{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:SA3DNEFXOD4XAXUBPHTQ6JWGCP","short_pith_number":"pith:SA3DNEFX","canonical_record":{"source":{"id":"2203.17113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T15:33:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"465de8518d8b0ec460b3604fd5af2d79838e652e0aa7867053579dd174ea5615","abstract_canon_sha256":"b9db5b2d97d2cd6e7763d0b7664b692aae8ee6513d00b873f3437e6ff4fc5158"},"schema_version":"1.0"},"canonical_sha256":"90363690b770f9705e8179e70f26c613dc7786c43463eb3dbfa162a97a9a9e8d","source":{"kind":"arxiv","id":"2203.17113","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.17113","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2203.17113v2","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17113","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"SA3DNEFXOD4X","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"SA3DNEFXOD4XAXUB","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"SA3DNEFX","created_at":"2026-07-05T04:32:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:SA3DNEFXOD4XAXUBPHTQ6JWGCP","target":"record","payload":{"canonical_record":{"source":{"id":"2203.17113","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T15:33:56Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"465de8518d8b0ec460b3604fd5af2d79838e652e0aa7867053579dd174ea5615","abstract_canon_sha256":"b9db5b2d97d2cd6e7763d0b7664b692aae8ee6513d00b873f3437e6ff4fc5158"},"schema_version":"1.0"},"canonical_sha256":"90363690b770f9705e8179e70f26c613dc7786c43463eb3dbfa162a97a9a9e8d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:58.167591Z","signature_b64":"tCOEyc5ZQiSRxCeGQ41p6pWPmnucnpXSfmHEv7MzIngUGEyYDG+9CZjKo+p4/kXBtL55mEObrmJ0IYFQqerKCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90363690b770f9705e8179e70f26c613dc7786c43463eb3dbfa162a97a9a9e8d","last_reissued_at":"2026-07-05T04:32:58.167118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:58.167118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.17113","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":"2026-07-05T04:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bCWs+tJnLW3XPRzh1YhkdmDyIrIj/Gw+FTNDZuvRUDds8MWZ7b7PrAHET4xjAwB6Wkbr0Ys4ZZW5Ioe9de9FDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:13:49.488113Z"},"content_sha256":"fcc2d5ed5e00fbc3e883ae8115dd5f6c681afe88b5ea0ec10a59d30454fda586","schema_version":"1.0","event_id":"sha256:fcc2d5ed5e00fbc3e883ae8115dd5f6c681afe88b5ea0ec10a59d30454fda586"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:SA3DNEFXOD4XAXUBPHTQ6JWGCP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Furu Wei, Haizhou Li, Jinyu Li, Junyi Ao, Lirong Dai, Long Zhou, Shujie Liu, Tom Ko, Yao Qian, Ziqiang Zhang","submitted_at":"2022-03-31T15:33:56Z","abstract_excerpt":"This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes, derived from an offline clustering model. One is to predict the pseudo codes via masked language modeling in encoder output, like HuBERT model, while the other lets the decoder learn to reconstruct pseudo codes autoregressively instead of generating textual scripts. In this way, the decoder learns to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17113","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/2203.17113/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":"2026-07-05T04:32:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8DkIszG2RWpj9UZguiRD+EHwEL9UBHsHTaZsmcd3LApIYpjIu6Qk0kf/hQiymHE0ZEbzdG44gtPXIpuRNglAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:13:49.488499Z"},"content_sha256":"e8091e7ca455204ab86ea4ee976dc032149467100740e036bff3b016560866c1","schema_version":"1.0","event_id":"sha256:e8091e7ca455204ab86ea4ee976dc032149467100740e036bff3b016560866c1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP/bundle.json","state_url":"https://pith.science/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP/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":"2026-07-06T18:13:49Z","links":{"resolver":"https://pith.science/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP","bundle":"https://pith.science/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP/bundle.json","state":"https://pith.science/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SA3DNEFXOD4XAXUBPHTQ6JWGCP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:SA3DNEFXOD4XAXUBPHTQ6JWGCP","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":"b9db5b2d97d2cd6e7763d0b7664b692aae8ee6513d00b873f3437e6ff4fc5158","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T15:33:56Z","title_canon_sha256":"465de8518d8b0ec460b3604fd5af2d79838e652e0aa7867053579dd174ea5615"},"schema_version":"1.0","source":{"id":"2203.17113","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.17113","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"arxiv_version","alias_value":"2203.17113v2","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.17113","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"pith_short_12","alias_value":"SA3DNEFXOD4X","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"pith_short_16","alias_value":"SA3DNEFXOD4XAXUB","created_at":"2026-07-05T04:32:58Z"},{"alias_kind":"pith_short_8","alias_value":"SA3DNEFX","created_at":"2026-07-05T04:32:58Z"}],"graph_snapshots":[{"event_id":"sha256:e8091e7ca455204ab86ea4ee976dc032149467100740e036bff3b016560866c1","target":"graph","created_at":"2026-07-05T04:32:58Z","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/2203.17113/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper studies a novel pre-training technique with unpaired speech data, Speech2C, for encoder-decoder based automatic speech recognition (ASR). Within a multi-task learning framework, we introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes, derived from an offline clustering model. One is to predict the pseudo codes via masked language modeling in encoder output, like HuBERT model, while the other lets the decoder learn to reconstruct pseudo codes autoregressively instead of generating textual scripts. In this way, the decoder learns to","authors_text":"Furu Wei, Haizhou Li, Jinyu Li, Junyi Ao, Lirong Dai, Long Zhou, Shujie Liu, Tom Ko, Yao Qian, Ziqiang Zhang","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T15:33:56Z","title":"Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.17113","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:fcc2d5ed5e00fbc3e883ae8115dd5f6c681afe88b5ea0ec10a59d30454fda586","target":"record","created_at":"2026-07-05T04:32:58Z","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":"b9db5b2d97d2cd6e7763d0b7664b692aae8ee6513d00b873f3437e6ff4fc5158","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-03-31T15:33:56Z","title_canon_sha256":"465de8518d8b0ec460b3604fd5af2d79838e652e0aa7867053579dd174ea5615"},"schema_version":"1.0","source":{"id":"2203.17113","kind":"arxiv","version":2}},"canonical_sha256":"90363690b770f9705e8179e70f26c613dc7786c43463eb3dbfa162a97a9a9e8d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"90363690b770f9705e8179e70f26c613dc7786c43463eb3dbfa162a97a9a9e8d","first_computed_at":"2026-07-05T04:32:58.167118Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:58.167118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tCOEyc5ZQiSRxCeGQ41p6pWPmnucnpXSfmHEv7MzIngUGEyYDG+9CZjKo+p4/kXBtL55mEObrmJ0IYFQqerKCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:58.167591Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.17113","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fcc2d5ed5e00fbc3e883ae8115dd5f6c681afe88b5ea0ec10a59d30454fda586","sha256:e8091e7ca455204ab86ea4ee976dc032149467100740e036bff3b016560866c1"],"state_sha256":"d23324f98c7195e19a929f2aa3e52571fcd81c562909ceb6de5c7ce57049611c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LFvwft7Q+M6d5KyIM6rGmpp7mHCE/27TZRFYlM6phc6l4r8QnklRFg0eQhCPxeV4SLlW2La1XAa16OobojBCBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:13:49.490511Z","bundle_sha256":"5012003adbdcc752968cfcc76fe4619761ed0538b33ee11f6d3671a8ebc39c89"}}