{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CUFBVWZUWFGLNVSLRTTHPP3Y6E","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":"ef9668d28278e2371e06cc8c2724660f657732f7108f191d2417903148e2e22e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-17T09:36:40Z","title_canon_sha256":"2e8b2bdb34a3fe664d2f643818c1f90c6ace40de24e23ac3e29330522c45c6b5"},"schema_version":"1.0","source":{"id":"1709.05631","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.05631","created_at":"2026-05-18T00:34:54Z"},{"alias_kind":"arxiv_version","alias_value":"1709.05631v2","created_at":"2026-05-18T00:34:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.05631","created_at":"2026-05-18T00:34:54Z"},{"alias_kind":"pith_short_12","alias_value":"CUFBVWZUWFGL","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CUFBVWZUWFGLNVSL","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CUFBVWZU","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:89ca8d93e4421ff54c0dffdbe738b9bb692a20104d8c0a22b35c416a67e9f784","target":"graph","created_at":"2026-05-18T00:34:54Z","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":"Word discovery is the task of extracting words from unsegmented text. In this paper we examine to what extent neural networks can be applied to this task in a realistic unwritten language scenario, where only small corpora and limited annotations are available. We investigate two scenarios: one with no supervision and another with limited supervision with access to the most frequent words. Obtained results show that it is possible to retrieve at least 27% of the gold standard vocabulary by training an encoder-decoder neural machine translation system with only 5,157 sentences. This result is c","authors_text":"Alexandre Berard, Aline Villavicencio, Laurent Besacier, Marcely Zanon Boito","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-17T09:36:40Z","title":"Unwritten Languages Demand Attention Too! Word Discovery with Encoder-Decoder Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.05631","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":"sha256:5bd34d096b0dc29355606a64ac8cf3086df79ebf4de78339efd6f54d9d99e253","target":"record","created_at":"2026-05-18T00:34:54Z","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":"ef9668d28278e2371e06cc8c2724660f657732f7108f191d2417903148e2e22e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-09-17T09:36:40Z","title_canon_sha256":"2e8b2bdb34a3fe664d2f643818c1f90c6ace40de24e23ac3e29330522c45c6b5"},"schema_version":"1.0","source":{"id":"1709.05631","kind":"arxiv","version":2}},"canonical_sha256":"150a1adb34b14cb6d64b8ce677bf78f12e82634123016fde88c1f4dad504c9a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"150a1adb34b14cb6d64b8ce677bf78f12e82634123016fde88c1f4dad504c9a8","first_computed_at":"2026-05-18T00:34:54.476567Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:34:54.476567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CLcfUdL+daMu158wYk/FKp91pA+RSQAK6SO6xNmPTzBUR8aQ5Idx9ElZuLs1QGX366TlRcePBhMtWJ4F6DLxCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:34:54.477249Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.05631","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5bd34d096b0dc29355606a64ac8cf3086df79ebf4de78339efd6f54d9d99e253","sha256:89ca8d93e4421ff54c0dffdbe738b9bb692a20104d8c0a22b35c416a67e9f784"],"state_sha256":"d7ac70062a90073e16c8ad338008a970eb74bc7451959155181d51abf71186a6"}