{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HLAFSAUQFWYUQPJM7TGYIUCHMA","short_pith_number":"pith:HLAFSAUQ","canonical_record":{"source":{"id":"2110.15836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T14:59:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1e8dbffe90735afdb46af82925c2736b502104f77e0670a0a2248021c258ed6d","abstract_canon_sha256":"b4698e25482cb18af1e3655df168691870d4b824d7d87c5de286e793454628b2"},"schema_version":"1.0"},"canonical_sha256":"3ac05902902db1483d2cfccd8450476002871becbfde543b126d447fa795697a","source":{"kind":"arxiv","id":"2110.15836","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15836","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15836v2","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15836","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"HLAFSAUQFWYU","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"HLAFSAUQFWYUQPJM","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"HLAFSAUQ","created_at":"2026-07-05T03:56:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HLAFSAUQFWYUQPJM7TGYIUCHMA","target":"record","payload":{"canonical_record":{"source":{"id":"2110.15836","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T14:59:18Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1e8dbffe90735afdb46af82925c2736b502104f77e0670a0a2248021c258ed6d","abstract_canon_sha256":"b4698e25482cb18af1e3655df168691870d4b824d7d87c5de286e793454628b2"},"schema_version":"1.0"},"canonical_sha256":"3ac05902902db1483d2cfccd8450476002871becbfde543b126d447fa795697a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:56:04.140500Z","signature_b64":"J/qwYEsXTlADlU62u5XpJkdG5IACDzW1novEAeOQVlP5+qdJl/JzKEhAkwfK/8shZBC2aIx3qP9nB8BaP/wQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ac05902902db1483d2cfccd8450476002871becbfde543b126d447fa795697a","last_reissued_at":"2026-07-05T03:56:04.140058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:56:04.140058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.15836","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":"2026-07-05T03:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ct6nUSeqNue/41JrYhPdqeytkE7VD7Un/EFG6qVBb+FBqegvOaZQ0yckVkZR6di68Pljs6T8bY8wdkDurdlaBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:29:51.964679Z"},"content_sha256":"a6c6d48bb70c6219fdc94f7ad995f959d6e049c66fe68ff4d2ca5b15eb5daf12","schema_version":"1.0","event_id":"sha256:a6c6d48bb70c6219fdc94f7ad995f959d6e049c66fe68ff4d2ca5b15eb5daf12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HLAFSAUQFWYUQPJM7TGYIUCHMA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chak-Fai Li, Francis Keith, Matthew Snover, William Hartmann","submitted_at":"2021-10-29T14:59:18Z","abstract_excerpt":"Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute -- conversational and broadcast domains. Moving beyond CTC, we pretrain state-of-the-art Conformer models in an unsupervised manner. While the unsupervised approach outperforms traditional semi-supervised training, the techniques are complementary. Combining the techniques is a 5% absolute improvement in WER, averaged over all conditions, compared to semi-supervis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15836","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/2110.15836/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":"2026-07-05T03:56:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/+YpGCfb2lNyLu9dkSEVbAQwEAckwkWDcPEEuI/gp+jy5x4XiIWiD815IbEsWcZb32i68gzAc4Yhw9JS6vc3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T19:29:51.965735Z"},"content_sha256":"f993ac4653929e1710c553f2b2e23bfff3d7d8a530ca797d0c59e33992e15b59","schema_version":"1.0","event_id":"sha256:f993ac4653929e1710c553f2b2e23bfff3d7d8a530ca797d0c59e33992e15b59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA/bundle.json","state_url":"https://pith.science/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA/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":"2026-08-15T19:29:51Z","links":{"resolver":"https://pith.science/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA","bundle":"https://pith.science/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA/bundle.json","state":"https://pith.science/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HLAFSAUQFWYUQPJM7TGYIUCHMA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HLAFSAUQFWYUQPJM7TGYIUCHMA","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":"b4698e25482cb18af1e3655df168691870d4b824d7d87c5de286e793454628b2","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T14:59:18Z","title_canon_sha256":"1e8dbffe90735afdb46af82925c2736b502104f77e0670a0a2248021c258ed6d"},"schema_version":"1.0","source":{"id":"2110.15836","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.15836","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"arxiv_version","alias_value":"2110.15836v2","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.15836","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_12","alias_value":"HLAFSAUQFWYU","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_16","alias_value":"HLAFSAUQFWYUQPJM","created_at":"2026-07-05T03:56:04Z"},{"alias_kind":"pith_short_8","alias_value":"HLAFSAUQ","created_at":"2026-07-05T03:56:04Z"}],"graph_snapshots":[{"event_id":"sha256:f993ac4653929e1710c553f2b2e23bfff3d7d8a530ca797d0c59e33992e15b59","target":"graph","created_at":"2026-07-05T03:56:04Z","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/2110.15836/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in unsupervised representation learning have demonstrated the impact of pretraining on large amounts of read speech. We adapt these techniques for domain adaptation in low-resource -- both in terms of data and compute -- conversational and broadcast domains. Moving beyond CTC, we pretrain state-of-the-art Conformer models in an unsupervised manner. While the unsupervised approach outperforms traditional semi-supervised training, the techniques are complementary. Combining the techniques is a 5% absolute improvement in WER, averaged over all conditions, compared to semi-supervis","authors_text":"Chak-Fai Li, Francis Keith, Matthew Snover, William Hartmann","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T14:59:18Z","title":"Combining Unsupervised and Text Augmented Semi-Supervised Learning for Low Resourced Autoregressive Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.15836","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:a6c6d48bb70c6219fdc94f7ad995f959d6e049c66fe68ff4d2ca5b15eb5daf12","target":"record","created_at":"2026-07-05T03:56:04Z","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":"b4698e25482cb18af1e3655df168691870d4b824d7d87c5de286e793454628b2","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-29T14:59:18Z","title_canon_sha256":"1e8dbffe90735afdb46af82925c2736b502104f77e0670a0a2248021c258ed6d"},"schema_version":"1.0","source":{"id":"2110.15836","kind":"arxiv","version":2}},"canonical_sha256":"3ac05902902db1483d2cfccd8450476002871becbfde543b126d447fa795697a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ac05902902db1483d2cfccd8450476002871becbfde543b126d447fa795697a","first_computed_at":"2026-07-05T03:56:04.140058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:56:04.140058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J/qwYEsXTlADlU62u5XpJkdG5IACDzW1novEAeOQVlP5+qdJl/JzKEhAkwfK/8shZBC2aIx3qP9nB8BaP/wQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:56:04.140500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.15836","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a6c6d48bb70c6219fdc94f7ad995f959d6e049c66fe68ff4d2ca5b15eb5daf12","sha256:f993ac4653929e1710c553f2b2e23bfff3d7d8a530ca797d0c59e33992e15b59"],"state_sha256":"074f6a75a62eda642ef31bc0fefaf3c67c7af0d8b5594b8dd0b15f1be9d8baf4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J3hlWSXJqG0KKtfSbHa7vpFaDxVUzUTg49EhS5aBi0RzI6Gn5wz8McP5xhrXNGbCLuPiGlC+65jD72/sXjGJAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T19:29:51.972267Z","bundle_sha256":"85f646ad8f2db97990810a729cb946a72a068e79ac8bed873f5ae87824574330"}}