{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X6Y4EP2L4I7447T77ALCNWMSUX","short_pith_number":"pith:X6Y4EP2L","canonical_record":{"source":{"id":"1905.03197","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T16:33:51Z","cross_cats_sorted":[],"title_canon_sha256":"2514f1db36b89ff10e5baf58e06b48cb0eb9a81fbccd53c0c8b61bd13135585f","abstract_canon_sha256":"1eae07da2cf3572311506acc8e637b099e8b61089a8f2fb46f10dc3f1bc0c8a7"},"schema_version":"1.0"},"canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","source":{"kind":"arxiv","id":"1905.03197","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03197","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03197v3","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03197","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"X6Y4EP2L4I74","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"X6Y4EP2L4I7447T7","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"X6Y4EP2L","created_at":"2026-07-05T00:11:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X6Y4EP2L4I7447T77ALCNWMSUX","target":"record","payload":{"canonical_record":{"source":{"id":"1905.03197","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T16:33:51Z","cross_cats_sorted":[],"title_canon_sha256":"2514f1db36b89ff10e5baf58e06b48cb0eb9a81fbccd53c0c8b61bd13135585f","abstract_canon_sha256":"1eae07da2cf3572311506acc8e637b099e8b61089a8f2fb46f10dc3f1bc0c8a7"},"schema_version":"1.0"},"canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:11:59.460447Z","signature_b64":"xyNEDj43QVHJg+cJGMSG92tlY85QAxeMoP3i50v4UVf0A+6tupPRBnf7X0h6OjGQyFdAEGjqyXEY+HyhHu4cCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","last_reissued_at":"2026-07-05T00:11:59.459979Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:11:59.459979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.03197","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"odYzz64dVR01vSTtB1a/0ugOH4l4DuWyVyz88ACSePxCVXbKu2ZRW35zS1FUSDbii5MbBQ4PDcGuFfUN5iVMCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:48:25.001237Z"},"content_sha256":"dc77ff65071d23d9a003854b214a96b2fd4379e108e66792983d199ab7918906","schema_version":"1.0","event_id":"sha256:dc77ff65071d23d9a003854b214a96b2fd4379e108e66792983d199ab7918906"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X6Y4EP2L4I7447T77ALCNWMSUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unified Language Model Pre-training for Natural Language Understanding and Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Hsiao-Wuen Hon, Jianfeng Gao, Li Dong, Ming Zhou, Nan Yang, Wenhui Wang, XiaoDong Liu, Yu Wang","submitted_at":"2019-05-08T16:33:51Z","abstract_excerpt":"This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03197","kind":"arxiv","version":3},"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/1905.03197/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":"2026-07-05T00:11:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mQDFvCBmwyB9BpK5HYoCRFno71B9iShiqbqwDeABI+DF5C3LII3UijxtR4TyES2dQGrn5+Mwy+NAtXqdTV8KAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:48:25.001639Z"},"content_sha256":"6609465a5f1f629026a6aec6e4271431d3ce6c322724a49a9716529d045a539b","schema_version":"1.0","event_id":"sha256:6609465a5f1f629026a6aec6e4271431d3ce6c322724a49a9716529d045a539b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/bundle.json","state_url":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X6Y4EP2L4I7447T77ALCNWMSUX/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":"2026-07-06T15:48:25Z","links":{"resolver":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX","bundle":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/bundle.json","state":"https://pith.science/pith/X6Y4EP2L4I7447T77ALCNWMSUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X6Y4EP2L4I7447T77ALCNWMSUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X6Y4EP2L4I7447T77ALCNWMSUX","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":"1eae07da2cf3572311506acc8e637b099e8b61089a8f2fb46f10dc3f1bc0c8a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T16:33:51Z","title_canon_sha256":"2514f1db36b89ff10e5baf58e06b48cb0eb9a81fbccd53c0c8b61bd13135585f"},"schema_version":"1.0","source":{"id":"1905.03197","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.03197","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"arxiv_version","alias_value":"1905.03197v3","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.03197","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"pith_short_12","alias_value":"X6Y4EP2L4I74","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"pith_short_16","alias_value":"X6Y4EP2L4I7447T7","created_at":"2026-07-05T00:11:59Z"},{"alias_kind":"pith_short_8","alias_value":"X6Y4EP2L","created_at":"2026-07-05T00:11:59Z"}],"graph_snapshots":[{"event_id":"sha256:6609465a5f1f629026a6aec6e4271431d3ce6c322724a49a9716529d045a539b","target":"graph","created_at":"2026-07-05T00:11:59Z","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/1905.03197/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieve","authors_text":"Furu Wei, Hsiao-Wuen Hon, Jianfeng Gao, Li Dong, Ming Zhou, Nan Yang, Wenhui Wang, XiaoDong Liu, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T16:33:51Z","title":"Unified Language Model Pre-training for Natural Language Understanding and Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.03197","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:dc77ff65071d23d9a003854b214a96b2fd4379e108e66792983d199ab7918906","target":"record","created_at":"2026-07-05T00:11:59Z","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":"1eae07da2cf3572311506acc8e637b099e8b61089a8f2fb46f10dc3f1bc0c8a7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-08T16:33:51Z","title_canon_sha256":"2514f1db36b89ff10e5baf58e06b48cb0eb9a81fbccd53c0c8b61bd13135585f"},"schema_version":"1.0","source":{"id":"1905.03197","kind":"arxiv","version":3}},"canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bfb1c23f4be23fce7e7ff81626d992a5f4414e5c019b81032cefcb9b65fcae30","first_computed_at":"2026-07-05T00:11:59.459979Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:11:59.459979Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xyNEDj43QVHJg+cJGMSG92tlY85QAxeMoP3i50v4UVf0A+6tupPRBnf7X0h6OjGQyFdAEGjqyXEY+HyhHu4cCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:11:59.460447Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.03197","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc77ff65071d23d9a003854b214a96b2fd4379e108e66792983d199ab7918906","sha256:6609465a5f1f629026a6aec6e4271431d3ce6c322724a49a9716529d045a539b"],"state_sha256":"3805b5360996addde7c957e72d8f48ed9bde18a10240544a906b16cd93c1260b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yIBV0hNmoW1yqReufmmhAnYqUHk/lzDL/iBwdQwoYfkQs/tnQmJshx/WlT6E0Hw+A2s76j+iJ7Iuf46oAlygBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:48:25.004196Z","bundle_sha256":"0ecd7a191b3c53a36de3a8d68fce17f6aaeb19914cc276636dca44aaf3ca2d39"}}