{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:YBYTULH2XGD6AT75JTWOAM5PBQ","short_pith_number":"pith:YBYTULH2","schema_version":"1.0","canonical_sha256":"c0713a2cfab987e04ffd4cece033af0c3521685185afe18b1f09130b33c99b66","source":{"kind":"arxiv","id":"1804.06024","version":1},"attestation_state":"computed","paper":{"title":"Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Ivan Meza-Ruiz, Katharina Kann, Manuel Mager","submitted_at":"2018-04-17T03:10:51Z","abstract_excerpt":"Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce. Since neural sequence-to-sequence (seq2seq) models define the state of the art for morphological segmentation in high-resource settings and for (mostly) European languages, we first show that they also obtain competitive performance for Mexican polysynthetic languages in minimal-resource settings. We then propose two novel multi-task training approaches -one with, one without need for external unlabeled resources-, and two cor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1804.06024","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T03:10:51Z","cross_cats_sorted":[],"title_canon_sha256":"fd27fef6612bc9429a6fab2d3e6d5fc044e2ada11534780049af6333bfb29fd4","abstract_canon_sha256":"a6323ddb75a2f1ffe22f1a254e60278f2f1e9d0072c47d6da264c6c6a3b0ae93"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:21.988472Z","signature_b64":"1HADD1+9LQ+jeKtynj18YZdNwkOOmgN88fYGPmkZ1R+7/g/s4UF6K7USifmggP+iD8Qj1Y3TULTj6EHQh9BeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0713a2cfab987e04ffd4cece033af0c3521685185afe18b1f09130b33c99b66","last_reissued_at":"2026-05-18T00:18:21.987692Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:21.987692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fortification of Neural Morphological Segmentation Models for Polysynthetic Minimal-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Ivan Meza-Ruiz, Katharina Kann, Manuel Mager","submitted_at":"2018-04-17T03:10:51Z","abstract_excerpt":"Morphological segmentation for polysynthetic languages is challenging, because a word may consist of many individual morphemes and training data can be extremely scarce. Since neural sequence-to-sequence (seq2seq) models define the state of the art for morphological segmentation in high-resource settings and for (mostly) European languages, we first show that they also obtain competitive performance for Mexican polysynthetic languages in minimal-resource settings. We then propose two novel multi-task training approaches -one with, one without need for external unlabeled resources-, and two cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06024","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1804.06024","created_at":"2026-05-18T00:18:21.987805+00:00"},{"alias_kind":"arxiv_version","alias_value":"1804.06024v1","created_at":"2026-05-18T00:18:21.987805+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06024","created_at":"2026-05-18T00:18:21.987805+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBYTULH2XGD6","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBYTULH2XGD6AT75","created_at":"2026-05-18T12:33:04.347982+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBYTULH2","created_at":"2026-05-18T12:33:04.347982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ","json":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ.json","graph_json":"https://pith.science/api/pith-number/YBYTULH2XGD6AT75JTWOAM5PBQ/graph.json","events_json":"https://pith.science/api/pith-number/YBYTULH2XGD6AT75JTWOAM5PBQ/events.json","paper":"https://pith.science/paper/YBYTULH2"},"agent_actions":{"view_html":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ","download_json":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ.json","view_paper":"https://pith.science/paper/YBYTULH2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1804.06024&json=true","fetch_graph":"https://pith.science/api/pith-number/YBYTULH2XGD6AT75JTWOAM5PBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YBYTULH2XGD6AT75JTWOAM5PBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ/action/storage_attestation","attest_author":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ/action/author_attestation","sign_citation":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ/action/citation_signature","submit_replication":"https://pith.science/pith/YBYTULH2XGD6AT75JTWOAM5PBQ/action/replication_record"}},"created_at":"2026-05-18T00:18:21.987805+00:00","updated_at":"2026-05-18T00:18:21.987805+00:00"}