{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:M3GDESGWBAKBRVLHZHX7HA4GPG","short_pith_number":"pith:M3GDESGW","canonical_record":{"source":{"id":"1904.05862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-11T17:29:30Z","cross_cats_sorted":[],"title_canon_sha256":"4a611cfb1e758df6959458e3a32727c3f978a0302f86ea60074d815ac881a4d6","abstract_canon_sha256":"d0c8b69d29b59fabb959910fd128aa5176a83e0807d5976ea6d92e1ac4d011e5"},"schema_version":"1.0"},"canonical_sha256":"66cc3248d6081418d567c9eff3838679a733c392ead67700b5af9d8974d1e7f9","source":{"kind":"arxiv","id":"1904.05862","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.05862","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1904.05862v4","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05862","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"M3GDESGWBAKB","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"M3GDESGWBAKBRVLH","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"M3GDESGW","created_at":"2026-07-05T00:03:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:M3GDESGWBAKBRVLHZHX7HA4GPG","target":"record","payload":{"canonical_record":{"source":{"id":"1904.05862","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-11T17:29:30Z","cross_cats_sorted":[],"title_canon_sha256":"4a611cfb1e758df6959458e3a32727c3f978a0302f86ea60074d815ac881a4d6","abstract_canon_sha256":"d0c8b69d29b59fabb959910fd128aa5176a83e0807d5976ea6d92e1ac4d011e5"},"schema_version":"1.0"},"canonical_sha256":"66cc3248d6081418d567c9eff3838679a733c392ead67700b5af9d8974d1e7f9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:03:55.975590Z","signature_b64":"zGgUyOjWw1X4Z5FCDfQD5pLuJNCYrHy4bvw7iVzLGLytUoEsO6YqP4Th23F/ehBd29+1BIWSNlJGMiefltV6CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66cc3248d6081418d567c9eff3838679a733c392ead67700b5af9d8974d1e7f9","last_reissued_at":"2026-07-05T00:03:55.975163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:03:55.975163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.05862","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":"2026-07-05T00:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b/egh1wGNQb50LHsj4P1h5Cj0w1k2K3vHhQLA5iVx3qLiFqIwxJH+yTaWtyoC1vRc7L525apnNgv0oJVubv+Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:32:21.866720Z"},"content_sha256":"11c4e5244854d091634225ad823a12d54f40a642aeccdff549ccbcdbdc7df4b1","schema_version":"1.0","event_id":"sha256:11c4e5244854d091634225ad823a12d54f40a642aeccdff549ccbcdbdc7df4b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:M3GDESGWBAKBRVLHZHX7HA4GPG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"wav2vec: Unsupervised Pre-training for Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Michael Auli, Ronan Collobert, Steffen Schneider","submitted_at":"2019-04-11T17:29:30Z","abstract_excerpt":"We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training. We pre-train a simple multi-layer convolutional neural network optimized via a noise contrastive binary classification task. Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available. Our approach achieves 2.43% WER on the nov92 test set. This outperform"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05862","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/1904.05862/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":"2026-07-05T00:03:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BmNa60kTkW8ycTcY/p+qyQVID45vUgH7WfGTQ0BYaTD+vna5DhAvUvlIhM8h7/SNq5rfdEsdwIsmrTf/oIZ3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T20:32:21.867347Z"},"content_sha256":"cd06d205fda5202352753295d5b7bbf24940b4f8a3a8daa3894ab0e1dbdf6270","schema_version":"1.0","event_id":"sha256:cd06d205fda5202352753295d5b7bbf24940b4f8a3a8daa3894ab0e1dbdf6270"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M3GDESGWBAKBRVLHZHX7HA4GPG/bundle.json","state_url":"https://pith.science/pith/M3GDESGWBAKBRVLHZHX7HA4GPG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M3GDESGWBAKBRVLHZHX7HA4GPG/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":"2026-08-22T20:32:21Z","links":{"resolver":"https://pith.science/pith/M3GDESGWBAKBRVLHZHX7HA4GPG","bundle":"https://pith.science/pith/M3GDESGWBAKBRVLHZHX7HA4GPG/bundle.json","state":"https://pith.science/pith/M3GDESGWBAKBRVLHZHX7HA4GPG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M3GDESGWBAKBRVLHZHX7HA4GPG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:M3GDESGWBAKBRVLHZHX7HA4GPG","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":"d0c8b69d29b59fabb959910fd128aa5176a83e0807d5976ea6d92e1ac4d011e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-11T17:29:30Z","title_canon_sha256":"4a611cfb1e758df6959458e3a32727c3f978a0302f86ea60074d815ac881a4d6"},"schema_version":"1.0","source":{"id":"1904.05862","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.05862","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"arxiv_version","alias_value":"1904.05862v4","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.05862","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_12","alias_value":"M3GDESGWBAKB","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_16","alias_value":"M3GDESGWBAKBRVLH","created_at":"2026-07-05T00:03:55Z"},{"alias_kind":"pith_short_8","alias_value":"M3GDESGW","created_at":"2026-07-05T00:03:55Z"}],"graph_snapshots":[{"event_id":"sha256:cd06d205fda5202352753295d5b7bbf24940b4f8a3a8daa3894ab0e1dbdf6270","target":"graph","created_at":"2026-07-05T00:03:55Z","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/1904.05862/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore unsupervised pre-training for speech recognition by learning representations of raw audio. wav2vec is trained on large amounts of unlabeled audio data and the resulting representations are then used to improve acoustic model training. We pre-train a simple multi-layer convolutional neural network optimized via a noise contrastive binary classification task. Our experiments on WSJ reduce WER of a strong character-based log-mel filterbank baseline by up to 36% when only a few hours of transcribed data is available. Our approach achieves 2.43% WER on the nov92 test set. This outperform","authors_text":"Alexei Baevski, Michael Auli, Ronan Collobert, Steffen Schneider","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-11T17:29:30Z","title":"wav2vec: Unsupervised Pre-training for Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.05862","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":"sha256:11c4e5244854d091634225ad823a12d54f40a642aeccdff549ccbcdbdc7df4b1","target":"record","created_at":"2026-07-05T00:03:55Z","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":"d0c8b69d29b59fabb959910fd128aa5176a83e0807d5976ea6d92e1ac4d011e5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-11T17:29:30Z","title_canon_sha256":"4a611cfb1e758df6959458e3a32727c3f978a0302f86ea60074d815ac881a4d6"},"schema_version":"1.0","source":{"id":"1904.05862","kind":"arxiv","version":4}},"canonical_sha256":"66cc3248d6081418d567c9eff3838679a733c392ead67700b5af9d8974d1e7f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"66cc3248d6081418d567c9eff3838679a733c392ead67700b5af9d8974d1e7f9","first_computed_at":"2026-07-05T00:03:55.975163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:03:55.975163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zGgUyOjWw1X4Z5FCDfQD5pLuJNCYrHy4bvw7iVzLGLytUoEsO6YqP4Th23F/ehBd29+1BIWSNlJGMiefltV6CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:03:55.975590Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.05862","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11c4e5244854d091634225ad823a12d54f40a642aeccdff549ccbcdbdc7df4b1","sha256:cd06d205fda5202352753295d5b7bbf24940b4f8a3a8daa3894ab0e1dbdf6270"],"state_sha256":"e5cd735922d4ddba3234833619bb1d1f0674b8c6ef3858d4f5b35d30e598c1d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z722Bb5RsKi31bfNJs4Cd92X69EHtYWEXfHEQ/NfYpzTGQjHErrDIt0f9K3VtWQzz3S24BaKbTnjxOqZQGgcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T20:32:21.870898Z","bundle_sha256":"9340d7859754f1f15736ba057c6547a8fc3c048c23890e8132a9b5b5f9900071"}}