{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:S67FUT5H5DFF24PMXDHZXDZ7GJ","short_pith_number":"pith:S67FUT5H","schema_version":"1.0","canonical_sha256":"97be5a4fa7e8ca5d71ecb8cf9b8f3f3268434f40f291ea827c2e68e129b4d6f3","source":{"kind":"arxiv","id":"1710.06112","version":1},"attestation_state":"computed","paper":{"title":"CASICT Tibetan Word Segmentation System for MLWS2017","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Hu, Qun Liu","submitted_at":"2017-10-17T06:05:50Z","abstract_excerpt":"We participated in the MLWS 2017 on Tibetan word segmentation task, our system is trained in a unrestricted way, by introducing a baseline system and 76w tibetan segmented sentences of ours. In the system character sequence is processed by the baseline system into word sequence, then a subword unit (BPE algorithm) split rare words into subwords with its corresponding features, after that a neural network classifier is adopted to token each subword into \"B,M,E,S\" label, in decoding step a simple rule is used to recover a final word sequence. The candidate system for submition is selected by eva"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1710.06112","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-17T06:05:50Z","cross_cats_sorted":[],"title_canon_sha256":"18d57c3f4a3d268c0bc7b967a2de6343b78affef680ed85107ef81113a31979a","abstract_canon_sha256":"9fd74a02e05cf18aae786dd16a9b26c740e11b04ec52b94b92676a9fd4fcf297"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:37.712884Z","signature_b64":"qWKl6ty6XQgz+aFp5kxPmPzOeLdqDDhDpo2lWpl+eljU62w1czVGdvCpQ6RI1StP8Vjl5cIFC857ZnsG1K+ACA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97be5a4fa7e8ca5d71ecb8cf9b8f3f3268434f40f291ea827c2e68e129b4d6f3","last_reissued_at":"2026-05-18T00:32:37.712213Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:37.712213Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CASICT Tibetan Word Segmentation System for MLWS2017","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiawei Hu, Qun Liu","submitted_at":"2017-10-17T06:05:50Z","abstract_excerpt":"We participated in the MLWS 2017 on Tibetan word segmentation task, our system is trained in a unrestricted way, by introducing a baseline system and 76w tibetan segmented sentences of ours. In the system character sequence is processed by the baseline system into word sequence, then a subword unit (BPE algorithm) split rare words into subwords with its corresponding features, after that a neural network classifier is adopted to token each subword into \"B,M,E,S\" label, in decoding step a simple rule is used to recover a final word sequence. The candidate system for submition is selected by eva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.06112","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1710.06112","created_at":"2026-05-18T00:32:37.712333+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.06112v1","created_at":"2026-05-18T00:32:37.712333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.06112","created_at":"2026-05-18T00:32:37.712333+00:00"},{"alias_kind":"pith_short_12","alias_value":"S67FUT5H5DFF","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_16","alias_value":"S67FUT5H5DFF24PM","created_at":"2026-05-18T12:31:43.269735+00:00"},{"alias_kind":"pith_short_8","alias_value":"S67FUT5H","created_at":"2026-05-18T12:31:43.269735+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ","json":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ.json","graph_json":"https://pith.science/api/pith-number/S67FUT5H5DFF24PMXDHZXDZ7GJ/graph.json","events_json":"https://pith.science/api/pith-number/S67FUT5H5DFF24PMXDHZXDZ7GJ/events.json","paper":"https://pith.science/paper/S67FUT5H"},"agent_actions":{"view_html":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ","download_json":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ.json","view_paper":"https://pith.science/paper/S67FUT5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.06112&json=true","fetch_graph":"https://pith.science/api/pith-number/S67FUT5H5DFF24PMXDHZXDZ7GJ/graph.json","fetch_events":"https://pith.science/api/pith-number/S67FUT5H5DFF24PMXDHZXDZ7GJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ/action/storage_attestation","attest_author":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ/action/author_attestation","sign_citation":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ/action/citation_signature","submit_replication":"https://pith.science/pith/S67FUT5H5DFF24PMXDHZXDZ7GJ/action/replication_record"}},"created_at":"2026-05-18T00:32:37.712333+00:00","updated_at":"2026-05-18T00:32:37.712333+00:00"}