{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:4NNMCIIUO6PD37FYHVON5XXIBU","short_pith_number":"pith:4NNMCIIU","canonical_record":{"source":{"id":"2207.00552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T17:09:53Z","cross_cats_sorted":[],"title_canon_sha256":"1d95c73995cf7091beb19b409a9d8235e20d3637f5f0336c8663a5af57ecde9f","abstract_canon_sha256":"be923c88a18a9a7172928b2be298b0a61ad25faf5642b04bfcae00ef6971f071"},"schema_version":"1.0"},"canonical_sha256":"e35ac12114779e3dfcb83d5cdedee80d3544aea975c7fbd819462a01b64004b8","source":{"kind":"arxiv","id":"2207.00552","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00552","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00552v1","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00552","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"4NNMCIIUO6PD","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"4NNMCIIUO6PD37FY","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"4NNMCIIU","created_at":"2026-07-05T04:36:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:4NNMCIIUO6PD37FYHVON5XXIBU","target":"record","payload":{"canonical_record":{"source":{"id":"2207.00552","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T17:09:53Z","cross_cats_sorted":[],"title_canon_sha256":"1d95c73995cf7091beb19b409a9d8235e20d3637f5f0336c8663a5af57ecde9f","abstract_canon_sha256":"be923c88a18a9a7172928b2be298b0a61ad25faf5642b04bfcae00ef6971f071"},"schema_version":"1.0"},"canonical_sha256":"e35ac12114779e3dfcb83d5cdedee80d3544aea975c7fbd819462a01b64004b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:44.395218Z","signature_b64":"KbwPKI92SC+W7HpppFwO3UMqOHmcjyr+WqfDbf6liT7KM8kBl3SH6ojmxPLUiczrQj4xqnRdSBTs9zgzGFSQCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e35ac12114779e3dfcb83d5cdedee80d3544aea975c7fbd819462a01b64004b8","last_reissued_at":"2026-07-05T04:36:44.394825Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:44.394825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2207.00552","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":"2026-07-05T04:36:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nu4OBiOS53ZXoqZBaHnBDhnYDRuHtdfZbWeo25LAWEawXLLJL75u4prt9gdwVAa/eLPUDmPBM/73qEN07fWsCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:06:48.544609Z"},"content_sha256":"61301ffc17b39a14a276f916bb1b4c6656479de4a7716e2678044ca4d37f579e","schema_version":"1.0","event_id":"sha256:61301ffc17b39a14a276f916bb1b4c6656479de4a7716e2678044ca4d37f579e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:4NNMCIIUO6PD37FYHVON5XXIBU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reduce Indonesian Vocabularies with an Indonesian Sub-word Separator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Feng Chong, Huang Heyan, Mukhlis Amien","submitted_at":"2022-07-01T17:09:53Z","abstract_excerpt":"Indonesian is an agglutinative language since it has a compounding process of word-formation. Therefore, the translation model of this language requires a mechanism that is even lower than the word level, referred to as the sub-word level. This compounding process leads to a rare word problem since the number of vocabulary explodes. We propose a strategy to address the unique word problem of the neural machine translation (NMT) system, which uses Indonesian as a pair language. Our approach uses a rule-based method to transform a word into its roots and accompanied affixes to retain its meaning"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00552","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/2207.00552/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":"2026-07-05T04:36:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"naAeeNKkJ9qppkxm/2LBRL0W1+e2y8ZROU1JE1xQe9exSdyZmDioRhV44fmluB6LrWKiR8teW9cVRf7F8bhkBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:06:48.545592Z"},"content_sha256":"ab5aff0771fdbeccaba5c765b64520a8f05f003dc3bcaf7546c44d8c9952a0d5","schema_version":"1.0","event_id":"sha256:ab5aff0771fdbeccaba5c765b64520a8f05f003dc3bcaf7546c44d8c9952a0d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4NNMCIIUO6PD37FYHVON5XXIBU/bundle.json","state_url":"https://pith.science/pith/4NNMCIIUO6PD37FYHVON5XXIBU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4NNMCIIUO6PD37FYHVON5XXIBU/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":"2026-08-03T16:06:48Z","links":{"resolver":"https://pith.science/pith/4NNMCIIUO6PD37FYHVON5XXIBU","bundle":"https://pith.science/pith/4NNMCIIUO6PD37FYHVON5XXIBU/bundle.json","state":"https://pith.science/pith/4NNMCIIUO6PD37FYHVON5XXIBU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4NNMCIIUO6PD37FYHVON5XXIBU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:4NNMCIIUO6PD37FYHVON5XXIBU","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":"be923c88a18a9a7172928b2be298b0a61ad25faf5642b04bfcae00ef6971f071","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T17:09:53Z","title_canon_sha256":"1d95c73995cf7091beb19b409a9d8235e20d3637f5f0336c8663a5af57ecde9f"},"schema_version":"1.0","source":{"id":"2207.00552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2207.00552","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"arxiv_version","alias_value":"2207.00552v1","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.00552","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_12","alias_value":"4NNMCIIUO6PD","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_16","alias_value":"4NNMCIIUO6PD37FY","created_at":"2026-07-05T04:36:44Z"},{"alias_kind":"pith_short_8","alias_value":"4NNMCIIU","created_at":"2026-07-05T04:36:44Z"}],"graph_snapshots":[{"event_id":"sha256:ab5aff0771fdbeccaba5c765b64520a8f05f003dc3bcaf7546c44d8c9952a0d5","target":"graph","created_at":"2026-07-05T04:36:44Z","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/2207.00552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Indonesian is an agglutinative language since it has a compounding process of word-formation. Therefore, the translation model of this language requires a mechanism that is even lower than the word level, referred to as the sub-word level. This compounding process leads to a rare word problem since the number of vocabulary explodes. We propose a strategy to address the unique word problem of the neural machine translation (NMT) system, which uses Indonesian as a pair language. Our approach uses a rule-based method to transform a word into its roots and accompanied affixes to retain its meaning","authors_text":"Feng Chong, Huang Heyan, Mukhlis Amien","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T17:09:53Z","title":"Reduce Indonesian Vocabularies with an Indonesian Sub-word Separator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.00552","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":"sha256:61301ffc17b39a14a276f916bb1b4c6656479de4a7716e2678044ca4d37f579e","target":"record","created_at":"2026-07-05T04:36:44Z","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":"be923c88a18a9a7172928b2be298b0a61ad25faf5642b04bfcae00ef6971f071","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-07-01T17:09:53Z","title_canon_sha256":"1d95c73995cf7091beb19b409a9d8235e20d3637f5f0336c8663a5af57ecde9f"},"schema_version":"1.0","source":{"id":"2207.00552","kind":"arxiv","version":1}},"canonical_sha256":"e35ac12114779e3dfcb83d5cdedee80d3544aea975c7fbd819462a01b64004b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e35ac12114779e3dfcb83d5cdedee80d3544aea975c7fbd819462a01b64004b8","first_computed_at":"2026-07-05T04:36:44.394825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:44.394825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KbwPKI92SC+W7HpppFwO3UMqOHmcjyr+WqfDbf6liT7KM8kBl3SH6ojmxPLUiczrQj4xqnRdSBTs9zgzGFSQCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:44.395218Z","signed_message":"canonical_sha256_bytes"},"source_id":"2207.00552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61301ffc17b39a14a276f916bb1b4c6656479de4a7716e2678044ca4d37f579e","sha256:ab5aff0771fdbeccaba5c765b64520a8f05f003dc3bcaf7546c44d8c9952a0d5"],"state_sha256":"86409ebff73cb045f4233208c2784c97145ab00107731935184bba92093d48f1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cikCYGs0+Ex0CB6vIqRTn2Mw9bbzv/e6Pj8kSaeGNAEMIYvfMUdC+3uXbQem8mFGLmrXQoQejfMABrpFX0/CDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:06:48.551470Z","bundle_sha256":"49109ec03bc6e9e98375f25dc65d0450993eef4040c121120ea79ac6b66d31f6"}}