{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:KYZ2CR4YBUFUYIIJXAESCIDAKR","short_pith_number":"pith:KYZ2CR4Y","canonical_record":{"source":{"id":"2011.03469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T16:47:43Z","cross_cats_sorted":[],"title_canon_sha256":"a8ec13c669687777d9b375f7ad04c42867974f3f1d99c9a16fef12daf30cd61e","abstract_canon_sha256":"e4c982888b63166b3ac364bb611e3ff6663415863c1adc681ceafcca2517fe4a"},"schema_version":"1.0"},"canonical_sha256":"5633a147980d0b4c2109b809212060544b301135b8c91bd23db2e1c693979a31","source":{"kind":"arxiv","id":"2011.03469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03469","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03469v1","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03469","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"KYZ2CR4YBUFU","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"KYZ2CR4YBUFUYIIJ","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"KYZ2CR4Y","created_at":"2026-07-05T01:49:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:KYZ2CR4YBUFUYIIJXAESCIDAKR","target":"record","payload":{"canonical_record":{"source":{"id":"2011.03469","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T16:47:43Z","cross_cats_sorted":[],"title_canon_sha256":"a8ec13c669687777d9b375f7ad04c42867974f3f1d99c9a16fef12daf30cd61e","abstract_canon_sha256":"e4c982888b63166b3ac364bb611e3ff6663415863c1adc681ceafcca2517fe4a"},"schema_version":"1.0"},"canonical_sha256":"5633a147980d0b4c2109b809212060544b301135b8c91bd23db2e1c693979a31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:43.447501Z","signature_b64":"NspwGtRZNg1urjbgZ4eCZo1WJcKjT39XSWAwTLDsLKWKXpAl4yWXu8Hyq0Wiza7DYqak8o8wPVEjlvHacvwqAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5633a147980d0b4c2109b809212060544b301135b8c91bd23db2e1c693979a31","last_reissued_at":"2026-07-05T01:49:43.447006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:43.447006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.03469","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":"2026-07-05T01:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UeY88ldTJXQwEJQQmNSNYgjec2mfBDvOgG4yHm71SPBrcn70viKq+PkxnMYZBEm7yiMShKzC33SHkbYkMXKGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:48:54.006023Z"},"content_sha256":"a8d44233060d0ec664f6b82de5247439cecbae0e743986dcb4b40bfd566d381e","schema_version":"1.0","event_id":"sha256:a8d44233060d0ec664f6b82de5247439cecbae0e743986dcb4b40bfd566d381e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:KYZ2CR4YBUFUYIIJXAESCIDAKR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gongbo Tang, Joakim Nivre, Rico Sennrich","submitted_at":"2020-11-06T16:47:43Z","abstract_excerpt":"Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this paper, we conduct an investigation into pure character-based models in the case of translating Finnish into English, including exploring the ability to learn word senses and morphological inflections and the attention mechanism. We demonstrate that word-level information is distributed over the entire character sequence rather than over a single character, and characters at differ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03469","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/2011.03469/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":"2026-07-05T01:49:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pycN1/nvDBrYaaK6YC8bYxcMnP9R5XSx3roj71HpCOqKAOhEnVsIQ0W3X5oIbu/q8W/2BAE+YuQ8Y0pjnZfaDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:48:54.006527Z"},"content_sha256":"27338e848197b6f302e40d6801fed1c2ee368ddec0a749e9c135bea8ea7238f0","schema_version":"1.0","event_id":"sha256:27338e848197b6f302e40d6801fed1c2ee368ddec0a749e9c135bea8ea7238f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR/bundle.json","state_url":"https://pith.science/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR/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":"2026-08-06T04:48:54Z","links":{"resolver":"https://pith.science/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR","bundle":"https://pith.science/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR/bundle.json","state":"https://pith.science/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KYZ2CR4YBUFUYIIJXAESCIDAKR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:KYZ2CR4YBUFUYIIJXAESCIDAKR","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":"e4c982888b63166b3ac364bb611e3ff6663415863c1adc681ceafcca2517fe4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T16:47:43Z","title_canon_sha256":"a8ec13c669687777d9b375f7ad04c42867974f3f1d99c9a16fef12daf30cd61e"},"schema_version":"1.0","source":{"id":"2011.03469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03469","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03469v1","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03469","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"pith_short_12","alias_value":"KYZ2CR4YBUFU","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"pith_short_16","alias_value":"KYZ2CR4YBUFUYIIJ","created_at":"2026-07-05T01:49:43Z"},{"alias_kind":"pith_short_8","alias_value":"KYZ2CR4Y","created_at":"2026-07-05T01:49:43Z"}],"graph_snapshots":[{"event_id":"sha256:27338e848197b6f302e40d6801fed1c2ee368ddec0a749e9c135bea8ea7238f0","target":"graph","created_at":"2026-07-05T01:49:43Z","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/2011.03469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent work has shown that deeper character-based neural machine translation (NMT) models can outperform subword-based models. However, it is still unclear what makes deeper character-based models successful. In this paper, we conduct an investigation into pure character-based models in the case of translating Finnish into English, including exploring the ability to learn word senses and morphological inflections and the attention mechanism. We demonstrate that word-level information is distributed over the entire character sequence rather than over a single character, and characters at differ","authors_text":"Gongbo Tang, Joakim Nivre, Rico Sennrich","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T16:47:43Z","title":"Understanding Pure Character-Based Neural Machine Translation: The Case of Translating Finnish into English"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03469","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:a8d44233060d0ec664f6b82de5247439cecbae0e743986dcb4b40bfd566d381e","target":"record","created_at":"2026-07-05T01:49:43Z","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":"e4c982888b63166b3ac364bb611e3ff6663415863c1adc681ceafcca2517fe4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-06T16:47:43Z","title_canon_sha256":"a8ec13c669687777d9b375f7ad04c42867974f3f1d99c9a16fef12daf30cd61e"},"schema_version":"1.0","source":{"id":"2011.03469","kind":"arxiv","version":1}},"canonical_sha256":"5633a147980d0b4c2109b809212060544b301135b8c91bd23db2e1c693979a31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5633a147980d0b4c2109b809212060544b301135b8c91bd23db2e1c693979a31","first_computed_at":"2026-07-05T01:49:43.447006Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:43.447006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NspwGtRZNg1urjbgZ4eCZo1WJcKjT39XSWAwTLDsLKWKXpAl4yWXu8Hyq0Wiza7DYqak8o8wPVEjlvHacvwqAA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:43.447501Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8d44233060d0ec664f6b82de5247439cecbae0e743986dcb4b40bfd566d381e","sha256:27338e848197b6f302e40d6801fed1c2ee368ddec0a749e9c135bea8ea7238f0"],"state_sha256":"4406431c826fc7e746e6f2458aea3ff7010da7944b8b5f3834f9f97624d9283c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6tSl4GsREte03S6VBiqbb1uaetpkZskXkuUZz3kA7bUnrvtTa6CEzkddgLcZV26RR3pJsJ6T0VH873xT7koBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:48:54.012222Z","bundle_sha256":"ff95d4ad704dca4bde75af4bd602849b1b957f632003f5d0f022cf3dfa154684"}}