{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:R4XGF2YVV2N7U2TRLU5SOFVS62","short_pith_number":"pith:R4XGF2YV","canonical_record":{"source":{"id":"2206.07238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T01:53:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b681c2a21c482736148c0109bf049a96640a07e2d37a755cc8dbb571fd6ab803","abstract_canon_sha256":"83810bf085d284ea7a9035a4eebf3df3d458b46737ce0d2f04c11cfa4e07643e"},"schema_version":"1.0"},"canonical_sha256":"8f2e62eb15ae9bfa6a715d3b2716b2f69c3d00afde546ee1f592c4b43296b8e9","source":{"kind":"arxiv","id":"2206.07238","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07238","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07238v1","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07238","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"R4XGF2YVV2N7","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"R4XGF2YVV2N7U2TR","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"R4XGF2YV","created_at":"2026-07-05T04:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:R4XGF2YVV2N7U2TRLU5SOFVS62","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07238","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T01:53:43Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"b681c2a21c482736148c0109bf049a96640a07e2d37a755cc8dbb571fd6ab803","abstract_canon_sha256":"83810bf085d284ea7a9035a4eebf3df3d458b46737ce0d2f04c11cfa4e07643e"},"schema_version":"1.0"},"canonical_sha256":"8f2e62eb15ae9bfa6a715d3b2716b2f69c3d00afde546ee1f592c4b43296b8e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:02.602217Z","signature_b64":"Lfy0GTZrCvIYNQ0s6QJLx1dg8GGwsWVawyJM0mHjpUGyHESPLGjjrOmxVe2fe53OprcP6Ahm33y11EG/EzchCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f2e62eb15ae9bfa6a715d3b2716b2f69c3d00afde546ee1f592c4b43296b8e9","last_reissued_at":"2026-07-05T04:32:02.601810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:02.601810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07238","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":"2026-07-05T04:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h2ZIcSVHFFvZvNqOOI14a0U5IuZvZrIOAiw9rpO03orMnDDat0F+bzebVTXDoed+YxjGolIFNokKz7Ya2KldCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T20:52:17.381796Z"},"content_sha256":"54420a39787cd7861b5668bfa4e9bf95e6fb8a1ebd7981bad6b3f34c38e0745c","schema_version":"1.0","event_id":"sha256:54420a39787cd7861b5668bfa4e9bf95e6fb8a1ebd7981bad6b3f34c38e0745c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:R4XGF2YVV2N7U2TRLU5SOFVS62","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Location-based Twitter Filtering for the Creation of Low-Resource Language Datasets in Indonesian Local Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chong Feng, Heyan Huang, Mukhlis Amien","submitted_at":"2022-06-15T01:53:43Z","abstract_excerpt":"Twitter contains an abundance of linguistic data from the real world. We examine Twitter for user-generated content in low-resource languages such as local Indonesian. For NLP to work in Indonesian, it must consider local dialects, geographic context, and regional culture influence Indonesian languages. This paper identifies the problems we faced when constructing a Local Indonesian NLP dataset. Furthermore, we are developing a framework for creating, collecting, and classifying Local Indonesian datasets for NLP. Using twitter's geolocation tool for automatic annotating."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07238","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/2206.07238/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NxAGXXfLeiBngdBmKsVxBNVABPYERL7fyuClLLnGrHB7vJm6VouLNfwUeWQyrvLmjOIiNeVd9S+SrZq3+8iCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T20:52:17.382184Z"},"content_sha256":"90e96b834107decbf1bfb3dee6ce24109dcd43f07c94be77e7c201ed53a1597b","schema_version":"1.0","event_id":"sha256:90e96b834107decbf1bfb3dee6ce24109dcd43f07c94be77e7c201ed53a1597b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4XGF2YVV2N7U2TRLU5SOFVS62/bundle.json","state_url":"https://pith.science/pith/R4XGF2YVV2N7U2TRLU5SOFVS62/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4XGF2YVV2N7U2TRLU5SOFVS62/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":"2026-08-01T20:52:17Z","links":{"resolver":"https://pith.science/pith/R4XGF2YVV2N7U2TRLU5SOFVS62","bundle":"https://pith.science/pith/R4XGF2YVV2N7U2TRLU5SOFVS62/bundle.json","state":"https://pith.science/pith/R4XGF2YVV2N7U2TRLU5SOFVS62/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4XGF2YVV2N7U2TRLU5SOFVS62/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R4XGF2YVV2N7U2TRLU5SOFVS62","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":"83810bf085d284ea7a9035a4eebf3df3d458b46737ce0d2f04c11cfa4e07643e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T01:53:43Z","title_canon_sha256":"b681c2a21c482736148c0109bf049a96640a07e2d37a755cc8dbb571fd6ab803"},"schema_version":"1.0","source":{"id":"2206.07238","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07238","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07238v1","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07238","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"R4XGF2YVV2N7","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"R4XGF2YVV2N7U2TR","created_at":"2026-07-05T04:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"R4XGF2YV","created_at":"2026-07-05T04:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:90e96b834107decbf1bfb3dee6ce24109dcd43f07c94be77e7c201ed53a1597b","target":"graph","created_at":"2026-07-05T04:32:02Z","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/2206.07238/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Twitter contains an abundance of linguistic data from the real world. We examine Twitter for user-generated content in low-resource languages such as local Indonesian. For NLP to work in Indonesian, it must consider local dialects, geographic context, and regional culture influence Indonesian languages. This paper identifies the problems we faced when constructing a Local Indonesian NLP dataset. Furthermore, we are developing a framework for creating, collecting, and classifying Local Indonesian datasets for NLP. Using twitter's geolocation tool for automatic annotating.","authors_text":"Chong Feng, Heyan Huang, Mukhlis Amien","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T01:53:43Z","title":"Location-based Twitter Filtering for the Creation of Low-Resource Language Datasets in Indonesian Local Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07238","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":"sha256:54420a39787cd7861b5668bfa4e9bf95e6fb8a1ebd7981bad6b3f34c38e0745c","target":"record","created_at":"2026-07-05T04:32:02Z","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":"83810bf085d284ea7a9035a4eebf3df3d458b46737ce0d2f04c11cfa4e07643e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-15T01:53:43Z","title_canon_sha256":"b681c2a21c482736148c0109bf049a96640a07e2d37a755cc8dbb571fd6ab803"},"schema_version":"1.0","source":{"id":"2206.07238","kind":"arxiv","version":1}},"canonical_sha256":"8f2e62eb15ae9bfa6a715d3b2716b2f69c3d00afde546ee1f592c4b43296b8e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f2e62eb15ae9bfa6a715d3b2716b2f69c3d00afde546ee1f592c4b43296b8e9","first_computed_at":"2026-07-05T04:32:02.601810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:02.601810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lfy0GTZrCvIYNQ0s6QJLx1dg8GGwsWVawyJM0mHjpUGyHESPLGjjrOmxVe2fe53OprcP6Ahm33y11EG/EzchCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:02.602217Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07238","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54420a39787cd7861b5668bfa4e9bf95e6fb8a1ebd7981bad6b3f34c38e0745c","sha256:90e96b834107decbf1bfb3dee6ce24109dcd43f07c94be77e7c201ed53a1597b"],"state_sha256":"717fa80e49d8057e6dc37412a51dc17e0770bb2b96df2bafecf4e5dc45da539b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+3APjwEsGrhA1rc416joLrGLY087p55wnx8GFGeUl0jfLS9MMxsPo4+54HNJsKDKdjm7j6pmPkV57nF7Kgi1CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T20:52:17.384448Z","bundle_sha256":"e4a8a3766b624337674deb8ccbadfcd9e62cc72600dd6a970a3185e9baccc394"}}