{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:ZWSDSROPKKWWSMNLNS2JJ2GABS","short_pith_number":"pith:ZWSDSROP","canonical_record":{"source":{"id":"1704.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T21:10:53Z","cross_cats_sorted":[],"title_canon_sha256":"00ee9b438f9f4bd146122ad2ad8bea20db535935249e74477f5d5c5a33de8eaa","abstract_canon_sha256":"f3e80b52b7768fe73ea26c732f5e58cf7b8d280c6d546c4c46e7c07fb320b0a8"},"schema_version":"1.0"},"canonical_sha256":"cda43945cf52ad6931ab6cb494e8c00ca6853a808705c4d15c70328acf084b3d","source":{"kind":"arxiv","id":"1704.08352","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08352","created_at":"2026-05-18T00:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08352v1","created_at":"2026-05-18T00:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08352","created_at":"2026-05-18T00:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZWSDSROPKKWW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZWSDSROPKKWWSMNL","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZWSDSROP","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:ZWSDSROPKKWWSMNLNS2JJ2GABS","target":"record","payload":{"canonical_record":{"source":{"id":"1704.08352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T21:10:53Z","cross_cats_sorted":[],"title_canon_sha256":"00ee9b438f9f4bd146122ad2ad8bea20db535935249e74477f5d5c5a33de8eaa","abstract_canon_sha256":"f3e80b52b7768fe73ea26c732f5e58cf7b8d280c6d546c4c46e7c07fb320b0a8"},"schema_version":"1.0"},"canonical_sha256":"cda43945cf52ad6931ab6cb494e8c00ca6853a808705c4d15c70328acf084b3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:27.890958Z","signature_b64":"qm920E0aJQCtEALMuYhWrSIdtkDzy2hJ9mnkhMFCgOeDKfg1W+PStquuLcqzuiANVnlcAy+IMuxWNNssqunTAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cda43945cf52ad6931ab6cb494e8c00ca6853a808705c4d15c70328acf084b3d","last_reissued_at":"2026-05-18T00:45:27.890540Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:27.890540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1704.08352","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":"2026-05-18T00:45:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"84kNKuDo60Fq4pFa3zUhssArSyq98ksnkC7Qj0tUM8bKV2isnpIlb38290NI3XO5J7dyA221FBNpvjn4yyf3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:58:07.472011Z"},"content_sha256":"c9bf7d0206cbe03e848974a329f4fc2d261e9d6701e11e2f288db16915803384","schema_version":"1.0","event_id":"sha256:c9bf7d0206cbe03e848974a329f4fc2d261e9d6701e11e2f288db16915803384"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:ZWSDSROPKKWWSMNLNS2JJ2GABS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Characters to Words to in Between: Do We Capture Morphology?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Lopez, Clara Vania","submitted_at":"2017-04-26T21:10:53Z","abstract_excerpt":"Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they have not been systematically compared, and it is not understood how they interact with different morphological typologies. On a language modeling task, we present experiments that systematically vary (1) the basic unit of representation, (2) the composition of these representations, and (3) the morphological typology of the language modeled. Our results exten"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08352","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":""},"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":"2026-05-18T00:45:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yzR4/tEfrFvZZ419IWGB2XCjcckphUUQIICpzmYAUGhTzmBkQy4JQsg2roACJ15KDM4H3vR3nJ6zZHNWNScIDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T00:58:07.472370Z"},"content_sha256":"e857b0ff2f009383c265e0b4134606f810211922eb2cb5ffad48ff8d71ea2606","schema_version":"1.0","event_id":"sha256:e857b0ff2f009383c265e0b4134606f810211922eb2cb5ffad48ff8d71ea2606"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS/bundle.json","state_url":"https://pith.science/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS/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":"2026-06-03T00:58:07Z","links":{"resolver":"https://pith.science/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS","bundle":"https://pith.science/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS/bundle.json","state":"https://pith.science/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZWSDSROPKKWWSMNLNS2JJ2GABS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:ZWSDSROPKKWWSMNLNS2JJ2GABS","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":"f3e80b52b7768fe73ea26c732f5e58cf7b8d280c6d546c4c46e7c07fb320b0a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T21:10:53Z","title_canon_sha256":"00ee9b438f9f4bd146122ad2ad8bea20db535935249e74477f5d5c5a33de8eaa"},"schema_version":"1.0","source":{"id":"1704.08352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1704.08352","created_at":"2026-05-18T00:45:27Z"},{"alias_kind":"arxiv_version","alias_value":"1704.08352v1","created_at":"2026-05-18T00:45:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1704.08352","created_at":"2026-05-18T00:45:27Z"},{"alias_kind":"pith_short_12","alias_value":"ZWSDSROPKKWW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZWSDSROPKKWWSMNL","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZWSDSROP","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:e857b0ff2f009383c265e0b4134606f810211922eb2cb5ffad48ff8d71ea2606","target":"graph","created_at":"2026-05-18T00:45:27Z","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":"Words can be represented by composing the representations of subword units such as word segments, characters, and/or character n-grams. While such representations are effective and may capture the morphological regularities of words, they have not been systematically compared, and it is not understood how they interact with different morphological typologies. On a language modeling task, we present experiments that systematically vary (1) the basic unit of representation, (2) the composition of these representations, and (3) the morphological typology of the language modeled. Our results exten","authors_text":"Adam Lopez, Clara Vania","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T21:10:53Z","title":"From Characters to Words to in Between: Do We Capture Morphology?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1704.08352","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:c9bf7d0206cbe03e848974a329f4fc2d261e9d6701e11e2f288db16915803384","target":"record","created_at":"2026-05-18T00:45:27Z","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":"f3e80b52b7768fe73ea26c732f5e58cf7b8d280c6d546c4c46e7c07fb320b0a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-04-26T21:10:53Z","title_canon_sha256":"00ee9b438f9f4bd146122ad2ad8bea20db535935249e74477f5d5c5a33de8eaa"},"schema_version":"1.0","source":{"id":"1704.08352","kind":"arxiv","version":1}},"canonical_sha256":"cda43945cf52ad6931ab6cb494e8c00ca6853a808705c4d15c70328acf084b3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cda43945cf52ad6931ab6cb494e8c00ca6853a808705c4d15c70328acf084b3d","first_computed_at":"2026-05-18T00:45:27.890540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:27.890540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qm920E0aJQCtEALMuYhWrSIdtkDzy2hJ9mnkhMFCgOeDKfg1W+PStquuLcqzuiANVnlcAy+IMuxWNNssqunTAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:27.890958Z","signed_message":"canonical_sha256_bytes"},"source_id":"1704.08352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9bf7d0206cbe03e848974a329f4fc2d261e9d6701e11e2f288db16915803384","sha256:e857b0ff2f009383c265e0b4134606f810211922eb2cb5ffad48ff8d71ea2606"],"state_sha256":"98fa05afce77eda7f5f9ab26a23080021b4cfe1fb7128b1f75737afd7af7fd77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4uaVues7WRLzKnTvj4c1aETBJQrrppgjiabXSdgq5n1NFL/pl1x+ef1Rr6/p4F/EJ5quVjuIbmAC0dP0pZc6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T00:58:07.474484Z","bundle_sha256":"e31b17a5b8ba7aa37fdf265b2b7eed9b49dfba5236e9e6ee7b859aa8e46c1beb"}}