{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:YOZB7G5VZ3SONO6K44AEFJ5QNA","short_pith_number":"pith:YOZB7G5V","canonical_record":{"source":{"id":"1909.11299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T06:04:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a899916becdf937233621f9ae572bf674ce41cd99f667d9e7ce03ed1742867a","abstract_canon_sha256":"136ca243c009d21da5f0c12be84b6bf81fd16a2a02315a6507ad22b38f7b5ee9"},"schema_version":"1.0"},"canonical_sha256":"c3b21f9bb5cee4e6bbcae70042a7b0681e293bbe016ccdbd7224cbfb2633cf8f","source":{"kind":"arxiv","id":"1909.11299","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11299","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11299v2","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11299","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_12","alias_value":"YOZB7G5VZ3SO","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_16","alias_value":"YOZB7G5VZ3SONO6K","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_8","alias_value":"YOZB7G5V","created_at":"2026-07-05T00:35:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:YOZB7G5VZ3SONO6K44AEFJ5QNA","target":"record","payload":{"canonical_record":{"source":{"id":"1909.11299","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T06:04:37Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"1a899916becdf937233621f9ae572bf674ce41cd99f667d9e7ce03ed1742867a","abstract_canon_sha256":"136ca243c009d21da5f0c12be84b6bf81fd16a2a02315a6507ad22b38f7b5ee9"},"schema_version":"1.0"},"canonical_sha256":"c3b21f9bb5cee4e6bbcae70042a7b0681e293bbe016ccdbd7224cbfb2633cf8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:10.401039Z","signature_b64":"dJRx1Zgs+RVKINtfDdniGpklurkUThgrPgNSwH8urwq/FRojQ8USqi53fwA8JFJuqbvG+4BLWlVwih9eJj+eBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3b21f9bb5cee4e6bbcae70042a7b0681e293bbe016ccdbd7224cbfb2633cf8f","last_reissued_at":"2026-07-05T00:35:10.400571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:10.400571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.11299","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":"2026-07-05T00:35:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ch7dPNzbvIv4MS9AeMEuBaHkYLT3nzoaL2fhrnjwvOeXURpbMLnPeNlk8JycmrAj4X+e44Fu7Wiu+aBcaqUbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:39:41.396682Z"},"content_sha256":"44542603e3cb0d7544487a232c1d0de3596c578038fa5ae6e8ef61899c375277","schema_version":"1.0","event_id":"sha256:44542603e3cb0d7544487a232c1d0de3596c578038fa5ae6e8ef61899c375277"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:YOZB7G5VZ3SONO6K44AEFJ5QNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Cheolhyoung Lee, Kyunghyun Cho, Wanmo Kang","submitted_at":"2019-09-25T06:04:37Z","abstract_excerpt":"In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption, finetuning a large pretrained language model on a downstream task is prone to degenerate performance when there are only a small number of training instances available. In this paper, we introduce a new regularization technique, to which we refer as \"mixout\", motivated by dropout. Mixout stochastically mixes the parameters of two models. We show that our mixout"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11299","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/1909.11299/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":"2026-07-05T00:35:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"E6A1XBbvK7OUN9d0HOOU83vaFOeoXKqV+c8kSRsJgJpiK5p9pCjhpXdEGRmJFAKyJf/YTO4e6Wc4zQ1MmIdHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T21:39:41.397346Z"},"content_sha256":"1cb0cb071d6ac3f0ba4257f7c06bfa21c6b2f618bd854d9ed7c64f92e00581f1","schema_version":"1.0","event_id":"sha256:1cb0cb071d6ac3f0ba4257f7c06bfa21c6b2f618bd854d9ed7c64f92e00581f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA/bundle.json","state_url":"https://pith.science/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA/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":"2026-08-15T21:39:41Z","links":{"resolver":"https://pith.science/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA","bundle":"https://pith.science/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA/bundle.json","state":"https://pith.science/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YOZB7G5VZ3SONO6K44AEFJ5QNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:YOZB7G5VZ3SONO6K44AEFJ5QNA","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":"136ca243c009d21da5f0c12be84b6bf81fd16a2a02315a6507ad22b38f7b5ee9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T06:04:37Z","title_canon_sha256":"1a899916becdf937233621f9ae572bf674ce41cd99f667d9e7ce03ed1742867a"},"schema_version":"1.0","source":{"id":"1909.11299","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.11299","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"arxiv_version","alias_value":"1909.11299v2","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.11299","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_12","alias_value":"YOZB7G5VZ3SO","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_16","alias_value":"YOZB7G5VZ3SONO6K","created_at":"2026-07-05T00:35:10Z"},{"alias_kind":"pith_short_8","alias_value":"YOZB7G5V","created_at":"2026-07-05T00:35:10Z"}],"graph_snapshots":[{"event_id":"sha256:1cb0cb071d6ac3f0ba4257f7c06bfa21c6b2f618bd854d9ed7c64f92e00581f1","target":"graph","created_at":"2026-07-05T00:35:10Z","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/1909.11299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In natural language processing, it has been observed recently that generalization could be greatly improved by finetuning a large-scale language model pretrained on a large unlabeled corpus. Despite its recent success and wide adoption, finetuning a large pretrained language model on a downstream task is prone to degenerate performance when there are only a small number of training instances available. In this paper, we introduce a new regularization technique, to which we refer as \"mixout\", motivated by dropout. Mixout stochastically mixes the parameters of two models. We show that our mixout","authors_text":"Cheolhyoung Lee, Kyunghyun Cho, Wanmo Kang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T06:04:37Z","title":"Mixout: Effective Regularization to Finetune Large-scale Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.11299","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":"sha256:44542603e3cb0d7544487a232c1d0de3596c578038fa5ae6e8ef61899c375277","target":"record","created_at":"2026-07-05T00:35:10Z","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":"136ca243c009d21da5f0c12be84b6bf81fd16a2a02315a6507ad22b38f7b5ee9","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-09-25T06:04:37Z","title_canon_sha256":"1a899916becdf937233621f9ae572bf674ce41cd99f667d9e7ce03ed1742867a"},"schema_version":"1.0","source":{"id":"1909.11299","kind":"arxiv","version":2}},"canonical_sha256":"c3b21f9bb5cee4e6bbcae70042a7b0681e293bbe016ccdbd7224cbfb2633cf8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3b21f9bb5cee4e6bbcae70042a7b0681e293bbe016ccdbd7224cbfb2633cf8f","first_computed_at":"2026-07-05T00:35:10.400571Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:10.400571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dJRx1Zgs+RVKINtfDdniGpklurkUThgrPgNSwH8urwq/FRojQ8USqi53fwA8JFJuqbvG+4BLWlVwih9eJj+eBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:10.401039Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.11299","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:44542603e3cb0d7544487a232c1d0de3596c578038fa5ae6e8ef61899c375277","sha256:1cb0cb071d6ac3f0ba4257f7c06bfa21c6b2f618bd854d9ed7c64f92e00581f1"],"state_sha256":"588710c94cfafdbec133a2a1ea10f684c3c33c9d6f48b738ff528c803da727af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1yB/cwPpow4pOqC5r+ooh9eUTWWHxVhuLpkhLVswg6ZGZzCglKqRXy8zNvCH4Jby3toyHUVNfb3YRQR6G6yBDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T21:39:41.403720Z","bundle_sha256":"6de17a15d6ebbf01407a8c8b35cf8ff103390e55a517d5cf5b0d54e2288699aa"}}