{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QPM6OPMDR3TXETR2ESFDXM5OCJ","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":"21d28bce968e80bcfadefef8462eac4970ac2127aba5245faa77142d76a94612","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T21:07:31Z","title_canon_sha256":"7f9ffbd8061c93ae6cc1bb68ee07da52214bb835c2ad5ec8a5040073baa7bf86"},"schema_version":"1.0","source":{"id":"2606.17299","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.17299","created_at":"2026-06-19T16:10:08Z"},{"alias_kind":"arxiv_version","alias_value":"2606.17299v1","created_at":"2026-06-19T16:10:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.17299","created_at":"2026-06-19T16:10:08Z"},{"alias_kind":"pith_short_12","alias_value":"QPM6OPMDR3TX","created_at":"2026-06-19T16:10:08Z"},{"alias_kind":"pith_short_16","alias_value":"QPM6OPMDR3TXETR2","created_at":"2026-06-19T16:10:08Z"},{"alias_kind":"pith_short_8","alias_value":"QPM6OPMD","created_at":"2026-06-19T16:10:08Z"}],"graph_snapshots":[{"event_id":"sha256:5a5c61eeacda84f483e8e16ff70701b16bcbf188b59436eb4a42b21eb4d55c1c","target":"graph","created_at":"2026-06-19T16:10:08Z","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/2606.17299/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Word2Vec's effectiveness at generating semantic embeddings has been widely validated, yet it has been tested almost exclusively on languages with large vocabulary inventories. This study examines whether Word2Vec can successfully capture semantic relationships within an extremely reduced vocabulary using data from Toki Pona, a constructed language with approximately 130 words. We sourced 1.4 million sentences (7.95 million tokens) from the Toki Pona community for training. Approximately 23% of sentences in the corpus contain non-Toki Pona tokens such as named entities, loanwords, and neologism","authors_text":"Daniel Zhenhan Huang, Hongchen Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T21:07:31Z","title":"Examining the Limits of Word2Vec with Toki Pona"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.17299","kind":"arxiv","version":1},"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:f8109831146b1cc07eb52b5408183c85ee3df888bd3538d8380ec38206a017e0","target":"record","created_at":"2026-06-19T16:10:08Z","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":"21d28bce968e80bcfadefef8462eac4970ac2127aba5245faa77142d76a94612","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-15T21:07:31Z","title_canon_sha256":"7f9ffbd8061c93ae6cc1bb68ee07da52214bb835c2ad5ec8a5040073baa7bf86"},"schema_version":"1.0","source":{"id":"2606.17299","kind":"arxiv","version":1}},"canonical_sha256":"83d9e73d838ee7724e3a248a3bb3ae1252c1896de80bc4a9a7b49487a995a822","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83d9e73d838ee7724e3a248a3bb3ae1252c1896de80bc4a9a7b49487a995a822","first_computed_at":"2026-06-19T16:10:08.459196Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:10:08.459196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"54ffd1mflTSRK06I2F5KLHKha+QOaOAGOqMERS+/zPIjO3KHYk2wnpjCKZZOw+dpaH2SSSdSIrUdDC11ob1uDw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:10:08.459595Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.17299","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8109831146b1cc07eb52b5408183c85ee3df888bd3538d8380ec38206a017e0","sha256:5a5c61eeacda84f483e8e16ff70701b16bcbf188b59436eb4a42b21eb4d55c1c"],"state_sha256":"40d16998cd981d66ef18e90d68abc60b4bfa4893ac6beb16367e2ad7ce887bf9"}