{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:JR3YPPC6HMMDSFRIUVRFSMNJIT","short_pith_number":"pith:JR3YPPC6","canonical_record":{"source":{"id":"1904.04307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T19:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"03aef451bb57fb2dde332a4d3471f9ca762c9931b0a6a358a4bf0e353618faaa","abstract_canon_sha256":"1c51553e57d8dd5fadf19ac4dce15ea55dec071dc77a590c616dcc428109dcc2"},"schema_version":"1.0"},"canonical_sha256":"4c7787bc5e3b18391628a5625931a944ed312998777a9aa371df62d8840fc2fc","source":{"kind":"arxiv","id":"1904.04307","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04307","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04307v1","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04307","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"JR3YPPC6HMMD","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JR3YPPC6HMMDSFRI","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JR3YPPC6","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:JR3YPPC6HMMDSFRIUVRFSMNJIT","target":"record","payload":{"canonical_record":{"source":{"id":"1904.04307","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T19:18:09Z","cross_cats_sorted":[],"title_canon_sha256":"03aef451bb57fb2dde332a4d3471f9ca762c9931b0a6a358a4bf0e353618faaa","abstract_canon_sha256":"1c51553e57d8dd5fadf19ac4dce15ea55dec071dc77a590c616dcc428109dcc2"},"schema_version":"1.0"},"canonical_sha256":"4c7787bc5e3b18391628a5625931a944ed312998777a9aa371df62d8840fc2fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:59.338283Z","signature_b64":"Vqw6LWzpVmvnwjf+KzsHFfkBoLaVoQEDjRxP70sSVVi8UjmnBMVZ29J0/0Rqune/olX0jRTMWF8fWdElPNQoCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c7787bc5e3b18391628a5625931a944ed312998777a9aa371df62d8840fc2fc","last_reissued_at":"2026-05-17T23:48:59.337926Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:59.337926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.04307","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X1Nj9L9ohfPx8vSQZn2f3jWYKS+jLnO9dK+PScQuU+ECO7/IIaHIl+avS2UyGQ5Wy17BgUeV2+s6UwOmGJ8PBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:41:42.922266Z"},"content_sha256":"1f282b35115d0985358f4e8d016021388ef95b7d6d57b87e6f9def0a5365a178","schema_version":"1.0","event_id":"sha256:1f282b35115d0985358f4e8d016021388ef95b7d6d57b87e6f9def0a5365a178"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:JR3YPPC6HMMDSFRIUVRFSMNJIT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Similarity Datasets for Thai: Construction and Evaluation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aleksei Pulich, Gerhard Wohlgenannt, Ponrudee Netisopakul","submitted_at":"2019-04-08T19:18:09Z","abstract_excerpt":"Distributional semantics in the form of word embeddings are an essential ingredient to many modern natural language processing systems. The quantification of semantic similarity between words can be used to evaluate the ability of a system to perform semantic interpretation. To this end, a number of word similarity datasets have been created for the English language over the last decades. For Thai language few such resources are available. In this work, we create three Thai word similarity datasets by translating and re-rating the popular WordSim-353, SimLex-999 and SemEval-2017-Task-2 dataset"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04307","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:48:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3J3j1DlualySfZbbOkKDQjNbjFwLkPVa4+IzzVp/KmIW0oYvlwR6D1TNfzsdPwLozODL/vObo6ne1uQzdxxoCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T17:41:42.922677Z"},"content_sha256":"8fc416766db6d2e42305e360d6040445b70c358a9aeaa00c721af561f48f853e","schema_version":"1.0","event_id":"sha256:8fc416766db6d2e42305e360d6040445b70c358a9aeaa00c721af561f48f853e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT/bundle.json","state_url":"https://pith.science/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-04T17:41:42Z","links":{"resolver":"https://pith.science/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT","bundle":"https://pith.science/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT/bundle.json","state":"https://pith.science/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JR3YPPC6HMMDSFRIUVRFSMNJIT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:JR3YPPC6HMMDSFRIUVRFSMNJIT","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":"1c51553e57d8dd5fadf19ac4dce15ea55dec071dc77a590c616dcc428109dcc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T19:18:09Z","title_canon_sha256":"03aef451bb57fb2dde332a4d3471f9ca762c9931b0a6a358a4bf0e353618faaa"},"schema_version":"1.0","source":{"id":"1904.04307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.04307","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"arxiv_version","alias_value":"1904.04307v1","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.04307","created_at":"2026-05-17T23:48:59Z"},{"alias_kind":"pith_short_12","alias_value":"JR3YPPC6HMMD","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"JR3YPPC6HMMDSFRI","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"JR3YPPC6","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:8fc416766db6d2e42305e360d6040445b70c358a9aeaa00c721af561f48f853e","target":"graph","created_at":"2026-05-17T23:48:59Z","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":"Distributional semantics in the form of word embeddings are an essential ingredient to many modern natural language processing systems. The quantification of semantic similarity between words can be used to evaluate the ability of a system to perform semantic interpretation. To this end, a number of word similarity datasets have been created for the English language over the last decades. For Thai language few such resources are available. In this work, we create three Thai word similarity datasets by translating and re-rating the popular WordSim-353, SimLex-999 and SemEval-2017-Task-2 dataset","authors_text":"Aleksei Pulich, Gerhard Wohlgenannt, Ponrudee Netisopakul","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T19:18:09Z","title":"Word Similarity Datasets for Thai: Construction and Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.04307","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":"sha256:1f282b35115d0985358f4e8d016021388ef95b7d6d57b87e6f9def0a5365a178","target":"record","created_at":"2026-05-17T23:48:59Z","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":"1c51553e57d8dd5fadf19ac4dce15ea55dec071dc77a590c616dcc428109dcc2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T19:18:09Z","title_canon_sha256":"03aef451bb57fb2dde332a4d3471f9ca762c9931b0a6a358a4bf0e353618faaa"},"schema_version":"1.0","source":{"id":"1904.04307","kind":"arxiv","version":1}},"canonical_sha256":"4c7787bc5e3b18391628a5625931a944ed312998777a9aa371df62d8840fc2fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c7787bc5e3b18391628a5625931a944ed312998777a9aa371df62d8840fc2fc","first_computed_at":"2026-05-17T23:48:59.337926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:59.337926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Vqw6LWzpVmvnwjf+KzsHFfkBoLaVoQEDjRxP70sSVVi8UjmnBMVZ29J0/0Rqune/olX0jRTMWF8fWdElPNQoCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:59.338283Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.04307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f282b35115d0985358f4e8d016021388ef95b7d6d57b87e6f9def0a5365a178","sha256:8fc416766db6d2e42305e360d6040445b70c358a9aeaa00c721af561f48f853e"],"state_sha256":"639c423bc7a478fabdd146363b22cf99e2d7d4a7682e91dcc530f5406f31124f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"15fqlPFV4KjKKefNkJcrDrMKruNpsOKRe5DErMM89FRVV3TYj7Ko8CCFWkx+bpakD2pOClCI70cf2K6hLu1OAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T17:41:42.925043Z","bundle_sha256":"afa73275409f909d94bd25c0ad9f636dca329bb03c9e8b8614f1d15f437d2206"}}