{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:MJCIBYICU7VAVT3HQTAZ7U2GHB","short_pith_number":"pith:MJCIBYIC","canonical_record":{"source":{"id":"2005.09862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T06:22:29Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"98732ff31441351325ef7c8fde4f3917ceb274c0325a2ff9354ab03f89af0e28","abstract_canon_sha256":"10287743c8176243e1cbfcec39cbba6464b455975ca5df9be55aaf55255e416a"},"schema_version":"1.0"},"canonical_sha256":"624480e102a7ea0acf6784c19fd34638602908ef481d53abe10132bf130ae0ba","source":{"kind":"arxiv","id":"2005.09862","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09862","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09862v2","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09862","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"MJCIBYICU7VA","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"MJCIBYICU7VAVT3H","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"MJCIBYIC","created_at":"2026-07-05T01:12:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:MJCIBYICU7VAVT3HQTAZ7U2GHB","target":"record","payload":{"canonical_record":{"source":{"id":"2005.09862","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T06:22:29Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"98732ff31441351325ef7c8fde4f3917ceb274c0325a2ff9354ab03f89af0e28","abstract_canon_sha256":"10287743c8176243e1cbfcec39cbba6464b455975ca5df9be55aaf55255e416a"},"schema_version":"1.0"},"canonical_sha256":"624480e102a7ea0acf6784c19fd34638602908ef481d53abe10132bf130ae0ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:12:47.052570Z","signature_b64":"f4mTKAVjH9OmwSxuC/IbL8cWL2uCjO+DkQKsS0vXZotMSlHWFR7bHzaPXb8c+zAbqLbaPFVRorKYPuBPsE00Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"624480e102a7ea0acf6784c19fd34638602908ef481d53abe10132bf130ae0ba","last_reissued_at":"2026-07-05T01:12:47.052076Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:12:47.052076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.09862","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":"2026-07-05T01:12:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kry+T4UvNDw/u9AaTD0BxEKYm4DNv+NAjHJMID2dL2T/MEJ6Fy7q3IbNTE9R0BJAkL6+prP7FXt25Y6igCWrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:08:14.911452Z"},"content_sha256":"c72ff087e4bf09b909b6b7dd2cdee433557e19f37669f4eaade1fa0180824168","schema_version":"1.0","event_id":"sha256:c72ff087e4bf09b909b6b7dd2cdee433557e19f37669f4eaade1fa0180824168"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:MJCIBYICU7VAVT3HQTAZ7U2GHB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Dongwei Jiang, Miao Cao, Ne Luo, Ruixiong Zhang, Wei Zou, Wubo Li, Xiangang Li, Yang Han","submitted_at":"2020-05-20T06:22:29Z","abstract_excerpt":"Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked Predictive Coding achieved significant improvements on various speech recognition datasets with BERT-like Masked Reconstruction loss and Transformer backbone. However, many aspects of MPC have not been fully investigated. In this paper, we conduct a further study on MPC and focus on three important aspects: the effect of pre-training data speaking style, its ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09862","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/2005.09862/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":"2026-07-05T01:12:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RBz2ShIHFZvuWu/YhkjtV0upsuVVuH3CzWSyiI7fGBRBwjyu9r7lvgIjAx63om1wYnUjz0gm8iHmDMeWoe54AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T18:08:14.912505Z"},"content_sha256":"cd19332d0f81dcf80f7feba53f490350d11aa2fa19e58ced89409412a54cb8fa","schema_version":"1.0","event_id":"sha256:cd19332d0f81dcf80f7feba53f490350d11aa2fa19e58ced89409412a54cb8fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB/bundle.json","state_url":"https://pith.science/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB/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":"2026-08-06T18:08:14Z","links":{"resolver":"https://pith.science/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB","bundle":"https://pith.science/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB/bundle.json","state":"https://pith.science/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJCIBYICU7VAVT3HQTAZ7U2GHB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:MJCIBYICU7VAVT3HQTAZ7U2GHB","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":"10287743c8176243e1cbfcec39cbba6464b455975ca5df9be55aaf55255e416a","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T06:22:29Z","title_canon_sha256":"98732ff31441351325ef7c8fde4f3917ceb274c0325a2ff9354ab03f89af0e28"},"schema_version":"1.0","source":{"id":"2005.09862","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.09862","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2005.09862v2","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.09862","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"MJCIBYICU7VA","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"MJCIBYICU7VAVT3H","created_at":"2026-07-05T01:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"MJCIBYIC","created_at":"2026-07-05T01:12:47Z"}],"graph_snapshots":[{"event_id":"sha256:cd19332d0f81dcf80f7feba53f490350d11aa2fa19e58ced89409412a54cb8fa","target":"graph","created_at":"2026-07-05T01:12:47Z","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/2005.09862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Building a good speech recognition system usually requires large amounts of transcribed data, which is expensive to collect. To tackle this problem, many unsupervised pre-training methods have been proposed. Among these methods, Masked Predictive Coding achieved significant improvements on various speech recognition datasets with BERT-like Masked Reconstruction loss and Transformer backbone. However, many aspects of MPC have not been fully investigated. In this paper, we conduct a further study on MPC and focus on three important aspects: the effect of pre-training data speaking style, its ext","authors_text":"Dongwei Jiang, Miao Cao, Ne Luo, Ruixiong Zhang, Wei Zou, Wubo Li, Xiangang Li, Yang Han","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T06:22:29Z","title":"A Further Study of Unsupervised Pre-training for Transformer Based Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.09862","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:c72ff087e4bf09b909b6b7dd2cdee433557e19f37669f4eaade1fa0180824168","target":"record","created_at":"2026-07-05T01:12:47Z","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":"10287743c8176243e1cbfcec39cbba6464b455975ca5df9be55aaf55255e416a","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.AS","submitted_at":"2020-05-20T06:22:29Z","title_canon_sha256":"98732ff31441351325ef7c8fde4f3917ceb274c0325a2ff9354ab03f89af0e28"},"schema_version":"1.0","source":{"id":"2005.09862","kind":"arxiv","version":2}},"canonical_sha256":"624480e102a7ea0acf6784c19fd34638602908ef481d53abe10132bf130ae0ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"624480e102a7ea0acf6784c19fd34638602908ef481d53abe10132bf130ae0ba","first_computed_at":"2026-07-05T01:12:47.052076Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:12:47.052076Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"f4mTKAVjH9OmwSxuC/IbL8cWL2uCjO+DkQKsS0vXZotMSlHWFR7bHzaPXb8c+zAbqLbaPFVRorKYPuBPsE00Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T01:12:47.052570Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.09862","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c72ff087e4bf09b909b6b7dd2cdee433557e19f37669f4eaade1fa0180824168","sha256:cd19332d0f81dcf80f7feba53f490350d11aa2fa19e58ced89409412a54cb8fa"],"state_sha256":"f11f5dc7cfff9fbf2d9ef229e7d9fd86ed5b0176bbdadd7c4fcc527a2be122a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PBr5AAINOrkbIayWKMmM16JiOLTkTlkR2bWKqYTBZF+B4fs4MDdBqa/76fkxC6k0hc7rC2DUwDYskr0Ha5fSBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T18:08:14.917830Z","bundle_sha256":"95d617cc53208aa7b031caae5055a762fa7b3da20824ac133ac2f318d48d306a"}}