{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WJBFEZQDNQD64O3ZZR6VS77VDD","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":"7ff7dd8e08780647ff2a5b8233563373d43f4296d6adbd0e937448fcf6916830","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T03:07:34Z","title_canon_sha256":"194b7fbf60503ab691381e5aee33726906c506eb84132ca987ebedd562b447aa"},"schema_version":"1.0","source":{"id":"2606.26556","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.26556","created_at":"2026-06-26T01:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.26556v1","created_at":"2026-06-26T01:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26556","created_at":"2026-06-26T01:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"WJBFEZQDNQD6","created_at":"2026-06-26T01:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"WJBFEZQDNQD64O3Z","created_at":"2026-06-26T01:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"WJBFEZQD","created_at":"2026-06-26T01:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:dc12c0c88559d731dfcc9992314db5bcbaca5f9ce7d764eb9b1b6e5b3b54efbe","target":"graph","created_at":"2026-06-26T01:15:34Z","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/2606.26556/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While pre-trained models excel in specialized tasks, learning universal representations across diverse acoustic domains remains challenging. To address this, we propose WQ-Fusion, a robust dual-encoder framework for cross-domain audio representation learning. Overcoming the limitations of static concatenation, WQ-Fusion integrates whisper and qwen via an Adaptive Feature Modulation module and a novel element-wise gated attention mechanism. This design enables dynamic feature selection, allowing the model to selectively emphasize relevant acoustic and semantic dimensions. Extensive experiments ","authors_text":"Gongping Huang, Hanchen Pei, Hao Zhang, Jacob Benesty, Jingdong Chen, Lei Ding, Mingda Lin, Tiantian Xiong, Xinyue Zhou","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T03:07:34Z","title":"WQ-Fusion: Dynamic Gated Attention for Cross-Domain Audio Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26556","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":"sha256:66b9db2cce80a3dac768e68fd41c62af1de9f1fd4cd9b4598c681c46a4cb2743","target":"record","created_at":"2026-06-26T01:15:34Z","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":"7ff7dd8e08780647ff2a5b8233563373d43f4296d6adbd0e937448fcf6916830","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-06-25T03:07:34Z","title_canon_sha256":"194b7fbf60503ab691381e5aee33726906c506eb84132ca987ebedd562b447aa"},"schema_version":"1.0","source":{"id":"2606.26556","kind":"arxiv","version":1}},"canonical_sha256":"b2425266036c07ee3b79cc7d597ff518f7f87b126dd5ed1f79c5588c0e8c5d43","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2425266036c07ee3b79cc7d597ff518f7f87b126dd5ed1f79c5588c0e8c5d43","first_computed_at":"2026-06-26T01:15:34.530712Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-26T01:15:34.530712Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JRHd7io3+6bcCUuiscxIF2v0zwn8VeWTGRDNgcWZ6gHFbG+bcSJEVZPegN10DurnRUiCCNDAe+QHuuGfmkG/Dw==","signature_status":"signed_v1","signed_at":"2026-06-26T01:15:34.531134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.26556","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66b9db2cce80a3dac768e68fd41c62af1de9f1fd4cd9b4598c681c46a4cb2743","sha256:dc12c0c88559d731dfcc9992314db5bcbaca5f9ce7d764eb9b1b6e5b3b54efbe"],"state_sha256":"399174de1b70deeeb5e29290261ac577ed9fab4f8e9068d9ba0004b047840328"}