{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:VDS3IL5OSTSRQIJLOHZ63LI3UH","short_pith_number":"pith:VDS3IL5O","canonical_record":{"source":{"id":"2104.01522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-04T02:34:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b95fc66e616e0dcc9aa6801a5413d3cafff91ea84c55fb571a65c1d33123b4a8","abstract_canon_sha256":"6df98ab09dc8d852e77568744d0870e7d0f908c902ffdf34377bc334f1a7a20a"},"schema_version":"1.0"},"canonical_sha256":"a8e5b42fae94e518212b71f3edad1ba1c0d1f9390802fadca18a55418313cbcb","source":{"kind":"arxiv","id":"2104.01522","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01522","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01522v1","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01522","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"VDS3IL5OSTSR","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"pith_short_16","alias_value":"VDS3IL5OSTSRQIJL","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"pith_short_8","alias_value":"VDS3IL5O","created_at":"2026-07-05T04:11:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:VDS3IL5OSTSRQIJLOHZ63LI3UH","target":"record","payload":{"canonical_record":{"source":{"id":"2104.01522","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-04T02:34:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b95fc66e616e0dcc9aa6801a5413d3cafff91ea84c55fb571a65c1d33123b4a8","abstract_canon_sha256":"6df98ab09dc8d852e77568744d0870e7d0f908c902ffdf34377bc334f1a7a20a"},"schema_version":"1.0"},"canonical_sha256":"a8e5b42fae94e518212b71f3edad1ba1c0d1f9390802fadca18a55418313cbcb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:11:24.209144Z","signature_b64":"nudM/uipWVhF1O2WOztLHpSsuUI+l1G+ox8F+xzJ3xvHHfxT3yPQAJPouuCktIx0DlkzzzFi/18wQJ+G+A0wBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8e5b42fae94e518212b71f3edad1ba1c0d1f9390802fadca18a55418313cbcb","last_reissued_at":"2026-07-05T04:11:24.208799Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:11:24.208799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.01522","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":"2026-07-05T04:11:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n46ih1YvDyvKFFxGx9XC4evw99yFIhWFqX+hNy/mAXSpwGFthf0t4VsBXxoY5bx13BUBo6xJyW9BVm1KMyZfCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:27:03.645656Z"},"content_sha256":"ff17236ebc54d648e3258749b70d3b67f7dd96e63e9df1511584718878e586b3","schema_version":"1.0","event_id":"sha256:ff17236ebc54d648e3258749b70d3b67f7dd96e63e9df1511584718878e586b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:VDS3IL5OSTSRQIJLOHZ63LI3UH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"eess.AS","authors_text":"Jiangyan Yi, Jianhua Tao, Shuai Zhang, Xuefei Liu, Ye Bai, Zhengkun Tian, Zhengqi Wen","submitted_at":"2021-04-04T02:34:55Z","abstract_excerpt":"The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded states, which is inefficient on GPUs. The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in at least one step. However, the NAR model still faces two major problems. On the one hand, there is still a great gap in performance between the NAR models and the advanced AR models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01522","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/2104.01522/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":"2026-07-05T04:11:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++oGjGy0rBd2YI/NJWTsVlbagkmTOGLOIQ+p7Dc4NRbanTGL4sDTZVJftpCVMiBAD1bmq0V8ATUCJ9UNZBzdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T03:27:03.646356Z"},"content_sha256":"8010766c81483a9d6143815e413e6c822d279beebebd23cf6f06d3d4ad7f421f","schema_version":"1.0","event_id":"sha256:8010766c81483a9d6143815e413e6c822d279beebebd23cf6f06d3d4ad7f421f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH/bundle.json","state_url":"https://pith.science/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH/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":"2026-08-13T03:27:03Z","links":{"resolver":"https://pith.science/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH","bundle":"https://pith.science/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH/bundle.json","state":"https://pith.science/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VDS3IL5OSTSRQIJLOHZ63LI3UH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:VDS3IL5OSTSRQIJLOHZ63LI3UH","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":"6df98ab09dc8d852e77568744d0870e7d0f908c902ffdf34377bc334f1a7a20a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-04T02:34:55Z","title_canon_sha256":"b95fc66e616e0dcc9aa6801a5413d3cafff91ea84c55fb571a65c1d33123b4a8"},"schema_version":"1.0","source":{"id":"2104.01522","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.01522","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"arxiv_version","alias_value":"2104.01522v1","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.01522","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"pith_short_12","alias_value":"VDS3IL5OSTSR","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"pith_short_16","alias_value":"VDS3IL5OSTSRQIJL","created_at":"2026-07-05T04:11:24Z"},{"alias_kind":"pith_short_8","alias_value":"VDS3IL5O","created_at":"2026-07-05T04:11:24Z"}],"graph_snapshots":[{"event_id":"sha256:8010766c81483a9d6143815e413e6c822d279beebebd23cf6f06d3d4ad7f421f","target":"graph","created_at":"2026-07-05T04:11:24Z","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/2104.01522/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The autoregressive (AR) models, such as attention-based encoder-decoder models and RNN-Transducer, have achieved great success in speech recognition. They predict the output sequence conditioned on the previous tokens and acoustic encoded states, which is inefficient on GPUs. The non-autoregressive (NAR) models can get rid of the temporal dependency between the output tokens and predict the entire output tokens in at least one step. However, the NAR model still faces two major problems. On the one hand, there is still a great gap in performance between the NAR models and the advanced AR models","authors_text":"Jiangyan Yi, Jianhua Tao, Shuai Zhang, Xuefei Liu, Ye Bai, Zhengkun Tian, Zhengqi Wen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-04T02:34:55Z","title":"TSNAT: Two-Step Non-Autoregressvie Transformer Models for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.01522","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:ff17236ebc54d648e3258749b70d3b67f7dd96e63e9df1511584718878e586b3","target":"record","created_at":"2026-07-05T04:11:24Z","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":"6df98ab09dc8d852e77568744d0870e7d0f908c902ffdf34377bc334f1a7a20a","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2021-04-04T02:34:55Z","title_canon_sha256":"b95fc66e616e0dcc9aa6801a5413d3cafff91ea84c55fb571a65c1d33123b4a8"},"schema_version":"1.0","source":{"id":"2104.01522","kind":"arxiv","version":1}},"canonical_sha256":"a8e5b42fae94e518212b71f3edad1ba1c0d1f9390802fadca18a55418313cbcb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a8e5b42fae94e518212b71f3edad1ba1c0d1f9390802fadca18a55418313cbcb","first_computed_at":"2026-07-05T04:11:24.208799Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:11:24.208799Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nudM/uipWVhF1O2WOztLHpSsuUI+l1G+ox8F+xzJ3xvHHfxT3yPQAJPouuCktIx0DlkzzzFi/18wQJ+G+A0wBA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:11:24.209144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.01522","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff17236ebc54d648e3258749b70d3b67f7dd96e63e9df1511584718878e586b3","sha256:8010766c81483a9d6143815e413e6c822d279beebebd23cf6f06d3d4ad7f421f"],"state_sha256":"255fcd86474c7636591b79d458a305cf4aaa9ca78c2d06b7b7776fcc61544254"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FCMw56zvRlquRrKSYbbAnMZL5qO5FI03x2HORVg+tVxsUvIX4xGRZmYWSv3iQ6AhHywXnWoxkmv6i9c55LbAAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T03:27:03.655444Z","bundle_sha256":"c221105ca583a157b00c5c9c2bb1e648b3976cb395506293c72d548f0c345914"}}