{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:PTI4SJLKECOYZFVGBLZLDC4O4F","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":"c32700ba127e7734346c830105e78ee0ec7203845707d37a34b86d955cccbea1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T15:28:49Z","title_canon_sha256":"ac6b139ccd36044f31f0ad47052f1a34c3273126c9e0c1ac61bff3dac3282587"},"schema_version":"1.0","source":{"id":"2002.12804","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.12804","created_at":"2026-07-05T00:44:34Z"},{"alias_kind":"arxiv_version","alias_value":"2002.12804v1","created_at":"2026-07-05T00:44:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.12804","created_at":"2026-07-05T00:44:34Z"},{"alias_kind":"pith_short_12","alias_value":"PTI4SJLKECOY","created_at":"2026-07-05T00:44:34Z"},{"alias_kind":"pith_short_16","alias_value":"PTI4SJLKECOYZFVG","created_at":"2026-07-05T00:44:34Z"},{"alias_kind":"pith_short_8","alias_value":"PTI4SJLK","created_at":"2026-07-05T00:44:34Z"}],"graph_snapshots":[{"event_id":"sha256:05c6de2a3936b6ae37869ea37b2f54b4557fca43a21ed2c23d7c8f19c006f2a4","target":"graph","created_at":"2026-07-05T00:44:34Z","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/2002.12804/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with masked tokens, we rely on conventional masks to learn inter-relations between corrupted tokens and context via autoencoding, and pseudo masks to learn intra-relations between masked spans via partially autoregressive modeling. With well-designed position embeddings and self-attention masks, the context encodings are reused to avoid redundant computation. Moreov","authors_text":"Furu Wei, Hangbo Bao, Hsiao-Wuen Hon, Jianfeng Gao, Li Dong, Ming Zhou, Nan Yang, Songhao Piao, Wenhui Wang, XiaoDong Liu, Yu Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T15:28:49Z","title":"UniLMv2: Pseudo-Masked Language Models for Unified Language Model Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.12804","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:d7324254d3f886df12b0994f215e6b43c643cc72ea0bdb3a87cc0ef8621ffb43","target":"record","created_at":"2026-07-05T00:44:34Z","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":"c32700ba127e7734346c830105e78ee0ec7203845707d37a34b86d955cccbea1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-28T15:28:49Z","title_canon_sha256":"ac6b139ccd36044f31f0ad47052f1a34c3273126c9e0c1ac61bff3dac3282587"},"schema_version":"1.0","source":{"id":"2002.12804","kind":"arxiv","version":1}},"canonical_sha256":"7cd1c9256a209d8c96a60af2b18b8ee14e3fb7cdd39bc151471161dd45fa4a8b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cd1c9256a209d8c96a60af2b18b8ee14e3fb7cdd39bc151471161dd45fa4a8b","first_computed_at":"2026-07-05T00:44:34.423578Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:44:34.423578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RDCqrxkzmw36v8LeQ2p2Rshb8qa/vupVUxzNqpFATd0KTXAypl/LAcZki8V63R/4zQEMjM2NZoJFXxUFZjoGDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:44:34.423953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.12804","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7324254d3f886df12b0994f215e6b43c643cc72ea0bdb3a87cc0ef8621ffb43","sha256:05c6de2a3936b6ae37869ea37b2f54b4557fca43a21ed2c23d7c8f19c006f2a4"],"state_sha256":"cab3e120edc32a35ca9c213ef1766cdde1c7f770742d358b2ceb0469fb662689"}