{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UOEYCMKSCMVHMHK7LQSP7KSEE6","short_pith_number":"pith:UOEYCMKS","canonical_record":{"source":{"id":"2204.06644","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T21:39:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a9f27c19e3333562bcca50fb6f207c88ede9b05807d871e729d75faa12a730cf","abstract_canon_sha256":"3792bece98dcf1dc834b77b7d01b05fb70ad27b49f2fd184d08e88a8d5406b12"},"schema_version":"1.0"},"canonical_sha256":"a389813152132a761d5f5c24ffaa4427b89731ae544d5f8524b70c569a78dee2","source":{"kind":"arxiv","id":"2204.06644","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06644","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06644v2","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06644","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"UOEYCMKSCMVH","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"UOEYCMKSCMVHMHK7","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"UOEYCMKS","created_at":"2026-07-05T04:15:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UOEYCMKSCMVHMHK7LQSP7KSEE6","target":"record","payload":{"canonical_record":{"source":{"id":"2204.06644","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T21:39:15Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a9f27c19e3333562bcca50fb6f207c88ede9b05807d871e729d75faa12a730cf","abstract_canon_sha256":"3792bece98dcf1dc834b77b7d01b05fb70ad27b49f2fd184d08e88a8d5406b12"},"schema_version":"1.0"},"canonical_sha256":"a389813152132a761d5f5c24ffaa4427b89731ae544d5f8524b70c569a78dee2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:15:16.088491Z","signature_b64":"B6/Rv6JVwfTCLPZzrtml8qBv/HQpsYv7WwDOWpjFnvVItatS1WE8hS/EcRcN8EKfS3k+VyUKLXujcs3wLBcUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a389813152132a761d5f5c24ffaa4427b89731ae544d5f8524b70c569a78dee2","last_reissued_at":"2026-07-05T04:15:16.088042Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:15:16.088042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.06644","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":"2026-07-05T04:15:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p6EJyh0OmmBhBbF/weHNC0q5hRn56Z/6HYEDG8AqsBgaKVlC2V1++Jmlgl3m3mjZQsWBV++uDc/Bvg8EmqgsAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:03:24.262922Z"},"content_sha256":"ede186f7930880cc541aa3ce7f83b752b407d9e50b610052e2fbda0ed2f3d754","schema_version":"1.0","event_id":"sha256:ede186f7930880cc541aa3ce7f83b752b407d9e50b610052e2fbda0ed2f3d754"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UOEYCMKSCMVHMHK7LQSP7KSEE6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Chenyan Xiong, Di He, Guolin Ke, Jianfeng Gao, Paul Bennett, Payal Bajaj, Saurabh Tiwary, Tie-Yan Liu, XiaoDong Liu, Xia Song","submitted_at":"2022-04-13T21:39:15Z","abstract_excerpt":"We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. Originated in ELECTRA, this training strategy has demonstrated sample-efficiency to pretrain models at the scale of hundreds of millions of parameters. In this work, we conduct a comprehensive empirical study, and propose a recipe, namely \"Model generated dEnoising TRaining Objective\" (METRO), which incorporates some of the best modeling techniques developed recently to speed up, stabilize, and enhance pretrained language models without compromising mod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06644","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/2204.06644/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":"2026-07-05T04:15:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/UEcRcCWphFtgry/m/27GEXLDckk/8e0k6HFLWF+En0aVCHic9gqWs5R106N1bkVEa1dl8QYuDt0Y5yREdA6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T12:03:24.263219Z"},"content_sha256":"3661aae7d96e6c548bb66bba71bd1fea5564e318da18189fdf72a55253864123","schema_version":"1.0","event_id":"sha256:3661aae7d96e6c548bb66bba71bd1fea5564e318da18189fdf72a55253864123"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6/bundle.json","state_url":"https://pith.science/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6/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":"2026-08-05T12:03:24Z","links":{"resolver":"https://pith.science/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6","bundle":"https://pith.science/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6/bundle.json","state":"https://pith.science/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOEYCMKSCMVHMHK7LQSP7KSEE6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UOEYCMKSCMVHMHK7LQSP7KSEE6","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":"3792bece98dcf1dc834b77b7d01b05fb70ad27b49f2fd184d08e88a8d5406b12","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T21:39:15Z","title_canon_sha256":"a9f27c19e3333562bcca50fb6f207c88ede9b05807d871e729d75faa12a730cf"},"schema_version":"1.0","source":{"id":"2204.06644","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.06644","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"arxiv_version","alias_value":"2204.06644v2","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.06644","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"pith_short_12","alias_value":"UOEYCMKSCMVH","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"pith_short_16","alias_value":"UOEYCMKSCMVHMHK7","created_at":"2026-07-05T04:15:16Z"},{"alias_kind":"pith_short_8","alias_value":"UOEYCMKS","created_at":"2026-07-05T04:15:16Z"}],"graph_snapshots":[{"event_id":"sha256:3661aae7d96e6c548bb66bba71bd1fea5564e318da18189fdf72a55253864123","target":"graph","created_at":"2026-07-05T04:15:16Z","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/2204.06644/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present an efficient method of pretraining large-scale autoencoding language models using training signals generated by an auxiliary model. Originated in ELECTRA, this training strategy has demonstrated sample-efficiency to pretrain models at the scale of hundreds of millions of parameters. In this work, we conduct a comprehensive empirical study, and propose a recipe, namely \"Model generated dEnoising TRaining Objective\" (METRO), which incorporates some of the best modeling techniques developed recently to speed up, stabilize, and enhance pretrained language models without compromising mod","authors_text":"Chenyan Xiong, Di He, Guolin Ke, Jianfeng Gao, Paul Bennett, Payal Bajaj, Saurabh Tiwary, Tie-Yan Liu, XiaoDong Liu, Xia Song","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T21:39:15Z","title":"METRO: Efficient Denoising Pretraining of Large Scale Autoencoding Language Models with Model Generated Signals"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.06644","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:ede186f7930880cc541aa3ce7f83b752b407d9e50b610052e2fbda0ed2f3d754","target":"record","created_at":"2026-07-05T04:15:16Z","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":"3792bece98dcf1dc834b77b7d01b05fb70ad27b49f2fd184d08e88a8d5406b12","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-04-13T21:39:15Z","title_canon_sha256":"a9f27c19e3333562bcca50fb6f207c88ede9b05807d871e729d75faa12a730cf"},"schema_version":"1.0","source":{"id":"2204.06644","kind":"arxiv","version":2}},"canonical_sha256":"a389813152132a761d5f5c24ffaa4427b89731ae544d5f8524b70c569a78dee2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a389813152132a761d5f5c24ffaa4427b89731ae544d5f8524b70c569a78dee2","first_computed_at":"2026-07-05T04:15:16.088042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:16.088042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"B6/Rv6JVwfTCLPZzrtml8qBv/HQpsYv7WwDOWpjFnvVItatS1WE8hS/EcRcN8EKfS3k+VyUKLXujcs3wLBcUCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:16.088491Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.06644","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ede186f7930880cc541aa3ce7f83b752b407d9e50b610052e2fbda0ed2f3d754","sha256:3661aae7d96e6c548bb66bba71bd1fea5564e318da18189fdf72a55253864123"],"state_sha256":"64a01d32b6479b2f06bdd9eebfbc4129fdd52d1f1a6464afd096a1e1c9bbfc65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RN2bPDlOrQXhEv7b2Krw4TPdZWammI8/FWN1LC/X3/wydIp418nsctvBFljtbYcLhtZcf61bbE/ByGzkIH/uCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T12:03:24.266780Z","bundle_sha256":"575c41daf1d925a66e842be8881634689e8fcbd0bcf89a6ae78b008d248bddaf"}}