{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GVUHADJMUCNS7GKGCD26PB7W6E","short_pith_number":"pith:GVUHADJM","canonical_record":{"source":{"id":"2404.07341","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T20:40:24Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"66caf5ffe8cfcf39f834fe51a7b2d94f9544ae24f291d314c40644553672a471","abstract_canon_sha256":"d983f1de9b784f520ef0a71f35960d70c373487028a34c821714031ed22644a2"},"schema_version":"1.0"},"canonical_sha256":"3568700d2ca09b2f994610f5e787f6f12aa193b3c7eab3a4f277bc6f76861126","source":{"kind":"arxiv","id":"2404.07341","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07341","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07341v2","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07341","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"GVUHADJMUCNS","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"GVUHADJMUCNS7GKG","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"GVUHADJM","created_at":"2026-07-05T08:07:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GVUHADJMUCNS7GKGCD26PB7W6E","target":"record","payload":{"canonical_record":{"source":{"id":"2404.07341","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T20:40:24Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"66caf5ffe8cfcf39f834fe51a7b2d94f9544ae24f291d314c40644553672a471","abstract_canon_sha256":"d983f1de9b784f520ef0a71f35960d70c373487028a34c821714031ed22644a2"},"schema_version":"1.0"},"canonical_sha256":"3568700d2ca09b2f994610f5e787f6f12aa193b3c7eab3a4f277bc6f76861126","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:07:37.314301Z","signature_b64":"CIUK3mW21HTyegfq2cusB/8O8bWb317Wwbqc2YF7ihebv9Cq2zq0OXFQcYrFkUgSPtbw67LbPjzeZr93mqULAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3568700d2ca09b2f994610f5e787f6f12aa193b3c7eab3a4f277bc6f76861126","last_reissued_at":"2026-07-05T08:07:37.313823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:07:37.313823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.07341","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":"2026-07-05T08:07:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g856Ue9YPvuJYccrlcY3s3a0AYD6pQF1YCYE4Us7l/ljZc7YY5VOTrCql3BAZzqZ2ha2kWqVKJaavKHT7hZoCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:55:18.408209Z"},"content_sha256":"438d835367b6d1abbe44fb1f8f26552b54a652a1fac8176fed66c42a2c0640a3","schema_version":"1.0","event_id":"sha256:438d835367b6d1abbe44fb1f8f26552b54a652a1fac8176fed66c42a2c0640a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GVUHADJMUCNS7GKGCD26PB7W6E","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Andrea Vanzo, Dillon Pulliam, Domenic Donato, Francis McCann Ramirez, Gabriel Oexle, Kevin Zhang, Luka Chkhetiani, Michael Liang, Michael Nguyen, Ruben Bousbib, Sergio Ramirez Martin, Taufiquzzaman Peyash, Yash Khare","submitted_at":"2024-04-10T20:40:24Z","abstract_excerpt":"This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we perform Noisy Student Training after generating pseudo-labels for the unlabeled public data using a strong Conformer RNN-T baseline model. The addition of these pseudo-labeled data results in remarkable improvements in relative Word Error Rate (WER) by 11.5% and 24.3% for our asynchronous and realtime models, respectively. Additionally, the model is more robust t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07341","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/2404.07341/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":"2026-07-05T08:07:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sRvg1kNy3XYPDHOxsReNvxbN8M0IoHEHmmIFgsi4JjVQbPWKb/IbitzUelPel22dUG1PzjOLH6kZ+gQAzeyfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:55:18.409068Z"},"content_sha256":"b7d2bd0373f84112925711add8db6e63321a2c364693b936da7158f77c8dd2bf","schema_version":"1.0","event_id":"sha256:b7d2bd0373f84112925711add8db6e63321a2c364693b936da7158f77c8dd2bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVUHADJMUCNS7GKGCD26PB7W6E/bundle.json","state_url":"https://pith.science/pith/GVUHADJMUCNS7GKGCD26PB7W6E/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVUHADJMUCNS7GKGCD26PB7W6E/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":"2026-08-08T11:55:18Z","links":{"resolver":"https://pith.science/pith/GVUHADJMUCNS7GKGCD26PB7W6E","bundle":"https://pith.science/pith/GVUHADJMUCNS7GKGCD26PB7W6E/bundle.json","state":"https://pith.science/pith/GVUHADJMUCNS7GKGCD26PB7W6E/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVUHADJMUCNS7GKGCD26PB7W6E/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GVUHADJMUCNS7GKGCD26PB7W6E","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":"d983f1de9b784f520ef0a71f35960d70c373487028a34c821714031ed22644a2","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T20:40:24Z","title_canon_sha256":"66caf5ffe8cfcf39f834fe51a7b2d94f9544ae24f291d314c40644553672a471"},"schema_version":"1.0","source":{"id":"2404.07341","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.07341","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"arxiv_version","alias_value":"2404.07341v2","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07341","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"pith_short_12","alias_value":"GVUHADJMUCNS","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"pith_short_16","alias_value":"GVUHADJMUCNS7GKG","created_at":"2026-07-05T08:07:37Z"},{"alias_kind":"pith_short_8","alias_value":"GVUHADJM","created_at":"2026-07-05T08:07:37Z"}],"graph_snapshots":[{"event_id":"sha256:b7d2bd0373f84112925711add8db6e63321a2c364693b936da7158f77c8dd2bf","target":"graph","created_at":"2026-07-05T08:07:37Z","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/2404.07341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents Conformer-1, an end-to-end Automatic Speech Recognition (ASR) model trained on an extensive dataset of 570k hours of speech audio data, 91% of which was acquired from publicly available sources. To achieve this, we perform Noisy Student Training after generating pseudo-labels for the unlabeled public data using a strong Conformer RNN-T baseline model. The addition of these pseudo-labeled data results in remarkable improvements in relative Word Error Rate (WER) by 11.5% and 24.3% for our asynchronous and realtime models, respectively. Additionally, the model is more robust t","authors_text":"Andrea Vanzo, Dillon Pulliam, Domenic Donato, Francis McCann Ramirez, Gabriel Oexle, Kevin Zhang, Luka Chkhetiani, Michael Liang, Michael Nguyen, Ruben Bousbib, Sergio Ramirez Martin, Taufiquzzaman Peyash, Yash Khare","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T20:40:24Z","title":"Conformer-1: Robust ASR via Large-Scale Semisupervised Bootstrapping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07341","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":"sha256:438d835367b6d1abbe44fb1f8f26552b54a652a1fac8176fed66c42a2c0640a3","target":"record","created_at":"2026-07-05T08:07:37Z","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":"d983f1de9b784f520ef0a71f35960d70c373487028a34c821714031ed22644a2","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-04-10T20:40:24Z","title_canon_sha256":"66caf5ffe8cfcf39f834fe51a7b2d94f9544ae24f291d314c40644553672a471"},"schema_version":"1.0","source":{"id":"2404.07341","kind":"arxiv","version":2}},"canonical_sha256":"3568700d2ca09b2f994610f5e787f6f12aa193b3c7eab3a4f277bc6f76861126","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3568700d2ca09b2f994610f5e787f6f12aa193b3c7eab3a4f277bc6f76861126","first_computed_at":"2026-07-05T08:07:37.313823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:07:37.313823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CIUK3mW21HTyegfq2cusB/8O8bWb317Wwbqc2YF7ihebv9Cq2zq0OXFQcYrFkUgSPtbw67LbPjzeZr93mqULAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:07:37.314301Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.07341","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:438d835367b6d1abbe44fb1f8f26552b54a652a1fac8176fed66c42a2c0640a3","sha256:b7d2bd0373f84112925711add8db6e63321a2c364693b936da7158f77c8dd2bf"],"state_sha256":"d95dfda51bcba4c6098bd0b2418f9b9b8bf612f3133c072568c5b989bd802474"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NQg7qBhA0EoWN5HvuxMIYpQ/Sx4BpF1L1SO8fhv0FLlkxzZIsLNHND+Ys5vMcDfsEiIfjOPSQyJ0p0f3hyUFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:55:18.413190Z","bundle_sha256":"133fed70e1567c7e0ec5d76e93952cf865ff35de03e240f5d41c2757cea06c80"}}