{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:TF2UGIAJQADXBHAJQEU6PEMPWQ","short_pith_number":"pith:TF2UGIAJ","canonical_record":{"source":{"id":"1905.04226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-10T15:50:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d25c22a28dea0507d5b944346dcf9624013bb180dbd3e1a6c7bb0c910a1980d","abstract_canon_sha256":"9eb9e0113898c1ef70073b7b393ddc25755478049b0b3e4dfb5fb03d1a2c1a4e"},"schema_version":"1.0"},"canonical_sha256":"99754320098007709c098129e7918fb41fff8a07e7a3695ce248c9db7e3dded8","source":{"kind":"arxiv","id":"1905.04226","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04226","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04226v2","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04226","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"TF2UGIAJQADX","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"TF2UGIAJQADXBHAJ","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"TF2UGIAJ","created_at":"2026-07-05T00:06:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:TF2UGIAJQADXBHAJQEU6PEMPWQ","target":"record","payload":{"canonical_record":{"source":{"id":"1905.04226","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-10T15:50:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d25c22a28dea0507d5b944346dcf9624013bb180dbd3e1a6c7bb0c910a1980d","abstract_canon_sha256":"9eb9e0113898c1ef70073b7b393ddc25755478049b0b3e4dfb5fb03d1a2c1a4e"},"schema_version":"1.0"},"canonical_sha256":"99754320098007709c098129e7918fb41fff8a07e7a3695ce248c9db7e3dded8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:06:43.336776Z","signature_b64":"3D1PRK/wYNgH4aLOzNhvy9m1B0vO5TUU3/nXeSWW2EUSSKYz1tsyg48IU/7O0pEGy7wRWJdE+KIKOTPbcFyzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99754320098007709c098129e7918fb41fff8a07e7a3695ce248c9db7e3dded8","last_reissued_at":"2026-07-05T00:06:43.336302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:06:43.336302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.04226","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":"2026-07-05T00:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Qee6665/Dvy4NbQ6nv09RhG2DU/BLbwpuBFhwRZLASlnXkadj+5GihRSZTikZm7GTJxxd2qNRXUY/+Kw3tKiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:15:52.976159Z"},"content_sha256":"32dbaa9f9178e21dfe2754d710feda1dbc0adfdaeb93288ac1144a950c547ee8","schema_version":"1.0","event_id":"sha256:32dbaa9f9178e21dfe2754d710feda1dbc0adfdaeb93288ac1144a950c547ee8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:TF2UGIAJQADXBHAJQEU6PEMPWQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Modeling with Deep Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Albert Zeyer, Hermann Ney, Kazuki Irie, Ralf Schl\\\"uter","submitted_at":"2019-05-10T15:50:00Z","abstract_excerpt":"We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured Transformer models outperform our baseline models based on the shallow stack of LSTM recurrent neural network layers. We carry out experiments on the open-source LibriSpeech 960hr task, for both 200K vocabulary word-level and 10K byte-pair encoding subword-level language modeling. We apply our word-level models to conventional hybrid speech recognition by lattic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04226","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/1905.04226/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":"2026-07-05T00:06:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YQbBJLXW8Xt3dX8JDD32a3iLXka6LDkDxKDEMra0vkd25KCuZiCMtd1iN65bJlU93U9yE9KbPCVkf1shgItHDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:15:52.976690Z"},"content_sha256":"b5409d99cb8bbd75c9400c92c7a6f6693f37b872d99b581fd6389b60ed174696","schema_version":"1.0","event_id":"sha256:b5409d99cb8bbd75c9400c92c7a6f6693f37b872d99b581fd6389b60ed174696"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ/bundle.json","state_url":"https://pith.science/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ/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":"2026-08-07T22:15:52Z","links":{"resolver":"https://pith.science/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ","bundle":"https://pith.science/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ/bundle.json","state":"https://pith.science/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TF2UGIAJQADXBHAJQEU6PEMPWQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:TF2UGIAJQADXBHAJQEU6PEMPWQ","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":"9eb9e0113898c1ef70073b7b393ddc25755478049b0b3e4dfb5fb03d1a2c1a4e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-10T15:50:00Z","title_canon_sha256":"9d25c22a28dea0507d5b944346dcf9624013bb180dbd3e1a6c7bb0c910a1980d"},"schema_version":"1.0","source":{"id":"1905.04226","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.04226","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"arxiv_version","alias_value":"1905.04226v2","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.04226","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"pith_short_12","alias_value":"TF2UGIAJQADX","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"pith_short_16","alias_value":"TF2UGIAJQADXBHAJ","created_at":"2026-07-05T00:06:43Z"},{"alias_kind":"pith_short_8","alias_value":"TF2UGIAJ","created_at":"2026-07-05T00:06:43Z"}],"graph_snapshots":[{"event_id":"sha256:b5409d99cb8bbd75c9400c92c7a6f6693f37b872d99b581fd6389b60ed174696","target":"graph","created_at":"2026-07-05T00:06:43Z","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/1905.04226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We explore deep autoregressive Transformer models in language modeling for speech recognition. We focus on two aspects. First, we revisit Transformer model configurations specifically for language modeling. We show that well configured Transformer models outperform our baseline models based on the shallow stack of LSTM recurrent neural network layers. We carry out experiments on the open-source LibriSpeech 960hr task, for both 200K vocabulary word-level and 10K byte-pair encoding subword-level language modeling. We apply our word-level models to conventional hybrid speech recognition by lattic","authors_text":"Albert Zeyer, Hermann Ney, Kazuki Irie, Ralf Schl\\\"uter","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-10T15:50:00Z","title":"Language Modeling with Deep Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.04226","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":"sha256:32dbaa9f9178e21dfe2754d710feda1dbc0adfdaeb93288ac1144a950c547ee8","target":"record","created_at":"2026-07-05T00:06:43Z","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":"9eb9e0113898c1ef70073b7b393ddc25755478049b0b3e4dfb5fb03d1a2c1a4e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-10T15:50:00Z","title_canon_sha256":"9d25c22a28dea0507d5b944346dcf9624013bb180dbd3e1a6c7bb0c910a1980d"},"schema_version":"1.0","source":{"id":"1905.04226","kind":"arxiv","version":2}},"canonical_sha256":"99754320098007709c098129e7918fb41fff8a07e7a3695ce248c9db7e3dded8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99754320098007709c098129e7918fb41fff8a07e7a3695ce248c9db7e3dded8","first_computed_at":"2026-07-05T00:06:43.336302Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:06:43.336302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3D1PRK/wYNgH4aLOzNhvy9m1B0vO5TUU3/nXeSWW2EUSSKYz1tsyg48IU/7O0pEGy7wRWJdE+KIKOTPbcFyzDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:06:43.336776Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.04226","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32dbaa9f9178e21dfe2754d710feda1dbc0adfdaeb93288ac1144a950c547ee8","sha256:b5409d99cb8bbd75c9400c92c7a6f6693f37b872d99b581fd6389b60ed174696"],"state_sha256":"87d6d96b506c1a7ba17c0866a725ca5b4291f4c17e20977db933b9a9d57548bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EWD0tIYkMX4piW4dK062n8RoQG+93ICXxRkX+frpNFvnvsMdBAbOHfq7UQvcqRBsTt2mKSctungQ7KlBcqe/Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:15:52.983383Z","bundle_sha256":"f09703fb4f17662ccca468b2d959b77663583fd1312141248a4c25e203b7ba01"}}