{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:7CKSWNEYUEB6S2B5TDSXBSMHHX","short_pith_number":"pith:7CKSWNEY","canonical_record":{"source":{"id":"1911.12391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-27T19:37:26Z","cross_cats_sorted":[],"title_canon_sha256":"71014959903d356d991dfa50401cfa15373621d14276076b14d4cdb6fb2dbf64","abstract_canon_sha256":"5fa78c3a8f7e07d3a6bce02e76a9b1aeb33e3039283c8e3b33438804ea62c005"},"schema_version":"1.0"},"canonical_sha256":"f8952b3498a103e9683d98e570c9873ddf39d4c02b713e9c2bddc1d2ad3b653d","source":{"kind":"arxiv","id":"1911.12391","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12391","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12391v1","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12391","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"7CKSWNEYUEB6","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"7CKSWNEYUEB6S2B5","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"7CKSWNEY","created_at":"2026-07-05T00:22:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:7CKSWNEYUEB6S2B5TDSXBSMHHX","target":"record","payload":{"canonical_record":{"source":{"id":"1911.12391","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-27T19:37:26Z","cross_cats_sorted":[],"title_canon_sha256":"71014959903d356d991dfa50401cfa15373621d14276076b14d4cdb6fb2dbf64","abstract_canon_sha256":"5fa78c3a8f7e07d3a6bce02e76a9b1aeb33e3039283c8e3b33438804ea62c005"},"schema_version":"1.0"},"canonical_sha256":"f8952b3498a103e9683d98e570c9873ddf39d4c02b713e9c2bddc1d2ad3b653d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:22:44.943181Z","signature_b64":"J9oIlkxx4Ggj1v1Zcp9IXZGy4/rtK7bwHoifhI/WRJyK4anaWjp3mb77dbMVPugoPuoTlOye0sImV3kVFKUtDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8952b3498a103e9683d98e570c9873ddf39d4c02b713e9c2bddc1d2ad3b653d","last_reissued_at":"2026-07-05T00:22:44.942736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:22:44.942736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1911.12391","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tACAIThJDKkG3mK2BS9eJjnTLJhKChzmiiHC7NX4pmAcpJHuBzAOeD3V0cdvAqD2U3cOyn7RvaMx5boRo+6VAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:18:18.272449Z"},"content_sha256":"05d42833662adc9bd32494fd05b49e6f4e69c3138929d3821ff89303e37d42a3","schema_version":"1.0","event_id":"sha256:05d42833662adc9bd32494fd05b49e6f4e69c3138929d3821ff89303e37d42a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:7CKSWNEYUEB6S2B5TDSXBSMHHX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SimpleBooks: Long-term dependency book dataset with simplified English vocabulary for word-level language modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Huyen Nguyen","submitted_at":"2019-11-27T19:37:26Z","abstract_excerpt":"With language modeling becoming the popular base task for unsupervised representation learning in Natural Language Processing, it is important to come up with new architectures and techniques for faster and better training of language models. However, due to a peculiarity of languages -- the larger the dataset, the higher the average number of times a word appears in that dataset -- datasets of different sizes have very different properties. Architectures performing well on small datasets might not perform well on larger ones. For example, LSTM models perform well on WikiText-2 but poorly on W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12391","kind":"arxiv","version":1},"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/1911.12391/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":"2026-07-05T00:22:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+rzIqFC0iRW7QWpvJeasa9DprZnXwHKZ6yJtdHMHxk8UT35yBaWyim532g9kP+d8j+CsxtPK5McFun9FkHCXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T19:18:18.273003Z"},"content_sha256":"ad179f72be254b39d7d0b04ceb8e82c261d796687696bd9bbd4a35a26376b6b4","schema_version":"1.0","event_id":"sha256:ad179f72be254b39d7d0b04ceb8e82c261d796687696bd9bbd4a35a26376b6b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX/bundle.json","state_url":"https://pith.science/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX/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":"2026-08-20T19:18:18Z","links":{"resolver":"https://pith.science/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX","bundle":"https://pith.science/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX/bundle.json","state":"https://pith.science/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7CKSWNEYUEB6S2B5TDSXBSMHHX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:7CKSWNEYUEB6S2B5TDSXBSMHHX","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":"5fa78c3a8f7e07d3a6bce02e76a9b1aeb33e3039283c8e3b33438804ea62c005","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-27T19:37:26Z","title_canon_sha256":"71014959903d356d991dfa50401cfa15373621d14276076b14d4cdb6fb2dbf64"},"schema_version":"1.0","source":{"id":"1911.12391","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1911.12391","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"arxiv_version","alias_value":"1911.12391v1","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1911.12391","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"pith_short_12","alias_value":"7CKSWNEYUEB6","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"pith_short_16","alias_value":"7CKSWNEYUEB6S2B5","created_at":"2026-07-05T00:22:44Z"},{"alias_kind":"pith_short_8","alias_value":"7CKSWNEY","created_at":"2026-07-05T00:22:44Z"}],"graph_snapshots":[{"event_id":"sha256:ad179f72be254b39d7d0b04ceb8e82c261d796687696bd9bbd4a35a26376b6b4","target":"graph","created_at":"2026-07-05T00:22:44Z","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/1911.12391/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With language modeling becoming the popular base task for unsupervised representation learning in Natural Language Processing, it is important to come up with new architectures and techniques for faster and better training of language models. However, due to a peculiarity of languages -- the larger the dataset, the higher the average number of times a word appears in that dataset -- datasets of different sizes have very different properties. Architectures performing well on small datasets might not perform well on larger ones. For example, LSTM models perform well on WikiText-2 but poorly on W","authors_text":"Huyen Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-27T19:37:26Z","title":"SimpleBooks: Long-term dependency book dataset with simplified English vocabulary for word-level language modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1911.12391","kind":"arxiv","version":1},"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":"sha256:05d42833662adc9bd32494fd05b49e6f4e69c3138929d3821ff89303e37d42a3","target":"record","created_at":"2026-07-05T00:22:44Z","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":"5fa78c3a8f7e07d3a6bce02e76a9b1aeb33e3039283c8e3b33438804ea62c005","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-11-27T19:37:26Z","title_canon_sha256":"71014959903d356d991dfa50401cfa15373621d14276076b14d4cdb6fb2dbf64"},"schema_version":"1.0","source":{"id":"1911.12391","kind":"arxiv","version":1}},"canonical_sha256":"f8952b3498a103e9683d98e570c9873ddf39d4c02b713e9c2bddc1d2ad3b653d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f8952b3498a103e9683d98e570c9873ddf39d4c02b713e9c2bddc1d2ad3b653d","first_computed_at":"2026-07-05T00:22:44.942736Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:22:44.942736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J9oIlkxx4Ggj1v1Zcp9IXZGy4/rtK7bwHoifhI/WRJyK4anaWjp3mb77dbMVPugoPuoTlOye0sImV3kVFKUtDg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:22:44.943181Z","signed_message":"canonical_sha256_bytes"},"source_id":"1911.12391","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05d42833662adc9bd32494fd05b49e6f4e69c3138929d3821ff89303e37d42a3","sha256:ad179f72be254b39d7d0b04ceb8e82c261d796687696bd9bbd4a35a26376b6b4"],"state_sha256":"4c19a03b5d5f780e9dbc0c3748f52d0ee6b77b2f3fc8abf2183f3c09415835cb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZrOYyv+rmB2pSJM8ztIC958VTTtkXWrGHtdG2yFPGgT5le0O2vqJTr0pbjScH0BzGbZFEp3vT1DYuzm5HjTJCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T19:18:18.280712Z","bundle_sha256":"483c56f13794de26182ab5a22fae69c525f94a582b78f5fa77067581ee17a122"}}