{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:WEERGLULX4W3KXEK2DNLUOOILF","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":"1da04fbe799423ee30b20f131ea95468607612e02cf7642c96ecf4884c74d697","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-18T16:30:26Z","title_canon_sha256":"5ac1f6b9147ccdb8087d3ac2bf4099753cacf029af30546d6295ade1021c0664"},"schema_version":"1.0","source":{"id":"2103.10360","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10360","created_at":"2026-07-05T04:05:57Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10360v2","created_at":"2026-07-05T04:05:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10360","created_at":"2026-07-05T04:05:57Z"},{"alias_kind":"pith_short_12","alias_value":"WEERGLULX4W3","created_at":"2026-07-05T04:05:57Z"},{"alias_kind":"pith_short_16","alias_value":"WEERGLULX4W3KXEK","created_at":"2026-07-05T04:05:57Z"},{"alias_kind":"pith_short_8","alias_value":"WEERGLUL","created_at":"2026-07-05T04:05:57Z"}],"graph_snapshots":[{"event_id":"sha256:9cb1e630b58686537d950ea14df92bab36cb9ee2eac9d2836607dca6c12da8ab","target":"graph","created_at":"2026-07-05T04:05:57Z","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/2103.10360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There have been various types of pretraining architectures including autoencoding models (e.g., BERT), autoregressive models (e.g., GPT), and encoder-decoder models (e.g., T5). However, none of the pretraining frameworks performs the best for all tasks of three main categories including natural language understanding (NLU), unconditional generation, and conditional generation. We propose a General Language Model (GLM) based on autoregressive blank infilling to address this challenge. GLM improves blank filling pretraining by adding 2D positional encodings and allowing an arbitrary order to pre","authors_text":"Jie Tang, Jiezhong Qiu, Ming Ding, Xiao Liu, Yujie Qian, Zhengxiao Du, Zhilin Yang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-18T16:30:26Z","title":"GLM: General Language Model Pretraining with Autoregressive Blank Infilling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10360","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":"sha256:71c4436fa0ffd0e7a728936475ed75122063e4c5153219e9d4dd83536c7d638e","target":"record","created_at":"2026-07-05T04:05:57Z","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":"1da04fbe799423ee30b20f131ea95468607612e02cf7642c96ecf4884c74d697","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-03-18T16:30:26Z","title_canon_sha256":"5ac1f6b9147ccdb8087d3ac2bf4099753cacf029af30546d6295ade1021c0664"},"schema_version":"1.0","source":{"id":"2103.10360","kind":"arxiv","version":2}},"canonical_sha256":"b109132e8bbf2db55c8ad0daba39c859435c70808e487bc51375ca19085d047e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b109132e8bbf2db55c8ad0daba39c859435c70808e487bc51375ca19085d047e","first_computed_at":"2026-07-05T04:05:57.727123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:05:57.727123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wfv2aI5YdTXGa7mAWy1PV4MhibO7gqdw/cBFasuNiJQiQxAM0LUmQMOOS4dmdrMK5I6Gl9jqzXvXoiH5jVpFCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:05:57.727608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.10360","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71c4436fa0ffd0e7a728936475ed75122063e4c5153219e9d4dd83536c7d638e","sha256:9cb1e630b58686537d950ea14df92bab36cb9ee2eac9d2836607dca6c12da8ab"],"state_sha256":"3b5b7b78ed338494855c2ab87329bc1a60c2c719afc2e9b9c87cdc2bfcced129"}