{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5RTDUEG5W3ZSVNFLN7Q2UUQKBS","short_pith_number":"pith:5RTDUEG5","canonical_record":{"source":{"id":"2104.04946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-11T07:43:19Z","cross_cats_sorted":[],"title_canon_sha256":"2e46eefa9eb6b11eede13ce2f0a407fb8e1c3813eb900ee2238644ab51dfe09c","abstract_canon_sha256":"0ca31f435e0763d97f4f6c8a207ad00c294febdcf5e7db9bf223be24e80df3a9"},"schema_version":"1.0"},"canonical_sha256":"ec663a10ddb6f32ab4ab6fe1aa520a0c926939ec1cdcb93895d0280aeea7341c","source":{"kind":"arxiv","id":"2104.04946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04946","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04946v1","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04946","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"5RTDUEG5W3ZS","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"5RTDUEG5W3ZSVNFL","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"5RTDUEG5","created_at":"2026-07-05T02:31:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5RTDUEG5W3ZSVNFLN7Q2UUQKBS","target":"record","payload":{"canonical_record":{"source":{"id":"2104.04946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-11T07:43:19Z","cross_cats_sorted":[],"title_canon_sha256":"2e46eefa9eb6b11eede13ce2f0a407fb8e1c3813eb900ee2238644ab51dfe09c","abstract_canon_sha256":"0ca31f435e0763d97f4f6c8a207ad00c294febdcf5e7db9bf223be24e80df3a9"},"schema_version":"1.0"},"canonical_sha256":"ec663a10ddb6f32ab4ab6fe1aa520a0c926939ec1cdcb93895d0280aeea7341c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:31:06.593786Z","signature_b64":"JvY1cRFLIYKNVQ6SLCwfyMLgT7dvyhjJNLYAAN+uEe/vFYhz35zlzJ7Nt9tLGn/inCz6F7ezhdRczKAkXPzrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec663a10ddb6f32ab4ab6fe1aa520a0c926939ec1cdcb93895d0280aeea7341c","last_reissued_at":"2026-07-05T02:31:06.593348Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:31:06.593348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.04946","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:31:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hlVxquWJYdGga4oe9mMGMUlHxPDLEVoo8MeBMF6Edf0F5/SMVl1tLXxCEgqIUM/FZF3QVPb2/Ii6pYsVIwW4BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:09:27.047820Z"},"content_sha256":"40b73df7fe289d0d5a5071e98d7701dbcb55e7f098a021a8aed939901510b38f","schema_version":"1.0","event_id":"sha256:40b73df7fe289d0d5a5071e98d7701dbcb55e7f098a021a8aed939901510b38f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5RTDUEG5W3ZSVNFLN7Q2UUQKBS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lijun Wu, Qi Meng, Shufang Xie, Tao Qin, Tie-Yan Liu, Xinyu Dai, Yingce Xia, Zhen Wu","submitted_at":"2021-04-11T07:43:19Z","abstract_excerpt":"Transformer architecture achieves great success in abundant natural language processing tasks. The over-parameterization of the Transformer model has motivated plenty of works to alleviate its overfitting for superior performances. With some explorations, we find simple techniques such as dropout, can greatly boost model performance with a careful design. Therefore, in this paper, we integrate different dropout techniques into the training of Transformer models. Specifically, we propose an approach named UniDrop to unites three different dropout techniques from fine-grain to coarse-grain, i.e."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04946","kind":"arxiv","version":1},"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/2104.04946/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":"2026-07-05T02:31:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xE1gBsKIUfHfQsgjLDxKguDCLD8C9TgAdzKgVM4UAaokSJLngrkceUh8xBJFt0cbur/2eXqbImYLCPp/GnxAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:09:27.048192Z"},"content_sha256":"a90d6fd0e0c315b03a10b71843c408d9d346859e7a6b0e3e65122e1d261d73f0","schema_version":"1.0","event_id":"sha256:a90d6fd0e0c315b03a10b71843c408d9d346859e7a6b0e3e65122e1d261d73f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS/bundle.json","state_url":"https://pith.science/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS/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":"2026-07-07T10:09:27Z","links":{"resolver":"https://pith.science/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS","bundle":"https://pith.science/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS/bundle.json","state":"https://pith.science/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5RTDUEG5W3ZSVNFLN7Q2UUQKBS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5RTDUEG5W3ZSVNFLN7Q2UUQKBS","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":"0ca31f435e0763d97f4f6c8a207ad00c294febdcf5e7db9bf223be24e80df3a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-11T07:43:19Z","title_canon_sha256":"2e46eefa9eb6b11eede13ce2f0a407fb8e1c3813eb900ee2238644ab51dfe09c"},"schema_version":"1.0","source":{"id":"2104.04946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.04946","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"arxiv_version","alias_value":"2104.04946v1","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.04946","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"pith_short_12","alias_value":"5RTDUEG5W3ZS","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"pith_short_16","alias_value":"5RTDUEG5W3ZSVNFL","created_at":"2026-07-05T02:31:06Z"},{"alias_kind":"pith_short_8","alias_value":"5RTDUEG5","created_at":"2026-07-05T02:31:06Z"}],"graph_snapshots":[{"event_id":"sha256:a90d6fd0e0c315b03a10b71843c408d9d346859e7a6b0e3e65122e1d261d73f0","target":"graph","created_at":"2026-07-05T02:31:06Z","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/2104.04946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer architecture achieves great success in abundant natural language processing tasks. The over-parameterization of the Transformer model has motivated plenty of works to alleviate its overfitting for superior performances. With some explorations, we find simple techniques such as dropout, can greatly boost model performance with a careful design. Therefore, in this paper, we integrate different dropout techniques into the training of Transformer models. Specifically, we propose an approach named UniDrop to unites three different dropout techniques from fine-grain to coarse-grain, i.e.","authors_text":"Lijun Wu, Qi Meng, Shufang Xie, Tao Qin, Tie-Yan Liu, Xinyu Dai, Yingce Xia, Zhen Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-11T07:43:19Z","title":"UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.04946","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":"sha256:40b73df7fe289d0d5a5071e98d7701dbcb55e7f098a021a8aed939901510b38f","target":"record","created_at":"2026-07-05T02:31:06Z","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":"0ca31f435e0763d97f4f6c8a207ad00c294febdcf5e7db9bf223be24e80df3a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-04-11T07:43:19Z","title_canon_sha256":"2e46eefa9eb6b11eede13ce2f0a407fb8e1c3813eb900ee2238644ab51dfe09c"},"schema_version":"1.0","source":{"id":"2104.04946","kind":"arxiv","version":1}},"canonical_sha256":"ec663a10ddb6f32ab4ab6fe1aa520a0c926939ec1cdcb93895d0280aeea7341c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec663a10ddb6f32ab4ab6fe1aa520a0c926939ec1cdcb93895d0280aeea7341c","first_computed_at":"2026-07-05T02:31:06.593348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:31:06.593348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JvY1cRFLIYKNVQ6SLCwfyMLgT7dvyhjJNLYAAN+uEe/vFYhz35zlzJ7Nt9tLGn/inCz6F7ezhdRczKAkXPzrAw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:31:06.593786Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.04946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40b73df7fe289d0d5a5071e98d7701dbcb55e7f098a021a8aed939901510b38f","sha256:a90d6fd0e0c315b03a10b71843c408d9d346859e7a6b0e3e65122e1d261d73f0"],"state_sha256":"0cfec00c668820127641a5c03f78c577e2c1bc278ab537af72dcd529ac902573"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8AmMs9XTUl9PtvB5i5SRpbrayhB7viM5+8U9uLMIZG9iC+pqFa/KlrdhpdLd7gz0neZa2VpTDAVQCr17DeNmCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:09:27.050123Z","bundle_sha256":"57bce293d6ceac3884adb68e9400fca66a1e66e1d93595db4d8cd84f0879f2d1"}}