{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:BGF34GYB2EWE42CL7LFZSA5QGO","short_pith_number":"pith:BGF34GYB","canonical_record":{"source":{"id":"2004.09297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T13:54:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ef3b8c51239f13e6bf7459363707b47782d57af41c975dd52bf81a7a121cb070","abstract_canon_sha256":"e23180ed8728568decb43e2c269e01284a62bc1c0db64306287cb9db97155b24"},"schema_version":"1.0"},"canonical_sha256":"098bbe1b01d12c4e684bfacb9903b033b4c2fa6a35aad1e9513d748c40d50f4d","source":{"kind":"arxiv","id":"2004.09297","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.09297","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.09297v2","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09297","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_12","alias_value":"BGF34GYB2EWE","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_16","alias_value":"BGF34GYB2EWE42CL","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_8","alias_value":"BGF34GYB","created_at":"2026-07-05T01:48:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:BGF34GYB2EWE42CL7LFZSA5QGO","target":"record","payload":{"canonical_record":{"source":{"id":"2004.09297","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T13:54:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ef3b8c51239f13e6bf7459363707b47782d57af41c975dd52bf81a7a121cb070","abstract_canon_sha256":"e23180ed8728568decb43e2c269e01284a62bc1c0db64306287cb9db97155b24"},"schema_version":"1.0"},"canonical_sha256":"098bbe1b01d12c4e684bfacb9903b033b4c2fa6a35aad1e9513d748c40d50f4d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:48:08.917264Z","signature_b64":"BateFMLwxHor/0lZX1x1qdbJYb0Rj3FMN3hsN4zxbLOvZ6fJ5b+gSVlaZwOxuqIEMnwjBRWfCNEvnvrH/5PcAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"098bbe1b01d12c4e684bfacb9903b033b4c2fa6a35aad1e9513d748c40d50f4d","last_reissued_at":"2026-07-05T01:48:08.916827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:48:08.916827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.09297","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:48:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zXLaXW90E9/Npw2Vq0VbetUAjjB9QaVwoPD3sJEAevn6AB21cj6Cqz7ymFG9vqGi17y79NmEM2SnSZLkNAf9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:31:21.103728Z"},"content_sha256":"85e7a30429377e63c5d39b1b86c7436d102aeff00faff55b3528241551363a15","schema_version":"1.0","event_id":"sha256:85e7a30429377e63c5d39b1b86c7436d102aeff00faff55b3528241551363a15"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:BGF34GYB2EWE42CL7LFZSA5QGO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MPNet: Masked and Permuted Pre-training for Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jianfeng Lu, Kaitao Song, Tao Qin, Tie-Yan Liu, Xu Tan","submitted_at":"2020-04-20T13:54:12Z","abstract_excerpt":"BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to address this problem. However, XLNet does not leverage the full position information of a sentence and thus suffers from position discrepancy between pre-training and fine-tuning. In this paper, we propose MPNet, a novel pre-training method that inherits the advantages of BERT and XLNet and avoids their limitations. MPNet leverages the dependency among predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09297","kind":"arxiv","version":2},"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/2004.09297/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":"2026-07-05T01:48:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B8lkXsax/ddt3uBJ5bK6jlfz5+aFW+n4A8VDbPYfHczA7TWReJpDogx/yBRQZxRAooUJxL5MXlZ0udwvlvK7Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T23:31:21.104249Z"},"content_sha256":"bfbff764fbd8e70490dc6640f68e647d5ff7e2112cb05f939373617bb2bbc393","schema_version":"1.0","event_id":"sha256:bfbff764fbd8e70490dc6640f68e647d5ff7e2112cb05f939373617bb2bbc393"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BGF34GYB2EWE42CL7LFZSA5QGO/bundle.json","state_url":"https://pith.science/pith/BGF34GYB2EWE42CL7LFZSA5QGO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BGF34GYB2EWE42CL7LFZSA5QGO/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":"2026-08-04T23:31:21Z","links":{"resolver":"https://pith.science/pith/BGF34GYB2EWE42CL7LFZSA5QGO","bundle":"https://pith.science/pith/BGF34GYB2EWE42CL7LFZSA5QGO/bundle.json","state":"https://pith.science/pith/BGF34GYB2EWE42CL7LFZSA5QGO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BGF34GYB2EWE42CL7LFZSA5QGO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:BGF34GYB2EWE42CL7LFZSA5QGO","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":"e23180ed8728568decb43e2c269e01284a62bc1c0db64306287cb9db97155b24","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T13:54:12Z","title_canon_sha256":"ef3b8c51239f13e6bf7459363707b47782d57af41c975dd52bf81a7a121cb070"},"schema_version":"1.0","source":{"id":"2004.09297","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.09297","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"arxiv_version","alias_value":"2004.09297v2","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.09297","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_12","alias_value":"BGF34GYB2EWE","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_16","alias_value":"BGF34GYB2EWE42CL","created_at":"2026-07-05T01:48:08Z"},{"alias_kind":"pith_short_8","alias_value":"BGF34GYB","created_at":"2026-07-05T01:48:08Z"}],"graph_snapshots":[{"event_id":"sha256:bfbff764fbd8e70490dc6640f68e647d5ff7e2112cb05f939373617bb2bbc393","target":"graph","created_at":"2026-07-05T01:48:08Z","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/2004.09297/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"BERT adopts masked language modeling (MLM) for pre-training and is one of the most successful pre-training models. Since BERT neglects dependency among predicted tokens, XLNet introduces permuted language modeling (PLM) for pre-training to address this problem. However, XLNet does not leverage the full position information of a sentence and thus suffers from position discrepancy between pre-training and fine-tuning. In this paper, we propose MPNet, a novel pre-training method that inherits the advantages of BERT and XLNet and avoids their limitations. MPNet leverages the dependency among predi","authors_text":"Jianfeng Lu, Kaitao Song, Tao Qin, Tie-Yan Liu, Xu Tan","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T13:54:12Z","title":"MPNet: Masked and Permuted Pre-training for Language Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.09297","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":"sha256:85e7a30429377e63c5d39b1b86c7436d102aeff00faff55b3528241551363a15","target":"record","created_at":"2026-07-05T01:48:08Z","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":"e23180ed8728568decb43e2c269e01284a62bc1c0db64306287cb9db97155b24","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-20T13:54:12Z","title_canon_sha256":"ef3b8c51239f13e6bf7459363707b47782d57af41c975dd52bf81a7a121cb070"},"schema_version":"1.0","source":{"id":"2004.09297","kind":"arxiv","version":2}},"canonical_sha256":"098bbe1b01d12c4e684bfacb9903b033b4c2fa6a35aad1e9513d748c40d50f4d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"098bbe1b01d12c4e684bfacb9903b033b4c2fa6a35aad1e9513d748c40d50f4d","first_computed_at":"2026-07-05T01:48:08.916827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:48:08.916827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BateFMLwxHor/0lZX1x1qdbJYb0Rj3FMN3hsN4zxbLOvZ6fJ5b+gSVlaZwOxuqIEMnwjBRWfCNEvnvrH/5PcAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:48:08.917264Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.09297","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:85e7a30429377e63c5d39b1b86c7436d102aeff00faff55b3528241551363a15","sha256:bfbff764fbd8e70490dc6640f68e647d5ff7e2112cb05f939373617bb2bbc393"],"state_sha256":"1109686c26b9f01c05bda3a163790da21caafbd3c47de2606891b2f3a518db16"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u4/Um5plCPbJTUhRSOVQFXHy523qCZRYeJL0Vhrv/+c42WfR4Hwsz7ZQv1Bk4trEHQ1q1rk0pwMO6CQzf2YsBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T23:31:21.109670Z","bundle_sha256":"e3954efff19be73723b0e68112570b7546ae2d71aac35ca04391e927571d5c45"}}