{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:5A6QK6ZCOXHHTNTFC7LHNM6VMW","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":"46b654e0ac151509ef455f2fed5fd585b3df74dcd4a80f571ab02d67520b396b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T11:50:14Z","title_canon_sha256":"baff48d913325adefa4aa6676258b3476a060b3d58a0b2c0e2e4939895f3e9ee"},"schema_version":"1.0","source":{"id":"1911.03912","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.03912","created_at":"2026-07-05T01:03:41Z"},{"alias_kind":"arxiv_version","alias_value":"1911.03912v3","created_at":"2026-07-05T01:03:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.03912","created_at":"2026-07-05T01:03:41Z"},{"alias_kind":"pith_short_12","alias_value":"5A6QK6ZCOXHH","created_at":"2026-07-05T01:03:41Z"},{"alias_kind":"pith_short_16","alias_value":"5A6QK6ZCOXHHTNTF","created_at":"2026-07-05T01:03:41Z"},{"alias_kind":"pith_short_8","alias_value":"5A6QK6ZC","created_at":"2026-07-05T01:03:41Z"}],"graph_snapshots":[{"event_id":"sha256:f68a147e2fca2701a49694381f8c5588d13bd7fa7ad4885dccb0b46eecb2ff26","target":"graph","created_at":"2026-07-05T01:03:41Z","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/1911.03912/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We compare self-supervised representation learning algorithms which either explicitly quantize the audio data or learn representations without quantization. We find the former to be more accurate since it builds a good vocabulary of the data through vq-wav2vec [1] to enable learning of effective representations in subsequent BERT training. Different to previous work, we directly fine-tune the pre-trained BERT models on transcribed speech using a Connectionist Temporal Classification (CTC) loss instead of feeding the representations into a task-specific model. We also propose a BERT-style model","authors_text":"Abdelrahman Mohamed, Alexei Baevski, Michael Auli","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T11:50:14Z","title":"Effectiveness of self-supervised pre-training for speech recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.03912","kind":"arxiv","version":3},"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":"sha256:9600e699983526e501d6f208d863fea739513ef9909f15e7efe4b8a6a100b1e7","target":"record","created_at":"2026-07-05T01:03:41Z","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":"46b654e0ac151509ef455f2fed5fd585b3df74dcd4a80f571ab02d67520b396b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-11-10T11:50:14Z","title_canon_sha256":"baff48d913325adefa4aa6676258b3476a060b3d58a0b2c0e2e4939895f3e9ee"},"schema_version":"1.0","source":{"id":"1911.03912","kind":"arxiv","version":3}},"canonical_sha256":"e83d057b2275ce79b66517d676b3d565b5a0f8b5a2b9b50084d92f12fa5ed618","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e83d057b2275ce79b66517d676b3d565b5a0f8b5a2b9b50084d92f12fa5ed618","first_computed_at":"2026-07-05T01:03:41.448355Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:03:41.448355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pdd6/7s/4+NxHswpjCR257qzw9ffDGrRGvVc8Oh1zGBDkKfFAzL1tnb2tCz+adlWph2ucicHKpPeSl8/p875AA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:03:41.448775Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.03912","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9600e699983526e501d6f208d863fea739513ef9909f15e7efe4b8a6a100b1e7","sha256:f68a147e2fca2701a49694381f8c5588d13bd7fa7ad4885dccb0b46eecb2ff26"],"state_sha256":"0cc1256e5bc48968ffcf956acddaab652b734584fe72d93e9afe6d4637c927bb"}