{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QI4LUU5USTPDG6H42MC2KGW75A","short_pith_number":"pith:QI4LUU5U","canonical_record":{"source":{"id":"2409.14494","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T19:14:18Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b03068842492805aa5289b9aabaf0d8a259fdbad115509bce3e781480ab85ef7","abstract_canon_sha256":"3da31570c48ffc2c7106bf50e1ea49fa4003add3538f405653ef84afc833ad5f"},"schema_version":"1.0"},"canonical_sha256":"8238ba53b494de3378fcd305a51adfe83820e573ef19da01513ae591769e4734","source":{"kind":"arxiv","id":"2409.14494","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14494","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14494v4","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14494","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"pith_short_12","alias_value":"QI4LUU5USTPD","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"pith_short_16","alias_value":"QI4LUU5USTPDG6H4","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"pith_short_8","alias_value":"QI4LUU5U","created_at":"2026-07-05T10:29:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QI4LUU5USTPDG6H42MC2KGW75A","target":"record","payload":{"canonical_record":{"source":{"id":"2409.14494","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T19:14:18Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"b03068842492805aa5289b9aabaf0d8a259fdbad115509bce3e781480ab85ef7","abstract_canon_sha256":"3da31570c48ffc2c7106bf50e1ea49fa4003add3538f405653ef84afc833ad5f"},"schema_version":"1.0"},"canonical_sha256":"8238ba53b494de3378fcd305a51adfe83820e573ef19da01513ae591769e4734","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:23.449514Z","signature_b64":"boSpL0kug3Xd5lXGJ/uTlXHGAQSYl90bb7PAYvrDxw6xAyUNGbmIt+E3YykFMremUWOEjCAmEjK86dFNGsPSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8238ba53b494de3378fcd305a51adfe83820e573ef19da01513ae591769e4734","last_reissued_at":"2026-07-05T10:29:23.449014Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:23.449014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.14494","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:29:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v+7IlPI84H41CbW5pOdB8CNntm6zPnTUA3KRYyTlFX/sm7XDVdiG9dW4kN9nOLcRtHZEyybxK4AUpPxLYY2dBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:38:18.923292Z"},"content_sha256":"17fa27f8fdf8b1b14ec98f3bd4c6b741cd4b86bffb355bb66f02a9f84ef199a4","schema_version":"1.0","event_id":"sha256:17fa27f8fdf8b1b14ec98f3bd4c6b741cd4b86bffb355bb66f02a9f84ef199a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QI4LUU5USTPDG6H42MC2KGW75A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Ahmed Adel Attia, Carol Espy-Wilson, Dorottya Demszky, Jing Liu, Tolulope Ogunremi","submitted_at":"2024-09-13T19:14:18Z","abstract_excerpt":"Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining (CPT) in adapting Wav2vec2.0 to the classroom domain. We show that CPT is a powerful tool in that regard and reduces the Word Error Rate (WER) of Wav2vec2.0-based models by upwards of 10%. More specifically, CPT improves the model's robustness to different noises, microphones and classroom conditions."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14494","kind":"arxiv","version":4},"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/2409.14494/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":"2026-07-05T10:29:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+pu4KuoJBtK3f0/8wqqZMA3oZmoEGql+Nq/TabI8hsZ2VBmYaCEvLqK/Sq60JgAvvzPWl2wYbMbE/QChM5xqBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:38:18.923800Z"},"content_sha256":"b0d1115f49276dbf40999c545fa6fb69762d8432d649744d04b6865436948818","schema_version":"1.0","event_id":"sha256:b0d1115f49276dbf40999c545fa6fb69762d8432d649744d04b6865436948818"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QI4LUU5USTPDG6H42MC2KGW75A/bundle.json","state_url":"https://pith.science/pith/QI4LUU5USTPDG6H42MC2KGW75A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QI4LUU5USTPDG6H42MC2KGW75A/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":"2026-08-08T18:38:18Z","links":{"resolver":"https://pith.science/pith/QI4LUU5USTPDG6H42MC2KGW75A","bundle":"https://pith.science/pith/QI4LUU5USTPDG6H42MC2KGW75A/bundle.json","state":"https://pith.science/pith/QI4LUU5USTPDG6H42MC2KGW75A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QI4LUU5USTPDG6H42MC2KGW75A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QI4LUU5USTPDG6H42MC2KGW75A","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":"3da31570c48ffc2c7106bf50e1ea49fa4003add3538f405653ef84afc833ad5f","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T19:14:18Z","title_canon_sha256":"b03068842492805aa5289b9aabaf0d8a259fdbad115509bce3e781480ab85ef7"},"schema_version":"1.0","source":{"id":"2409.14494","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.14494","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.14494v4","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14494","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"pith_short_12","alias_value":"QI4LUU5USTPD","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"pith_short_16","alias_value":"QI4LUU5USTPDG6H4","created_at":"2026-07-05T10:29:23Z"},{"alias_kind":"pith_short_8","alias_value":"QI4LUU5U","created_at":"2026-07-05T10:29:23Z"}],"graph_snapshots":[{"event_id":"sha256:b0d1115f49276dbf40999c545fa6fb69762d8432d649744d04b6865436948818","target":"graph","created_at":"2026-07-05T10:29:23Z","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/2409.14494/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Creating Automatic Speech Recognition (ASR) systems that are robust and resilient to classroom conditions is paramount to the development of AI tools to aid teachers and students. In this work, we study the efficacy of continued pretraining (CPT) in adapting Wav2vec2.0 to the classroom domain. We show that CPT is a powerful tool in that regard and reduces the Word Error Rate (WER) of Wav2vec2.0-based models by upwards of 10%. More specifically, CPT improves the model's robustness to different noises, microphones and classroom conditions.","authors_text":"Ahmed Adel Attia, Carol Espy-Wilson, Dorottya Demszky, Jing Liu, Tolulope Ogunremi","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T19:14:18Z","title":"CPT-Boosted Wav2vec2.0: Towards Noise Robust Speech Recognition for Classroom Environments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14494","kind":"arxiv","version":4},"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":"sha256:17fa27f8fdf8b1b14ec98f3bd4c6b741cd4b86bffb355bb66f02a9f84ef199a4","target":"record","created_at":"2026-07-05T10:29:23Z","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":"3da31570c48ffc2c7106bf50e1ea49fa4003add3538f405653ef84afc833ad5f","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-13T19:14:18Z","title_canon_sha256":"b03068842492805aa5289b9aabaf0d8a259fdbad115509bce3e781480ab85ef7"},"schema_version":"1.0","source":{"id":"2409.14494","kind":"arxiv","version":4}},"canonical_sha256":"8238ba53b494de3378fcd305a51adfe83820e573ef19da01513ae591769e4734","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8238ba53b494de3378fcd305a51adfe83820e573ef19da01513ae591769e4734","first_computed_at":"2026-07-05T10:29:23.449014Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:29:23.449014Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"boSpL0kug3Xd5lXGJ/uTlXHGAQSYl90bb7PAYvrDxw6xAyUNGbmIt+E3YykFMremUWOEjCAmEjK86dFNGsPSCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:29:23.449514Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.14494","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:17fa27f8fdf8b1b14ec98f3bd4c6b741cd4b86bffb355bb66f02a9f84ef199a4","sha256:b0d1115f49276dbf40999c545fa6fb69762d8432d649744d04b6865436948818"],"state_sha256":"f907afbc7276b43bb2a36dde8722d29f798741ab59a60a64a77273e8dd0e0357"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H/bd0mnNNI7U1BfR3xumpea3DG7ki5hK6DFZd9HEND50cLvhkYRGWO7KbWsl+e10LcTAckhUJ00/oIyM+mR7Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:38:18.928082Z","bundle_sha256":"28c142cd9d5cf3e50953525fced24438397a486ae74a14da9081d6318e9540e6"}}