{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:CWGTK27RRWXW5PPPVVDTHDKKNP","short_pith_number":"pith:CWGTK27R","canonical_record":{"source":{"id":"1808.09500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T19:11:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd4f3ed23ec4ec8cb754423e7e743cfe4ceaec00ba66acc2e93f1d4fa9071c08","abstract_canon_sha256":"f17bca156e8b11325ff8756609666b37741ea7b8b3bb7b8444d2bd218e9ebbe6"},"schema_version":"1.0"},"canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","source":{"kind":"arxiv","id":"1808.09500","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09500","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09500v1","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09500","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"pith_short_12","alias_value":"CWGTK27RRWXW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CWGTK27RRWXW5PPP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CWGTK27R","created_at":"2026-05-18T12:32:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:CWGTK27RRWXW5PPPVVDTHDKKNP","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09500","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T19:11:20Z","cross_cats_sorted":[],"title_canon_sha256":"dd4f3ed23ec4ec8cb754423e7e743cfe4ceaec00ba66acc2e93f1d4fa9071c08","abstract_canon_sha256":"f17bca156e8b11325ff8756609666b37741ea7b8b3bb7b8444d2bd218e9ebbe6"},"schema_version":"1.0"},"canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:55.394252Z","signature_b64":"IYQqWulnsmDG+FssL04VHui2nfFbTXnEEZenv5kP+DJFH7aIR39m5QHNQ47ZIBzYByXPHg8IjVZRicpsRHN4Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","last_reissued_at":"2026-05-18T00:06:55.393599Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:55.393599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09500","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":"2026-05-18T00:06:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"svfIxHzrgvJxRor3aVO7QAjKSLpV37PBbq7ScNSUpu1HJAputOC+noZl1b3wEOQLuOJQCZRh5GfZZ31Wia71DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:35:02.073106Z"},"content_sha256":"f11bcebc5960e2882c127371b252c8b764b81a780120618e0266717f7d3f8fec","schema_version":"1.0","event_id":"sha256:f11bcebc5960e2882c127371b252c8b764b81a780120618e0266717f7d3f8fec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:CWGTK27RRWXW5PPPVVDTHDKKNP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aditi Chaudhary, Chunting Zhou, David R. Mortensen, Graham Neubig, Jaime G. Carbonell, Lori Levin","submitted_at":"2018-08-28T19:11:20Z","abstract_excerpt":"Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Reco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09500","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":"2026-05-18T00:06:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Is4FmJw87m/Z8Uj7lu+LPPXdf4vU5muhhKzDf2hKNU3UMTMwOK6m8bxYDQogGKw5h2YY9tNI1fpjOW1VlheLDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:35:02.073472Z"},"content_sha256":"cb75913dd1c51469831298456328139ba185f584076b4b40872149657cd0dd52","schema_version":"1.0","event_id":"sha256:cb75913dd1c51469831298456328139ba185f584076b4b40872149657cd0dd52"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/bundle.json","state_url":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/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":"2026-05-28T14:35:02Z","links":{"resolver":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP","bundle":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/bundle.json","state":"https://pith.science/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CWGTK27RRWXW5PPPVVDTHDKKNP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:CWGTK27RRWXW5PPPVVDTHDKKNP","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":"f17bca156e8b11325ff8756609666b37741ea7b8b3bb7b8444d2bd218e9ebbe6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T19:11:20Z","title_canon_sha256":"dd4f3ed23ec4ec8cb754423e7e743cfe4ceaec00ba66acc2e93f1d4fa9071c08"},"schema_version":"1.0","source":{"id":"1808.09500","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09500","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09500v1","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09500","created_at":"2026-05-18T00:06:55Z"},{"alias_kind":"pith_short_12","alias_value":"CWGTK27RRWXW","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_16","alias_value":"CWGTK27RRWXW5PPP","created_at":"2026-05-18T12:32:19Z"},{"alias_kind":"pith_short_8","alias_value":"CWGTK27R","created_at":"2026-05-18T12:32:19Z"}],"graph_snapshots":[{"event_id":"sha256:cb75913dd1c51469831298456328139ba185f584076b4b40872149657cd0dd52","target":"graph","created_at":"2026-05-18T00:06:55Z","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":"Much work in Natural Language Processing (NLP) has been for resource-rich languages, making generalization to new, less-resourced languages challenging. We present two approaches for improving generalization to low-resourced languages by adapting continuous word representations using linguistically motivated subword units: phonemes, morphemes and graphemes. Our method requires neither parallel corpora nor bilingual dictionaries and provides a significant gain in performance over previous methods relying on these resources. We demonstrate the effectiveness of our approaches on Named Entity Reco","authors_text":"Aditi Chaudhary, Chunting Zhou, David R. Mortensen, Graham Neubig, Jaime G. Carbonell, Lori Levin","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T19:11:20Z","title":"Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09500","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:f11bcebc5960e2882c127371b252c8b764b81a780120618e0266717f7d3f8fec","target":"record","created_at":"2026-05-18T00:06:55Z","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":"f17bca156e8b11325ff8756609666b37741ea7b8b3bb7b8444d2bd218e9ebbe6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-28T19:11:20Z","title_canon_sha256":"dd4f3ed23ec4ec8cb754423e7e743cfe4ceaec00ba66acc2e93f1d4fa9071c08"},"schema_version":"1.0","source":{"id":"1808.09500","kind":"arxiv","version":1}},"canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"158d356bf18daf6ebdefad47338d4a6bf597a17745c8f9d3ba4b3fba210d41ae","first_computed_at":"2026-05-18T00:06:55.393599Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:55.393599Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IYQqWulnsmDG+FssL04VHui2nfFbTXnEEZenv5kP+DJFH7aIR39m5QHNQ47ZIBzYByXPHg8IjVZRicpsRHN4Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:55.394252Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09500","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f11bcebc5960e2882c127371b252c8b764b81a780120618e0266717f7d3f8fec","sha256:cb75913dd1c51469831298456328139ba185f584076b4b40872149657cd0dd52"],"state_sha256":"7f918059ed2c0fd8988df9b11f5e86345a6b1d946c267fe5939b32a0c26d9f63"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HYpyPGEmZGkDmaX5jt+I3TZ4l3Az034TsgxN6s7Cc1yaQKsWqzhIC1lGMGktq2RHyDXtjV5pPUOzHyus22NmAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:35:02.075682Z","bundle_sha256":"db896b23dd4b4d0587cd662eb9a419ef9846812d8b5f75fe6e59d6b62bff17fe"}}