1793532839b6864a42a2eee7a0211ab7b7981ae370e","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-09T05:24:20Z","title_canon_sha256":"d85d248e23edc761cafe53bd58e6b2fcb624e1a255417faac3b6c753d77d5988"},"schema_version":"1.0","source":{"id":"2311.05152","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.05152","created_at":"2026-07-05T07:26:41Z"},{"alias_kind":"arxiv_version","alias_value":"2311.05152v2","created_at":"2026-07-05T07:26:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.05152","created_at":"2026-07-05T07:26:41Z"},{"alias_kind":"pith_short_12","alias_value":"S3BIREVG5ODZ","created_at":"2026-07-05T07:26:41Z"},{"alias_kind":"pith_short_16","alias_value":"S3BIREVG5ODZQWHV","created_at":"2026-07-05T07:26:41Z"},{"alias_kind":"pith_short_8","alias_value":"S3BIREVG","created_at":"2026-07-05T07:26:41Z"}],"graph_snapshots":[{"event_id":"sha256:9f350aeba64c06bde15ff5ca920527fd00030dd5e60ba0531621e634bad17970","target":"graph","created_at":"2026-07-05T07:26:41Z","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/2311.05152/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the deployment of large-scale pre-trained models in audio-visual downstream tasks has yielded remarkable outcomes. However, these models, primarily trained on single-modality unconstrained datasets, still encounter challenges in feature extraction for multi-modal tasks, leading to suboptimal performance. This limitation arises due to the introduction of irrelevant modality-specific information during encoding, which adversely affects the performance of downstream tasks. To address this challenge, this paper proposes a novel Dual-Guided Spatial-Channel-Temporal (DG-SCT) attenti","authors_text":"Haoyi Duan, Jieming Zhu, Li Tang, Mingze Zhou, Yan Xia, Zhou Zhao","cross_cats":["cs.AI","cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-09T05:24:20Z","title":"Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.05152","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":"sha256:11ae0743a88bd0adbbff36e2eb97520466341335f048bf3b35613fd5a58d6704","target":"record","created_at":"2026-07-05T07:26:41Z","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":"b4af3d290ac73db7ca9fe1793532839b6864a42a2eee7a0211ab7b7981ae370e","cross_cats_sorted":["cs.AI","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-09T05:24:20Z","title_canon_sha256":"d85d248e23edc761cafe53bd58e6b2fcb624e1a255417faac3b6c753d77d5988"},"schema_version":"1.0","source":{"id":"2311.05152","kind":"arxiv","version":2}},"canonical_sha256":"96c28892a6eb879858f542fa405a16740092f9d6c3fea1e72057c5b3e7b6a7d3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"96c28892a6eb879858f542fa405a16740092f9d6c3fea1e72057c5b3e7b6a7d3","first_computed_at":"2026-07-05T07:26:41.132403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:41.132403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j7YSiHo3mJazI68GRp+2NanLlVkc+6Kfc/joX7lgGElFMC7gQptRKb7xI6almfTYNb/oWdA9oyc43iHp594NAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:41.132874Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.05152","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ae0743a88bd0adbbff36e2eb97520466341335f048bf3b35613fd5a58d6704","sha256:9f350aeba64c06bde15ff5ca920527fd00030dd5e60ba0531621e634bad17970"],"state_sha256":"6fad33775de280b4a49c0e957c0da6c9f1e70ead3fee8271aee4ce11ea907b7c"}