{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:AJ5TJQMBD6UOY7CQ6O54P27JZ2","short_pith_number":"pith:AJ5TJQMB","canonical_record":{"source":{"id":"1909.02855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T12:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"6b101a704ed739c7467853d5bb0de6cbc79e69497161404aebbc60eceaccb920","abstract_canon_sha256":"1c37e10e4e8b86d8d44b17777559820f83fdb451843796f9d78daf8b36a498b8"},"schema_version":"1.0"},"canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","source":{"kind":"arxiv","id":"1909.02855","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02855","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02855v2","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02855","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"AJ5TJQMBD6UO","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"pith_short_16","alias_value":"AJ5TJQMBD6UOY7CQ","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"pith_short_8","alias_value":"AJ5TJQMB","created_at":"2026-07-05T00:13:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:AJ5TJQMBD6UOY7CQ6O54P27JZ2","target":"record","payload":{"canonical_record":{"source":{"id":"1909.02855","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T12:27:43Z","cross_cats_sorted":[],"title_canon_sha256":"6b101a704ed739c7467853d5bb0de6cbc79e69497161404aebbc60eceaccb920","abstract_canon_sha256":"1c37e10e4e8b86d8d44b17777559820f83fdb451843796f9d78daf8b36a498b8"},"schema_version":"1.0"},"canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:13:55.429936Z","signature_b64":"zfh7hNmOisA9nNo4In7thiLycwsKV/NLumVotim7UQrsuchDtib8Y+dWhAan6tYdE5U2KomECJyBNv+2WaKmAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","last_reissued_at":"2026-07-05T00:13:55.429523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:13:55.429523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1909.02855","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":"2026-07-05T00:13:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pQPa46cK+uNaOUAxxub1IaRqKTlU+CMbjHXfihp/irTI5vUR7iD1eqw08++aHOGazAMpGsd76SSXk88ZOQnzAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:15:40.753049Z"},"content_sha256":"dc068fc509c7b2eb74831412781ac42eb9fb4478ea61f3971afc5fca37482060","schema_version":"1.0","event_id":"sha256:dc068fc509c7b2eb74831412781ac42eb9fb4478ea61f3971afc5fca37482060"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:AJ5TJQMBD6UOY7CQ6O54P27JZ2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ann Copestake, Edouard Grave, Paula Czarnowska, Ryan Cotterell, Sebastian Ruder","submitted_at":"2019-09-06T12:27:43Z","abstract_excerpt":"Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a statistically rare inflection such as habl\\'aramos. Note the lexeme itself, hablar, is relatively common. In this work, we investigate whether state-of-the-art bilingual lexicon inducers are capable of learning this kind of generalization. We introduce 40 morphologically complete dictionaries in 10 languages and evaluate three of the state-of-the-art models"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02855","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/1909.02855/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":"2026-07-05T00:13:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tuSKU/9/MBO3Sc7a9V4dZyMWyi/x+DJOelcbXkAFHvfyq4nDNr1WFVUzpGTuTk1fUH5XoC2iE0k0u6Y/afw2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:15:40.753445Z"},"content_sha256":"367e96f84c53b223a3eebc03cac374eb10f5fbfe45ee96cdcae9f65fe7f28c35","schema_version":"1.0","event_id":"sha256:367e96f84c53b223a3eebc03cac374eb10f5fbfe45ee96cdcae9f65fe7f28c35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/bundle.json","state_url":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/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":"2026-07-08T07:15:40Z","links":{"resolver":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2","bundle":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/bundle.json","state":"https://pith.science/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AJ5TJQMBD6UOY7CQ6O54P27JZ2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:AJ5TJQMBD6UOY7CQ6O54P27JZ2","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":"1c37e10e4e8b86d8d44b17777559820f83fdb451843796f9d78daf8b36a498b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T12:27:43Z","title_canon_sha256":"6b101a704ed739c7467853d5bb0de6cbc79e69497161404aebbc60eceaccb920"},"schema_version":"1.0","source":{"id":"1909.02855","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1909.02855","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"arxiv_version","alias_value":"1909.02855v2","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1909.02855","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"pith_short_12","alias_value":"AJ5TJQMBD6UO","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"pith_short_16","alias_value":"AJ5TJQMBD6UOY7CQ","created_at":"2026-07-05T00:13:55Z"},{"alias_kind":"pith_short_8","alias_value":"AJ5TJQMB","created_at":"2026-07-05T00:13:55Z"}],"graph_snapshots":[{"event_id":"sha256:367e96f84c53b223a3eebc03cac374eb10f5fbfe45ee96cdcae9f65fe7f28c35","target":"graph","created_at":"2026-07-05T00:13:55Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1909.02855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human translators routinely have to translate rare inflections of words - due to the Zipfian distribution of words in a language. When translating from Spanish, a good translator would have no problem identifying the proper translation of a statistically rare inflection such as habl\\'aramos. Note the lexeme itself, hablar, is relatively common. In this work, we investigate whether state-of-the-art bilingual lexicon inducers are capable of learning this kind of generalization. We introduce 40 morphologically complete dictionaries in 10 languages and evaluate three of the state-of-the-art models","authors_text":"Ann Copestake, Edouard Grave, Paula Czarnowska, Ryan Cotterell, Sebastian Ruder","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T12:27:43Z","title":"Don't Forget the Long Tail! A Comprehensive Analysis of Morphological Generalization in Bilingual Lexicon Induction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1909.02855","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:dc068fc509c7b2eb74831412781ac42eb9fb4478ea61f3971afc5fca37482060","target":"record","created_at":"2026-07-05T00:13:55Z","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":"1c37e10e4e8b86d8d44b17777559820f83fdb451843796f9d78daf8b36a498b8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-09-06T12:27:43Z","title_canon_sha256":"6b101a704ed739c7467853d5bb0de6cbc79e69497161404aebbc60eceaccb920"},"schema_version":"1.0","source":{"id":"1909.02855","kind":"arxiv","version":2}},"canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"027b34c1811fa8ec7c50f3bbc7ebe9cea15c6184b34e07dab327c00d835ae047","first_computed_at":"2026-07-05T00:13:55.429523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:13:55.429523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zfh7hNmOisA9nNo4In7thiLycwsKV/NLumVotim7UQrsuchDtib8Y+dWhAan6tYdE5U2KomECJyBNv+2WaKmAA==","signature_status":"signed_v1","signed_at":"2026-07-05T00:13:55.429936Z","signed_message":"canonical_sha256_bytes"},"source_id":"1909.02855","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc068fc509c7b2eb74831412781ac42eb9fb4478ea61f3971afc5fca37482060","sha256:367e96f84c53b223a3eebc03cac374eb10f5fbfe45ee96cdcae9f65fe7f28c35"],"state_sha256":"12e15012ca20e89c9d7b58b4018b935597504db5f309369ba89e17c6654ea271"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JW16rvmZN+BKa50MVQFgB8dLTsgbUf+/A5FJ8ctVbmjrasJ5c0ScRszVQRc4Ml6PNWTL7ehh9kL8ASOWRH1qCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:15:40.755764Z","bundle_sha256":"342a551d294e46662d0274a8c95ced56a3f30210d348353240d02d4100615b20"}}