{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ROXNHI4VFSJTIL6UFKKXCKPJ3T","short_pith_number":"pith:ROXNHI4V","canonical_record":{"source":{"id":"1809.01301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T02:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"8a9532e32e35f9c2e6df80589442896d181c442ec7bd9029610defb28811d962","abstract_canon_sha256":"9cc691e88f0df5e5b30c11b3aa907e681f7153488c6eb8d6be39f4aaabed425a"},"schema_version":"1.0"},"canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","source":{"kind":"arxiv","id":"1809.01301","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01301","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01301v2","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01301","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"ROXNHI4VFSJT","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ROXNHI4VFSJTIL6U","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ROXNHI4V","created_at":"2026-05-18T12:32:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ROXNHI4VFSJTIL6UFKKXCKPJ3T","target":"record","payload":{"canonical_record":{"source":{"id":"1809.01301","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T02:26:09Z","cross_cats_sorted":[],"title_canon_sha256":"8a9532e32e35f9c2e6df80589442896d181c442ec7bd9029610defb28811d962","abstract_canon_sha256":"9cc691e88f0df5e5b30c11b3aa907e681f7153488c6eb8d6be39f4aaabed425a"},"schema_version":"1.0"},"canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:10.954752Z","signature_b64":"AWi4gA6vQCk/XmDjO70TFVdfk4QuvfzSacHzZfJzNpNfPFfy5lL4RwgTOuYZrbKlEq4X5rjxc6PBrzDnfvqSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","last_reissued_at":"2026-05-18T00:06:10.954107Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:10.954107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1809.01301","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":"2026-05-18T00:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RdunG6gYOVpZ1yiieGHSSKR004pZYhMsIoH657uFtaLuS6tV4/tLV/7AforUrVuPKS8/MdFYC6B88+HhOyRVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:45:25.600475Z"},"content_sha256":"083195d93f159d8f54f020bf6d73cc3e684127e650cb8807fdd0ab87cce7478c","schema_version":"1.0","event_id":"sha256:083195d93f159d8f54f020bf6d73cc3e684127e650cb8807fdd0ab87cce7478c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ROXNHI4VFSJTIL6UFKKXCKPJ3T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kevin Duh, Pamela Shapiro","submitted_at":"2018-09-05T02:26:09Z","abstract_excerpt":"Neural Machine Translation (NMT) in low-resource settings and of morphologically rich languages is made difficult in part by data sparsity of vocabulary words. Several methods have been used to help reduce this sparsity, notably Byte-Pair Encoding (BPE) and a character-based CNN layer (charCNN). However, the charCNN has largely been neglected, possibly because it has only been compared to BPE rather than combined with it. We argue for a reconsideration of the charCNN, based on cross-lingual improvements on low-resource data. We translate from 8 languages into English, using a multi-way paralle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01301","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":""},"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":"2026-05-18T00:06:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tr1PL1VeNgA1ekKCAYn67nWny0G5sX3Q0NfaFRtktkK38jqNH44VPCowEsQLM0DKS9Z7Pl5DOaztwS9q8UvZBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:45:25.600805Z"},"content_sha256":"d67fa46b46cb8fc909818e0fe65e9a210994f73e1ff3bea181d9ae6181d69856","schema_version":"1.0","event_id":"sha256:d67fa46b46cb8fc909818e0fe65e9a210994f73e1ff3bea181d9ae6181d69856"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/bundle.json","state_url":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/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":"2026-06-07T14:45:25Z","links":{"resolver":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T","bundle":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/bundle.json","state":"https://pith.science/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ROXNHI4VFSJTIL6UFKKXCKPJ3T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ROXNHI4VFSJTIL6UFKKXCKPJ3T","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":"9cc691e88f0df5e5b30c11b3aa907e681f7153488c6eb8d6be39f4aaabed425a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T02:26:09Z","title_canon_sha256":"8a9532e32e35f9c2e6df80589442896d181c442ec7bd9029610defb28811d962"},"schema_version":"1.0","source":{"id":"1809.01301","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1809.01301","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"arxiv_version","alias_value":"1809.01301v2","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.01301","created_at":"2026-05-18T00:06:10Z"},{"alias_kind":"pith_short_12","alias_value":"ROXNHI4VFSJT","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_16","alias_value":"ROXNHI4VFSJTIL6U","created_at":"2026-05-18T12:32:50Z"},{"alias_kind":"pith_short_8","alias_value":"ROXNHI4V","created_at":"2026-05-18T12:32:50Z"}],"graph_snapshots":[{"event_id":"sha256:d67fa46b46cb8fc909818e0fe65e9a210994f73e1ff3bea181d9ae6181d69856","target":"graph","created_at":"2026-05-18T00:06:10Z","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"},"paper":{"abstract_excerpt":"Neural Machine Translation (NMT) in low-resource settings and of morphologically rich languages is made difficult in part by data sparsity of vocabulary words. Several methods have been used to help reduce this sparsity, notably Byte-Pair Encoding (BPE) and a character-based CNN layer (charCNN). However, the charCNN has largely been neglected, possibly because it has only been compared to BPE rather than combined with it. We argue for a reconsideration of the charCNN, based on cross-lingual improvements on low-resource data. We translate from 8 languages into English, using a multi-way paralle","authors_text":"Kevin Duh, Pamela Shapiro","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T02:26:09Z","title":"BPE and CharCNNs for Translation of Morphology: A Cross-Lingual Comparison and Analysis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.01301","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":"sha256:083195d93f159d8f54f020bf6d73cc3e684127e650cb8807fdd0ab87cce7478c","target":"record","created_at":"2026-05-18T00:06:10Z","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":"9cc691e88f0df5e5b30c11b3aa907e681f7153488c6eb8d6be39f4aaabed425a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-09-05T02:26:09Z","title_canon_sha256":"8a9532e32e35f9c2e6df80589442896d181c442ec7bd9029610defb28811d962"},"schema_version":"1.0","source":{"id":"1809.01301","kind":"arxiv","version":2}},"canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8baed3a3952c93342fd42a957129e9dcf5fae02826ac60cd0def299a91948a7a","first_computed_at":"2026-05-18T00:06:10.954107Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:10.954107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AWi4gA6vQCk/XmDjO70TFVdfk4QuvfzSacHzZfJzNpNfPFfy5lL4RwgTOuYZrbKlEq4X5rjxc6PBrzDnfvqSAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:10.954752Z","signed_message":"canonical_sha256_bytes"},"source_id":"1809.01301","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:083195d93f159d8f54f020bf6d73cc3e684127e650cb8807fdd0ab87cce7478c","sha256:d67fa46b46cb8fc909818e0fe65e9a210994f73e1ff3bea181d9ae6181d69856"],"state_sha256":"3b866deaa0bc1cacfedaeacd7ef2206a69b9864f7ba539eaf4f1dfd5206f1c35"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o22iTPZSciQ5CeoByFnHdf/cMdRFyzXF3vBi+6lxxV7tGUCSE2EIZAtSidTEqCaASH0bWI7o3KyZOrb6CTneBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:45:25.602550Z","bundle_sha256":"afc829fd76c2392f2866c0206482c56b400a798a3b931469e93468e31e62be92"}}