{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4F6RPHEV6MDQB5F6DDPFAYWNDG","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":"bde864a4394b15d2d5e49c7818777e14b6831e2fb5534afc45858a36b0357e86","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-05T21:30:10Z","title_canon_sha256":"bca6a6af68551ca9dd553775dc3371c6d625362f57f00e03ac38112116fb64ee"},"schema_version":"1.0","source":{"id":"2311.02772","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.02772","created_at":"2026-07-05T07:42:43Z"},{"alias_kind":"arxiv_version","alias_value":"2311.02772v2","created_at":"2026-07-05T07:42:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.02772","created_at":"2026-07-05T07:42:43Z"},{"alias_kind":"pith_short_12","alias_value":"4F6RPHEV6MDQ","created_at":"2026-07-05T07:42:43Z"},{"alias_kind":"pith_short_16","alias_value":"4F6RPHEV6MDQB5F6","created_at":"2026-07-05T07:42:43Z"},{"alias_kind":"pith_short_8","alias_value":"4F6RPHEV","created_at":"2026-07-05T07:42:43Z"}],"graph_snapshots":[{"event_id":"sha256:6cc7eb2ef42e35a2bb7ebd7365bb9f522ec2a4ae0fe7a98ea23e3e5fa7ce08c4","target":"graph","created_at":"2026-07-05T07:42:43Z","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/2311.02772/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we show that a simple self-supervised pre-trained audio model can achieve comparable inference efficiency to more complicated pre-trained models with speech transformer encoders. These speech transformers rely on mixing convolutional modules with self-attention modules. They achieve state-of-the-art performance on ASR with top efficiency. We first show that employing these speech transformers as an encoder significantly improves the efficiency of pre-trained audio models as well. However, our study shows that we can achieve comparable efficiency with advanced self-attention sole","authors_text":"Ching-Feng Yeh, Daniel Bikel, Hakan Inan, Rashi Rungta, Sungho Jeon, Wei-Ning Hsu, Yashar Mehdad","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-05T21:30:10Z","title":"Attention or Convolution: Transformer Encoders in Audio Language Models for Inference Efficiency"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.02772","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":"sha256:8900c666205903e8a7b5c539dd03957149bbc1239ac0af8f152d1ddd6ec6e2a6","target":"record","created_at":"2026-07-05T07:42:43Z","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":"bde864a4394b15d2d5e49c7818777e14b6831e2fb5534afc45858a36b0357e86","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-11-05T21:30:10Z","title_canon_sha256":"bca6a6af68551ca9dd553775dc3371c6d625362f57f00e03ac38112116fb64ee"},"schema_version":"1.0","source":{"id":"2311.02772","kind":"arxiv","version":2}},"canonical_sha256":"e17d179c95f30700f4be18de5062cd199765cee094eaba9e49d074ffc0dd639e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e17d179c95f30700f4be18de5062cd199765cee094eaba9e49d074ffc0dd639e","first_computed_at":"2026-07-05T07:42:43.140924Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:42:43.140924Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MsuDnacsa5FY/SjbKhrhc+gmA37+ogm2hwupEsXe+JlEcZX11qkHWYU1ohyE8ZtuhtOIxHInlkCgwgsOOYc+Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:42:43.141383Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.02772","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8900c666205903e8a7b5c539dd03957149bbc1239ac0af8f152d1ddd6ec6e2a6","sha256:6cc7eb2ef42e35a2bb7ebd7365bb9f522ec2a4ae0fe7a98ea23e3e5fa7ce08c4"],"state_sha256":"ea3bc384bc3fb2ca02eb4ccffa648ce8c95fd8b13889778355b48ff552933bb4"}