{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GYGD7RAXUZVVORQG6DP6RT43O2","short_pith_number":"pith:GYGD7RAX","schema_version":"1.0","canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","source":{"kind":"arxiv","id":"2005.00956","version":1},"attestation_state":"computed","paper":{"title":"Bootstrapping Techniques for Polysynthetic Morphological Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Steven Bird, William Lane","submitted_at":"2020-05-03T00:35:19Z","abstract_excerpt":"Polysynthetic languages have exceptionally large and sparse vocabularies, thanks to the number of morpheme slots and combinations in a word. This complexity, together with a general scarcity of written data, poses a challenge to the development of natural language technologies. To address this challenge, we offer linguistically-informed approaches for bootstrapping a neural morphological analyzer, and demonstrate its application to Kunwinjku, a polysynthetic Australian language. We generate data from a finite state transducer to train an encoder-decoder model. We improve the model by \"hallucin"},"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":"2005.00956","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-03T00:35:19Z","cross_cats_sorted":[],"title_canon_sha256":"131e7464b382e81278d112d59d30c65eb33fe931628649d60f13d91630c1424c","abstract_canon_sha256":"9c57816eb03099d8ad35f6b78fbff93905795af84a6890f426cbdfbd8228d758"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:00:02.613732Z","signature_b64":"CHIxJdcLSMrRiIyl6AbX9L6fq8ro/rwPKtHNr7m0ttq9Hmk0lv39YvYtOkPmEPBK/xKdTeJG36ZND6ircwlFBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"360c3fc417a66b574606f0dfe8cf9b769b18f5ecab0f4ede99d0b73ab19e6403","last_reissued_at":"2026-07-05T01:00:02.613266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:00:02.613266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bootstrapping Techniques for Polysynthetic Morphological Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Steven Bird, William Lane","submitted_at":"2020-05-03T00:35:19Z","abstract_excerpt":"Polysynthetic languages have exceptionally large and sparse vocabularies, thanks to the number of morpheme slots and combinations in a word. This complexity, together with a general scarcity of written data, poses a challenge to the development of natural language technologies. To address this challenge, we offer linguistically-informed approaches for bootstrapping a neural morphological analyzer, and demonstrate its application to Kunwinjku, a polysynthetic Australian language. We generate data from a finite state transducer to train an encoder-decoder model. We improve the model by \"hallucin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.00956","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/2005.00956/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2005.00956","created_at":"2026-07-05T01:00:02.613336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.00956v1","created_at":"2026-07-05T01:00:02.613336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.00956","created_at":"2026-07-05T01:00:02.613336+00:00"},{"alias_kind":"pith_short_12","alias_value":"GYGD7RAXUZVV","created_at":"2026-07-05T01:00:02.613336+00:00"},{"alias_kind":"pith_short_16","alias_value":"GYGD7RAXUZVVORQG","created_at":"2026-07-05T01:00:02.613336+00:00"},{"alias_kind":"pith_short_8","alias_value":"GYGD7RAX","created_at":"2026-07-05T01:00:02.613336+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/GYGD7RAXUZVVORQG6DP6RT43O2","json":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2.json","graph_json":"https://pith.science/api/pith-number/GYGD7RAXUZVVORQG6DP6RT43O2/graph.json","events_json":"https://pith.science/api/pith-number/GYGD7RAXUZVVORQG6DP6RT43O2/events.json","paper":"https://pith.science/paper/GYGD7RAX"},"agent_actions":{"view_html":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2","download_json":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2.json","view_paper":"https://pith.science/paper/GYGD7RAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.00956&json=true","fetch_graph":"https://pith.science/api/pith-number/GYGD7RAXUZVVORQG6DP6RT43O2/graph.json","fetch_events":"https://pith.science/api/pith-number/GYGD7RAXUZVVORQG6DP6RT43O2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/action/storage_attestation","attest_author":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/action/author_attestation","sign_citation":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/action/citation_signature","submit_replication":"https://pith.science/pith/GYGD7RAXUZVVORQG6DP6RT43O2/action/replication_record"}},"created_at":"2026-07-05T01:00:02.613336+00:00","updated_at":"2026-07-05T01:00:02.613336+00:00"}