{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IFL7GS3QJXB3DCS7YMVCGYT5YT","short_pith_number":"pith:IFL7GS3Q","canonical_record":{"source":{"id":"2112.07254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2d03165e74d5c7b13d773e6c4b575422394596d51cae44b8a452e275328fca12","abstract_canon_sha256":"3cfc4438b9f1ac9a6f01fc42ae17c899daff99ff1b49178039406c8473f8ce53"},"schema_version":"1.0"},"canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","source":{"kind":"arxiv","id":"2112.07254","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07254","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07254v1","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07254","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"IFL7GS3QJXB3","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"IFL7GS3QJXB3DCS7","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"IFL7GS3Q","created_at":"2026-07-05T03:40:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IFL7GS3QJXB3DCS7YMVCGYT5YT","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07254","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"2d03165e74d5c7b13d773e6c4b575422394596d51cae44b8a452e275328fca12","abstract_canon_sha256":"3cfc4438b9f1ac9a6f01fc42ae17c899daff99ff1b49178039406c8473f8ce53"},"schema_version":"1.0"},"canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:56.376637Z","signature_b64":"JL4vfoF0ZULbQZG3V/Kf7nu04LH+X9hcoi++8u0JjWA8QQP9USpxb1JMzY6Mh4hmWNmLwfGic41MKmWBVDN7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","last_reissued_at":"2026-07-05T03:40:56.376150Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:56.376150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07254","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":"2026-07-05T03:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lZbCvlyfSrxs+6vMHolqB9eojXdKhWjyB/AQ8H8LNFh0w0wesJXLwrptU5z2FsG3oGrU8oNkvT4TyLVIUFHFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:48:27.972180Z"},"content_sha256":"80f5ac1c8aab60cee36252e2bc2390bda87b45a8c8370214795bc0754aa1611b","schema_version":"1.0","event_id":"sha256:80f5ac1c8aab60cee36252e2bc2390bda87b45a8c8370214795bc0754aa1611b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IFL7GS3QJXB3DCS7YMVCGYT5YT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Keqi Deng, Long Ma, Songjun Cao, Yike Zhang","submitted_at":"2021-12-14T09:38:31Z","abstract_excerpt":"Recently, self-supervised pretraining has achieved impressive results in end-to-end (E2E) automatic speech recognition (ASR). However, the dominant sequence-to-sequence (S2S) E2E model is still hard to fully utilize the self-supervised pre-training methods because its decoder is conditioned on acoustic representation thus cannot be pretrained separately. In this paper, we propose a pretrained Transformer (Preformer) S2S ASR architecture based on hybrid CTC/attention E2E models to fully utilize the pretrained acoustic models (AMs) and language models (LMs). In our framework, the encoder is init"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07254","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/2112.07254/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":"2026-07-05T03:40:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dD4rx23mIAIXZp025lJQ3waExNNmyjwa9yO3I3AynO2UX57wHPykhyW6+QFVxgf+lYZ/m/7C+eYDJOAAYsbCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T07:48:27.972834Z"},"content_sha256":"ae25229aae5cdf7c18ee078ad3382e7149ef3a3d83e91e902102875cfe94514e","schema_version":"1.0","event_id":"sha256:ae25229aae5cdf7c18ee078ad3382e7149ef3a3d83e91e902102875cfe94514e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT/bundle.json","state_url":"https://pith.science/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT/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":"2026-08-08T07:48:27Z","links":{"resolver":"https://pith.science/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT","bundle":"https://pith.science/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT/bundle.json","state":"https://pith.science/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IFL7GS3QJXB3DCS7YMVCGYT5YT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IFL7GS3QJXB3DCS7YMVCGYT5YT","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":"3cfc4438b9f1ac9a6f01fc42ae17c899daff99ff1b49178039406c8473f8ce53","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","title_canon_sha256":"2d03165e74d5c7b13d773e6c4b575422394596d51cae44b8a452e275328fca12"},"schema_version":"1.0","source":{"id":"2112.07254","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07254","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07254v1","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07254","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_12","alias_value":"IFL7GS3QJXB3","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_16","alias_value":"IFL7GS3QJXB3DCS7","created_at":"2026-07-05T03:40:56Z"},{"alias_kind":"pith_short_8","alias_value":"IFL7GS3Q","created_at":"2026-07-05T03:40:56Z"}],"graph_snapshots":[{"event_id":"sha256:ae25229aae5cdf7c18ee078ad3382e7149ef3a3d83e91e902102875cfe94514e","target":"graph","created_at":"2026-07-05T03:40:56Z","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/2112.07254/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, self-supervised pretraining has achieved impressive results in end-to-end (E2E) automatic speech recognition (ASR). However, the dominant sequence-to-sequence (S2S) E2E model is still hard to fully utilize the self-supervised pre-training methods because its decoder is conditioned on acoustic representation thus cannot be pretrained separately. In this paper, we propose a pretrained Transformer (Preformer) S2S ASR architecture based on hybrid CTC/attention E2E models to fully utilize the pretrained acoustic models (AMs) and language models (LMs). In our framework, the encoder is init","authors_text":"Keqi Deng, Long Ma, Songjun Cao, Yike Zhang","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","title":"Improving Hybrid CTC/Attention End-to-end Speech Recognition with Pretrained Acoustic and Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07254","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":"sha256:80f5ac1c8aab60cee36252e2bc2390bda87b45a8c8370214795bc0754aa1611b","target":"record","created_at":"2026-07-05T03:40:56Z","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":"3cfc4438b9f1ac9a6f01fc42ae17c899daff99ff1b49178039406c8473f8ce53","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-12-14T09:38:31Z","title_canon_sha256":"2d03165e74d5c7b13d773e6c4b575422394596d51cae44b8a452e275328fca12"},"schema_version":"1.0","source":{"id":"2112.07254","kind":"arxiv","version":1}},"canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4157f34b704dc3b18a5fc32a23627dc4dd42bac338add3d78c77b69f084f7d84","first_computed_at":"2026-07-05T03:40:56.376150Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:56.376150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JL4vfoF0ZULbQZG3V/Kf7nu04LH+X9hcoi++8u0JjWA8QQP9USpxb1JMzY6Mh4hmWNmLwfGic41MKmWBVDN7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:56.376637Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07254","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:80f5ac1c8aab60cee36252e2bc2390bda87b45a8c8370214795bc0754aa1611b","sha256:ae25229aae5cdf7c18ee078ad3382e7149ef3a3d83e91e902102875cfe94514e"],"state_sha256":"ffa80ccf38c065c13c9c15fb681db19d6f9e94980431cafac55860583f2a1ac3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C65FDLg+vjnZtWMWTrl7nQqQLabEpxmWm/33lcctnREUySfYKAyVxV4OX5KRekoUCF4uzemDCGWAHuaGyVY1Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T07:48:27.977441Z","bundle_sha256":"9c2165fac25e43727c793abb93d3d6f3a44d46d71a534218d4b97055d2469f1c"}}