{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:7XJN472AGFRPZ7Z5VQEZH3JEI2","short_pith_number":"pith:7XJN472A","canonical_record":{"source":{"id":"2005.08100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T20:56:25Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"cfd29d663f86f531f18fe68dbd29f394e74232eea1a2c4b0095cb35176712793","abstract_canon_sha256":"5077984e6bf30f590d4891aa7f4c1dfc7586d07bfa019c392ffaaf7be822c9b0"},"schema_version":"1.0"},"canonical_sha256":"fdd2de7f403162fcff3dac0993ed24468261e0d3f127b05d8364da976ae4a4e1","source":{"kind":"arxiv","id":"2005.08100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08100","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08100v1","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08100","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"7XJN472AGFRP","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"7XJN472AGFRPZ7Z5","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"7XJN472A","created_at":"2026-07-05T01:03:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:7XJN472AGFRPZ7Z5VQEZH3JEI2","target":"record","payload":{"canonical_record":{"source":{"id":"2005.08100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T20:56:25Z","cross_cats_sorted":["cs.LG","cs.SD"],"title_canon_sha256":"cfd29d663f86f531f18fe68dbd29f394e74232eea1a2c4b0095cb35176712793","abstract_canon_sha256":"5077984e6bf30f590d4891aa7f4c1dfc7586d07bfa019c392ffaaf7be822c9b0"},"schema_version":"1.0"},"canonical_sha256":"fdd2de7f403162fcff3dac0993ed24468261e0d3f127b05d8364da976ae4a4e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:28.083541Z","signature_b64":"oaStL2dRTO6k2H8cnbMTe1c4Ekj2c71b6ZAnHiZwr6nHDHVI51l/1hXcEZ0hnl8WPTiVR2D215xxOGm1R5iWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdd2de7f403162fcff3dac0993ed24468261e0d3f127b05d8364da976ae4a4e1","last_reissued_at":"2026-07-05T01:03:28.083135Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:28.083135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.08100","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DvuqJhWde4fbeD7Tdl8FqaVJZlH+lRaBiroT2qRgNpf149qUXJ2YhfptHVMPkggT1r9jBgT16uFMBHf4X4eJDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:47:55.478917Z"},"content_sha256":"1cf03706d1692781194cac049acc8f687e907923d68e5cc65d2d7ae57858ba75","schema_version":"1.0","event_id":"sha256:1cf03706d1692781194cac049acc8f687e907923d68e5cc65d2d7ae57858ba75"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:7XJN472AGFRPZ7Z5VQEZH3JEI2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conformer: Convolution-augmented Transformer for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Anmol Gulati, Chung-Cheng Chiu, James Qin, Jiahui Yu, Niki Parmar, Ruoming Pang, Shibo Wang, Wei Han, Yonghui Wu, Yu Zhang, Zhengdong Zhang","submitted_at":"2020-05-16T20:56:25Z","abstract_excerpt":"Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08100","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/2005.08100/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:03:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"167uN7gybzDvY/j/QEsarAEpIBdAsv/MHype6yNHIuGRGq/frJxIvB9T42gRsquodu4j5j54miaMXutX/0+/AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T13:47:55.479434Z"},"content_sha256":"3817225ff876399789a019d4fbccce2e7ea53b9875bc0aa7d1f0071ceeaded08","schema_version":"1.0","event_id":"sha256:3817225ff876399789a019d4fbccce2e7ea53b9875bc0aa7d1f0071ceeaded08"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2/bundle.json","state_url":"https://pith.science/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-22T13:47:55Z","links":{"resolver":"https://pith.science/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2","bundle":"https://pith.science/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2/bundle.json","state":"https://pith.science/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7XJN472AGFRPZ7Z5VQEZH3JEI2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:7XJN472AGFRPZ7Z5VQEZH3JEI2","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":"5077984e6bf30f590d4891aa7f4c1dfc7586d07bfa019c392ffaaf7be822c9b0","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T20:56:25Z","title_canon_sha256":"cfd29d663f86f531f18fe68dbd29f394e74232eea1a2c4b0095cb35176712793"},"schema_version":"1.0","source":{"id":"2005.08100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.08100","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"arxiv_version","alias_value":"2005.08100v1","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.08100","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"pith_short_12","alias_value":"7XJN472AGFRP","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"pith_short_16","alias_value":"7XJN472AGFRPZ7Z5","created_at":"2026-07-05T01:03:28Z"},{"alias_kind":"pith_short_8","alias_value":"7XJN472A","created_at":"2026-07-05T01:03:28Z"}],"graph_snapshots":[{"event_id":"sha256:3817225ff876399789a019d4fbccce2e7ea53b9875bc0aa7d1f0071ceeaded08","target":"graph","created_at":"2026-07-05T01:03:28Z","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/2005.08100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR), outperforming Recurrent neural networks (RNNs). Transformer models are good at capturing content-based global interactions, while CNNs exploit local features effectively. In this work, we achieve the best of both worlds by studying how to combine convolution neural networks and transformers to model both local and global dependencies of an audio sequence in a parameter-efficient way. To this regard, we propose the convolution-augmented transformer for speec","authors_text":"Anmol Gulati, Chung-Cheng Chiu, James Qin, Jiahui Yu, Niki Parmar, Ruoming Pang, Shibo Wang, Wei Han, Yonghui Wu, Yu Zhang, Zhengdong Zhang","cross_cats":["cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T20:56:25Z","title":"Conformer: Convolution-augmented Transformer for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.08100","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":"sha256:1cf03706d1692781194cac049acc8f687e907923d68e5cc65d2d7ae57858ba75","target":"record","created_at":"2026-07-05T01:03:28Z","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":"5077984e6bf30f590d4891aa7f4c1dfc7586d07bfa019c392ffaaf7be822c9b0","cross_cats_sorted":["cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-16T20:56:25Z","title_canon_sha256":"cfd29d663f86f531f18fe68dbd29f394e74232eea1a2c4b0095cb35176712793"},"schema_version":"1.0","source":{"id":"2005.08100","kind":"arxiv","version":1}},"canonical_sha256":"fdd2de7f403162fcff3dac0993ed24468261e0d3f127b05d8364da976ae4a4e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fdd2de7f403162fcff3dac0993ed24468261e0d3f127b05d8364da976ae4a4e1","first_computed_at":"2026-07-05T01:03:28.083135Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:28.083135Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oaStL2dRTO6k2H8cnbMTe1c4Ekj2c71b6ZAnHiZwr6nHDHVI51l/1hXcEZ0hnl8WPTiVR2D215xxOGm1R5iWCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:28.083541Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.08100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1cf03706d1692781194cac049acc8f687e907923d68e5cc65d2d7ae57858ba75","sha256:3817225ff876399789a019d4fbccce2e7ea53b9875bc0aa7d1f0071ceeaded08"],"state_sha256":"3c3385118c2c6e5f328e4c9d9033b0e7fcd67f7c520c52ff8845ef846644a04b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4I0G6J4erX3/Ux/qtqOL2JZnIV3Oqrdnybt5WZTV7vauJr7uKg3Z8FZ7L30x37srgN2yoozeaaGiDaE5pBNeBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T13:47:55.483111Z","bundle_sha256":"218c9cbe2d51b9c2c3a0dcf1249627e9eba9a1d4659992abedf7ffac5c4be145"}}