{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VENOWBATEV4XQ4LZFE4GFZV3JV","short_pith_number":"pith:VENOWBAT","schema_version":"1.0","canonical_sha256":"a91aeb04132579787179293862e6bb4d6811c068b2b32ddd948261769cfb0d40","source":{"kind":"arxiv","id":"2305.17834","version":3},"attestation_state":"computed","paper":{"title":"Streaming Audio Transformers for Online Audio Tagging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2023-05-29T00:32:11Z","abstract_excerpt":"Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory usage, slow inference speed, and considerable model delay, rendering them impractical for real-world AT applications. In this study, we introduce streaming audio transformers (SAT) that combine the vision transformer (ViT) architecture with Transformer-Xl-like chunk processing, enabling efficient processing of long-range audio signals. Our proposed SAT is be"},"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":"2305.17834","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-05-29T00:32:11Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"74ac1dafe56b8115e6e84da727ddce0e9405e88c5ed79c5e53f9fb45c0b93121","abstract_canon_sha256":"f4327ea71288ee750bfdbbe7d3a1201be62290bbd531e5fe5728ee27195a42b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:15.511104Z","signature_b64":"s2LMxJT7WJKUDRkssLI42GkECGUsXkkzVuAmX218bzKYOJofaSO+Elbo0TZ4N0UfSqXUUhaEQs4aC5X5v5RtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a91aeb04132579787179293862e6bb4d6811c068b2b32ddd948261769cfb0d40","last_reissued_at":"2026-07-05T08:29:15.510418Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:15.510418Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Audio Transformers for Online Audio Tagging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Bin Wang, Heinrich Dinkel, Junbo Zhang, Yongqing Wang, Yujun Wang, Zhiyong Yan","submitted_at":"2023-05-29T00:32:11Z","abstract_excerpt":"Transformers have emerged as a prominent model framework for audio tagging (AT), boasting state-of-the-art (SOTA) performance on the widely-used Audioset dataset. However, their impressive performance often comes at the cost of high memory usage, slow inference speed, and considerable model delay, rendering them impractical for real-world AT applications. In this study, we introduce streaming audio transformers (SAT) that combine the vision transformer (ViT) architecture with Transformer-Xl-like chunk processing, enabling efficient processing of long-range audio signals. Our proposed SAT is be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17834","kind":"arxiv","version":3},"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/2305.17834/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":"2305.17834","created_at":"2026-07-05T08:29:15.510551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17834v3","created_at":"2026-07-05T08:29:15.510551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17834","created_at":"2026-07-05T08:29:15.510551+00:00"},{"alias_kind":"pith_short_12","alias_value":"VENOWBATEV4X","created_at":"2026-07-05T08:29:15.510551+00:00"},{"alias_kind":"pith_short_16","alias_value":"VENOWBATEV4XQ4LZ","created_at":"2026-07-05T08:29:15.510551+00:00"},{"alias_kind":"pith_short_8","alias_value":"VENOWBAT","created_at":"2026-07-05T08:29:15.510551+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/VENOWBATEV4XQ4LZFE4GFZV3JV","json":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV.json","graph_json":"https://pith.science/api/pith-number/VENOWBATEV4XQ4LZFE4GFZV3JV/graph.json","events_json":"https://pith.science/api/pith-number/VENOWBATEV4XQ4LZFE4GFZV3JV/events.json","paper":"https://pith.science/paper/VENOWBAT"},"agent_actions":{"view_html":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV","download_json":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV.json","view_paper":"https://pith.science/paper/VENOWBAT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17834&json=true","fetch_graph":"https://pith.science/api/pith-number/VENOWBATEV4XQ4LZFE4GFZV3JV/graph.json","fetch_events":"https://pith.science/api/pith-number/VENOWBATEV4XQ4LZFE4GFZV3JV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV/action/storage_attestation","attest_author":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV/action/author_attestation","sign_citation":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV/action/citation_signature","submit_replication":"https://pith.science/pith/VENOWBATEV4XQ4LZFE4GFZV3JV/action/replication_record"}},"created_at":"2026-07-05T08:29:15.510551+00:00","updated_at":"2026-07-05T08:29:15.510551+00:00"}