{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KPJTCD753NT3HA2Y3VFUSDXQ27","short_pith_number":"pith:KPJTCD75","canonical_record":{"source":{"id":"1910.13267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T13:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"8680ac3f3e224efb2980201147dd8ea292201e2ce8d46dcac274cd0f240fbdd2","abstract_canon_sha256":"052326b624dc25a358352168495d374733049610e2ad949991975ee912996b42"},"schema_version":"1.0"},"canonical_sha256":"53d3310ffddb67b38358dd4b490ef0d7d17e6d9389a2cc9681092cda0da41cd6","source":{"kind":"arxiv","id":"1910.13267","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.13267","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"arxiv_version","alias_value":"1910.13267v2","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13267","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"pith_short_12","alias_value":"KPJTCD753NT3","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"pith_short_16","alias_value":"KPJTCD753NT3HA2Y","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"pith_short_8","alias_value":"KPJTCD75","created_at":"2026-07-05T00:59:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KPJTCD753NT3HA2Y3VFUSDXQ27","target":"record","payload":{"canonical_record":{"source":{"id":"1910.13267","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T13:42:56Z","cross_cats_sorted":[],"title_canon_sha256":"8680ac3f3e224efb2980201147dd8ea292201e2ce8d46dcac274cd0f240fbdd2","abstract_canon_sha256":"052326b624dc25a358352168495d374733049610e2ad949991975ee912996b42"},"schema_version":"1.0"},"canonical_sha256":"53d3310ffddb67b38358dd4b490ef0d7d17e6d9389a2cc9681092cda0da41cd6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:42.733090Z","signature_b64":"WvCGHjY5HIIOy3sPYtAfgYZ2NczFrWs7pNqmK9TiZImH0qTv7cgJn/nMUv14mMtd2W2asfr307fmMX0yJ+kmBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"53d3310ffddb67b38358dd4b490ef0d7d17e6d9389a2cc9681092cda0da41cd6","last_reissued_at":"2026-07-05T00:59:42.732580Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:42.732580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.13267","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":"2026-07-05T00:59:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4QjJkmmouzxi0LiZBrPekhixHwxN1a5Z1dUBmaejtK39ni808r277ggse4kZdUuCwDC/pjnX/fTFOqGAJwrJAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:54:27.962566Z"},"content_sha256":"210ec69848e2b019617e06cde15355c173a54757cf8af50bae9ae093d163a562","schema_version":"1.0","event_id":"sha256:210ec69848e2b019617e06cde15355c173a54757cf8af50bae9ae093d163a562"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KPJTCD753NT3HA2Y3VFUSDXQ27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BPE-Dropout: Simple and Effective Subword Regularization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dmitrii Emelianenko, Elena Voita, Ivan Provilkov","submitted_at":"2019-10-29T13:42:56Z","abstract_excerpt":"Subword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent words intact while splitting the rare ones into multiple tokens. While multiple segmentations are possible even with the same vocabulary, BPE splits words into unique sequences; this may prevent a model from better learning the compositionality of words and being robust to segmentation errors. So far, the only way to overcome this BPE imperfection, its deterministic nature, was to create anoth"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13267","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/1910.13267/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":"2026-07-05T00:59:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LcOAeSt70DjctS/i3LPeVu/srUfdVYDhRjFl4/HwsqVcCqKMpCKyDgtljZS+8iCH0wpJKt4htCqeyS819is7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:54:27.963068Z"},"content_sha256":"27c3e22051d0ee7238d12b66bf26dff9b9853508f4c8afc30d6a02463f73ef8e","schema_version":"1.0","event_id":"sha256:27c3e22051d0ee7238d12b66bf26dff9b9853508f4c8afc30d6a02463f73ef8e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KPJTCD753NT3HA2Y3VFUSDXQ27/bundle.json","state_url":"https://pith.science/pith/KPJTCD753NT3HA2Y3VFUSDXQ27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KPJTCD753NT3HA2Y3VFUSDXQ27/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":"2026-08-09T04:54:27Z","links":{"resolver":"https://pith.science/pith/KPJTCD753NT3HA2Y3VFUSDXQ27","bundle":"https://pith.science/pith/KPJTCD753NT3HA2Y3VFUSDXQ27/bundle.json","state":"https://pith.science/pith/KPJTCD753NT3HA2Y3VFUSDXQ27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KPJTCD753NT3HA2Y3VFUSDXQ27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KPJTCD753NT3HA2Y3VFUSDXQ27","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":"052326b624dc25a358352168495d374733049610e2ad949991975ee912996b42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T13:42:56Z","title_canon_sha256":"8680ac3f3e224efb2980201147dd8ea292201e2ce8d46dcac274cd0f240fbdd2"},"schema_version":"1.0","source":{"id":"1910.13267","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.13267","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"arxiv_version","alias_value":"1910.13267v2","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.13267","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"pith_short_12","alias_value":"KPJTCD753NT3","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"pith_short_16","alias_value":"KPJTCD753NT3HA2Y","created_at":"2026-07-05T00:59:42Z"},{"alias_kind":"pith_short_8","alias_value":"KPJTCD75","created_at":"2026-07-05T00:59:42Z"}],"graph_snapshots":[{"event_id":"sha256:27c3e22051d0ee7238d12b66bf26dff9b9853508f4c8afc30d6a02463f73ef8e","target":"graph","created_at":"2026-07-05T00:59:42Z","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/1910.13267/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subword segmentation is widely used to address the open vocabulary problem in machine translation. The dominant approach to subword segmentation is Byte Pair Encoding (BPE), which keeps the most frequent words intact while splitting the rare ones into multiple tokens. While multiple segmentations are possible even with the same vocabulary, BPE splits words into unique sequences; this may prevent a model from better learning the compositionality of words and being robust to segmentation errors. So far, the only way to overcome this BPE imperfection, its deterministic nature, was to create anoth","authors_text":"Dmitrii Emelianenko, Elena Voita, Ivan Provilkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T13:42:56Z","title":"BPE-Dropout: Simple and Effective Subword Regularization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.13267","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":"sha256:210ec69848e2b019617e06cde15355c173a54757cf8af50bae9ae093d163a562","target":"record","created_at":"2026-07-05T00:59:42Z","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":"052326b624dc25a358352168495d374733049610e2ad949991975ee912996b42","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-29T13:42:56Z","title_canon_sha256":"8680ac3f3e224efb2980201147dd8ea292201e2ce8d46dcac274cd0f240fbdd2"},"schema_version":"1.0","source":{"id":"1910.13267","kind":"arxiv","version":2}},"canonical_sha256":"53d3310ffddb67b38358dd4b490ef0d7d17e6d9389a2cc9681092cda0da41cd6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"53d3310ffddb67b38358dd4b490ef0d7d17e6d9389a2cc9681092cda0da41cd6","first_computed_at":"2026-07-05T00:59:42.732580Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:42.732580Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WvCGHjY5HIIOy3sPYtAfgYZ2NczFrWs7pNqmK9TiZImH0qTv7cgJn/nMUv14mMtd2W2asfr307fmMX0yJ+kmBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:42.733090Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.13267","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:210ec69848e2b019617e06cde15355c173a54757cf8af50bae9ae093d163a562","sha256:27c3e22051d0ee7238d12b66bf26dff9b9853508f4c8afc30d6a02463f73ef8e"],"state_sha256":"e045ca51129a9d89ed38cee22af3911cc779bcc8efed558f3b918eeecb63dada"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"amwX62fP4pd3oWnM32qoVKvUgnreji8OwfFYFYgvMmu2z6J88/mE9WrX3TcV6EtwzKOTsQYD9YGS8OuzGgCDDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:54:27.967943Z","bundle_sha256":"41a40d06ef8d550544bac9e8bdbf46486146cee5bd1227d2bd5cfc78a295b226"}}