{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Z65QVI4GIOMSEMYDBKFOAKKB26","short_pith_number":"pith:Z65QVI4G","canonical_record":{"source":{"id":"2012.05481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2020-12-10T06:54:54Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"fe1f56dfe68ed92ebb3bfee62cb651beb56bf863a093b5fbe00171ef253d3f33","abstract_canon_sha256":"20a7dfa16f68fa12b5c1dab6cf7e2aad1bd1005b198682048647210c044aabf0"},"schema_version":"1.0"},"canonical_sha256":"cfbb0aa38643992233030a8ae02941d78bba49ce7b16880a8478aa9529b6d391","source":{"kind":"arxiv","id":"2012.05481","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05481","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05481v2","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05481","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"Z65QVI4GIOMS","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"Z65QVI4GIOMSEMYD","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"Z65QVI4G","created_at":"2026-07-05T03:44:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Z65QVI4GIOMSEMYDBKFOAKKB26","target":"record","payload":{"canonical_record":{"source":{"id":"2012.05481","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2020-12-10T06:54:54Z","cross_cats_sorted":["cs.CL","eess.AS"],"title_canon_sha256":"fe1f56dfe68ed92ebb3bfee62cb651beb56bf863a093b5fbe00171ef253d3f33","abstract_canon_sha256":"20a7dfa16f68fa12b5c1dab6cf7e2aad1bd1005b198682048647210c044aabf0"},"schema_version":"1.0"},"canonical_sha256":"cfbb0aa38643992233030a8ae02941d78bba49ce7b16880a8478aa9529b6d391","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:44:08.285438Z","signature_b64":"5c4yZP6jedd9EpHiMWPJUQjsRycarglVc5mBfycU4NHFOTeghTSj01KHROOS2Rz0KAmY9JDXaN0gaDpxZiDUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfbb0aa38643992233030a8ae02941d78bba49ce7b16880a8478aa9529b6d391","last_reissued_at":"2026-07-05T03:44:08.284996Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:44:08.284996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.05481","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mdgU739DvlQmlUgVVhZ+A3ceWJa8qD51+Y/09Ia0z+FcGAaHLIijgH54QBrhTx/Z0nhs7TbgOFEVrbYIgbvVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T08:58:01.334595Z"},"content_sha256":"2b4a95de3367914c7ba6f3553387b9373a763d9594cd4da52039eb27e85da8f5","schema_version":"1.0","event_id":"sha256:2b4a95de3367914c7ba6f3553387b9373a763d9594cd4da52039eb27e85da8f5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Z65QVI4GIOMSEMYDBKFOAKKB26","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","eess.AS"],"primary_cat":"cs.SD","authors_text":"Binbin Zhang, Chao Yang, Di Wu, Fan Yu, Lei Xie, Liyong Guo, Xin Lei, Xiong Wang, Yaguang Hu, Zhuoyuan Yao","submitted_at":"2020-12-10T06:54:54Z","abstract_excerpt":"In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05481","kind":"arxiv","version":2},"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/2012.05481/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":"2026-07-05T03:44:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5LF4tTZfoCgGDum5NltXyKLSwimfDHJjxTIBdo0D4Cuqk4OiUogG7tj5QwH7KrFgf2fM3x+QgY5JjYtOKqdCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T08:58:01.334964Z"},"content_sha256":"79e088566d6058d4749e8eb98a72703cc2e86753737ceb2650cab577e3b1be0d","schema_version":"1.0","event_id":"sha256:79e088566d6058d4749e8eb98a72703cc2e86753737ceb2650cab577e3b1be0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z65QVI4GIOMSEMYDBKFOAKKB26/bundle.json","state_url":"https://pith.science/pith/Z65QVI4GIOMSEMYDBKFOAKKB26/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z65QVI4GIOMSEMYDBKFOAKKB26/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":"2026-07-27T08:58:01Z","links":{"resolver":"https://pith.science/pith/Z65QVI4GIOMSEMYDBKFOAKKB26","bundle":"https://pith.science/pith/Z65QVI4GIOMSEMYDBKFOAKKB26/bundle.json","state":"https://pith.science/pith/Z65QVI4GIOMSEMYDBKFOAKKB26/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z65QVI4GIOMSEMYDBKFOAKKB26/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Z65QVI4GIOMSEMYDBKFOAKKB26","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":"20a7dfa16f68fa12b5c1dab6cf7e2aad1bd1005b198682048647210c044aabf0","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2020-12-10T06:54:54Z","title_canon_sha256":"fe1f56dfe68ed92ebb3bfee62cb651beb56bf863a093b5fbe00171ef253d3f33"},"schema_version":"1.0","source":{"id":"2012.05481","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.05481","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"arxiv_version","alias_value":"2012.05481v2","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.05481","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"pith_short_12","alias_value":"Z65QVI4GIOMS","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"pith_short_16","alias_value":"Z65QVI4GIOMSEMYD","created_at":"2026-07-05T03:44:08Z"},{"alias_kind":"pith_short_8","alias_value":"Z65QVI4G","created_at":"2026-07-05T03:44:08Z"}],"graph_snapshots":[{"event_id":"sha256:79e088566d6058d4749e8eb98a72703cc2e86753737ceb2650cab577e3b1be0d","target":"graph","created_at":"2026-07-05T03:44:08Z","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/2012.05481/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a novel two-pass approach to unify streaming and non-streaming end-to-end (E2E) speech recognition in a single model. Our model adopts the hybrid CTC/attention architecture, in which the conformer layers in the encoder are modified. We propose a dynamic chunk-based attention strategy to allow arbitrary right context length. At inference time, the CTC decoder generates n-best hypotheses in a streaming way. The inference latency could be easily controlled by only changing the chunk size. The CTC hypotheses are then rescored by the attention decoder to get the final resu","authors_text":"Binbin Zhang, Chao Yang, Di Wu, Fan Yu, Lei Xie, Liyong Guo, Xin Lei, Xiong Wang, Yaguang Hu, Zhuoyuan Yao","cross_cats":["cs.CL","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2020-12-10T06:54:54Z","title":"Unified Streaming and Non-streaming Two-pass End-to-end Model for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.05481","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":"sha256:2b4a95de3367914c7ba6f3553387b9373a763d9594cd4da52039eb27e85da8f5","target":"record","created_at":"2026-07-05T03:44:08Z","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":"20a7dfa16f68fa12b5c1dab6cf7e2aad1bd1005b198682048647210c044aabf0","cross_cats_sorted":["cs.CL","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2020-12-10T06:54:54Z","title_canon_sha256":"fe1f56dfe68ed92ebb3bfee62cb651beb56bf863a093b5fbe00171ef253d3f33"},"schema_version":"1.0","source":{"id":"2012.05481","kind":"arxiv","version":2}},"canonical_sha256":"cfbb0aa38643992233030a8ae02941d78bba49ce7b16880a8478aa9529b6d391","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cfbb0aa38643992233030a8ae02941d78bba49ce7b16880a8478aa9529b6d391","first_computed_at":"2026-07-05T03:44:08.284996Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:44:08.284996Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5c4yZP6jedd9EpHiMWPJUQjsRycarglVc5mBfycU4NHFOTeghTSj01KHROOS2Rz0KAmY9JDXaN0gaDpxZiDUBA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:44:08.285438Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.05481","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2b4a95de3367914c7ba6f3553387b9373a763d9594cd4da52039eb27e85da8f5","sha256:79e088566d6058d4749e8eb98a72703cc2e86753737ceb2650cab577e3b1be0d"],"state_sha256":"e07048045208570c48d8dfc6515628090d1c3511eda8e66129a6e9869741a42e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mNC9f0ybScMkirCqZ2wRT6MCWnbb7WiZc/RHklDANzC1FQmPo3rd2HwWqKvyEy37dWozHpleT6JpnlPjhloUAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T08:58:01.337378Z","bundle_sha256":"a70c91c6ef56e320cecb66e3d07f16e333a6f05a931ac395c3096c990236fa4e"}}