{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:T5KOPKEZIJ6S2LTOYXOLAM5LEF","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":"f67a7da9ec1557d4bcdb92241a3a2dbf8f302d96f7e6214d9ad4deba54a472c9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-14T23:21:56Z","title_canon_sha256":"4d82a6dac14dec501e2f810d5bd037700d9c90d9e412024e1d2d1a4c5d3d7e1b"},"schema_version":"1.0","source":{"id":"1909.06695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.06695","created_at":"2026-07-05T00:04:48Z"},{"alias_kind":"arxiv_version","alias_value":"1909.06695v1","created_at":"2026-07-05T00:04:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.06695","created_at":"2026-07-05T00:04:48Z"},{"alias_kind":"pith_short_12","alias_value":"T5KOPKEZIJ6S","created_at":"2026-07-05T00:04:48Z"},{"alias_kind":"pith_short_16","alias_value":"T5KOPKEZIJ6S2LTO","created_at":"2026-07-05T00:04:48Z"},{"alias_kind":"pith_short_8","alias_value":"T5KOPKEZ","created_at":"2026-07-05T00:04:48Z"}],"graph_snapshots":[{"event_id":"sha256:f2468293c259c9c746fe094312b2e4232a457be6fdeeca7393c9ac0be535036e","target":"graph","created_at":"2026-07-05T00:04:48Z","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/1909.06695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models are essential for natural language processing (NLP) tasks, such as machine translation and text summarization. Remarkable performance has been demonstrated recently across many NLP domains via a Transformer-based language model with over a billion parameters, verifying the benefits of model size. Model parallelism is required if a model is too large to fit in a single computing device. Current methods for model parallelism either suffer from backward locking in backpropagation or are not applicable to language models. We propose the first model-parallel algorithm that speeds th","authors_text":"Heng Huang, Lawrence Carin, Qian Yang, Wenlin Wang, Zhouyuan Huo","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-14T23:21:56Z","title":"Ouroboros: On Accelerating Training of Transformer-Based Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.06695","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:fff5ba65b6b9155b5c744ec61194ceca2d0bb279f78bbaf1ad79366ecdede567","target":"record","created_at":"2026-07-05T00:04:48Z","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":"f67a7da9ec1557d4bcdb92241a3a2dbf8f302d96f7e6214d9ad4deba54a472c9","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-14T23:21:56Z","title_canon_sha256":"4d82a6dac14dec501e2f810d5bd037700d9c90d9e412024e1d2d1a4c5d3d7e1b"},"schema_version":"1.0","source":{"id":"1909.06695","kind":"arxiv","version":1}},"canonical_sha256":"9f54e7a899427d2d2e6ec5dcb033ab216be64712864a2d2f473692905989a9c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f54e7a899427d2d2e6ec5dcb033ab216be64712864a2d2f473692905989a9c7","first_computed_at":"2026-07-05T00:04:48.743399Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:04:48.743399Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hNVzwAHGoXXq1thBR0t+sVWLNDWR9hZnfbsxIFC2h+fNBN8fXXh1eGEy2eLiXq2EmhNCQvwZXkDREHUNXE12Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:04:48.744024Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.06695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fff5ba65b6b9155b5c744ec61194ceca2d0bb279f78bbaf1ad79366ecdede567","sha256:f2468293c259c9c746fe094312b2e4232a457be6fdeeca7393c9ac0be535036e"],"state_sha256":"81bffc78044681fa0b427cade9e57b6f8078fc0c3c6ee86aab695647238a5d19"}