{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:FHTBS24DQDOL3NECA2TV45ZB5A","short_pith_number":"pith:FHTBS24D","schema_version":"1.0","canonical_sha256":"29e6196b8380dcbdb48206a75e7721e8386a13b4d71a66787a7264449f66cb02","source":{"kind":"arxiv","id":"1806.03746","version":2},"attestation_state":"computed","paper":{"title":"A Structured Variational Autoencoder for Contextual Morphological Inflection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jason Naradowsky, Lawrence Wolf-Sonkin, Ryan Cotterell, Sabrina J. Mielke","submitted_at":"2018-06-10T23:47:53Z","abstract_excerpt":"Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-r"},"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":"1806.03746","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-10T23:47:53Z","cross_cats_sorted":[],"title_canon_sha256":"02b090dcdc54c1b9855d103e331060f55570c65145343f720efa34d7c1784f9c","abstract_canon_sha256":"aed120a5c25f0ede9fe5981b69eec29156524ebf5a43678178066e01ed77e6d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:43:30.913099Z","signature_b64":"XjEwUc5/ipB7tde+fb4uHyMxAzfIckxVBrIPCr0eBC9pqSe9zCkTvzCvnmjr8pcWHs55nvyQq7Cnh8dbtjZjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29e6196b8380dcbdb48206a75e7721e8386a13b4d71a66787a7264449f66cb02","last_reissued_at":"2026-07-05T00:43:30.912715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:43:30.912715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Structured Variational Autoencoder for Contextual Morphological Inflection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jason Naradowsky, Lawrence Wolf-Sonkin, Ryan Cotterell, Sabrina J. Mielke","submitted_at":"2018-06-10T23:47:53Z","abstract_excerpt":"Statistical morphological inflectors are typically trained on fully supervised, type-level data. One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance? To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation. To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm. We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.03746","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/1806.03746/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":"1806.03746","created_at":"2026-07-05T00:43:30.912776+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.03746v2","created_at":"2026-07-05T00:43:30.912776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.03746","created_at":"2026-07-05T00:43:30.912776+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHTBS24DQDOL","created_at":"2026-07-05T00:43:30.912776+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHTBS24DQDOL3NEC","created_at":"2026-07-05T00:43:30.912776+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHTBS24D","created_at":"2026-07-05T00:43:30.912776+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/FHTBS24DQDOL3NECA2TV45ZB5A","json":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A.json","graph_json":"https://pith.science/api/pith-number/FHTBS24DQDOL3NECA2TV45ZB5A/graph.json","events_json":"https://pith.science/api/pith-number/FHTBS24DQDOL3NECA2TV45ZB5A/events.json","paper":"https://pith.science/paper/FHTBS24D"},"agent_actions":{"view_html":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A","download_json":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A.json","view_paper":"https://pith.science/paper/FHTBS24D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.03746&json=true","fetch_graph":"https://pith.science/api/pith-number/FHTBS24DQDOL3NECA2TV45ZB5A/graph.json","fetch_events":"https://pith.science/api/pith-number/FHTBS24DQDOL3NECA2TV45ZB5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A/action/storage_attestation","attest_author":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A/action/author_attestation","sign_citation":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A/action/citation_signature","submit_replication":"https://pith.science/pith/FHTBS24DQDOL3NECA2TV45ZB5A/action/replication_record"}},"created_at":"2026-07-05T00:43:30.912776+00:00","updated_at":"2026-07-05T00:43:30.912776+00:00"}