{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:PILXBIZWK65MPAJPRCBAA3GVBU","short_pith_number":"pith:PILXBIZW","schema_version":"1.0","canonical_sha256":"7a1770a33657bac7812f8882006cd50d371c87bd08ccabb2848a204f8f6dbc36","source":{"kind":"arxiv","id":"1607.05822","version":2},"attestation_state":"computed","paper":{"title":"Incremental Learning for Fully Unsupervised Word Segmentation Using Penalized Likelihood and Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruey-Cheng Chen","submitted_at":"2016-07-20T04:38:01Z","abstract_excerpt":"We present a novel incremental learning approach for unsupervised word segmentation that combines features from probabilistic modeling and model selection. This includes super-additive penalties for addressing the cognitive burden imposed by long word formation, and new model selection criteria based on higher-order generative assumptions. Our approach is fully unsupervised; it relies on a small number of parameters that permits flexible modeling and a mechanism that automatically learns parameters from the data. Through experimentation, we show that this intricate design has led to top-tier p"},"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":"1607.05822","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:38:01Z","cross_cats_sorted":[],"title_canon_sha256":"a815364128b0ee614540a31b3a4bfd86f160878c0fe2e89c5fba461371e8b6db","abstract_canon_sha256":"2adc693213a2d9b005782c42c821fa604033bfb4e2b2b66adcee892cd880b687"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:01.079502Z","signature_b64":"ccZemsI5mGIfD2PFgxLNOYE7B14nvlCCJnArL8uR3PHgxvpSAVZr6RP57xtpTlIfRxUpuRpU2s1/TWLmlMoSCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a1770a33657bac7812f8882006cd50d371c87bd08ccabb2848a204f8f6dbc36","last_reissued_at":"2026-05-18T01:04:01.078893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:01.078893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incremental Learning for Fully Unsupervised Word Segmentation Using Penalized Likelihood and Model Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ruey-Cheng Chen","submitted_at":"2016-07-20T04:38:01Z","abstract_excerpt":"We present a novel incremental learning approach for unsupervised word segmentation that combines features from probabilistic modeling and model selection. This includes super-additive penalties for addressing the cognitive burden imposed by long word formation, and new model selection criteria based on higher-order generative assumptions. Our approach is fully unsupervised; it relies on a small number of parameters that permits flexible modeling and a mechanism that automatically learns parameters from the data. Through experimentation, we show that this intricate design has led to top-tier p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05822","kind":"arxiv","version":2},"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":"1607.05822","created_at":"2026-05-18T01:04:01.078985+00:00"},{"alias_kind":"arxiv_version","alias_value":"1607.05822v2","created_at":"2026-05-18T01:04:01.078985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05822","created_at":"2026-05-18T01:04:01.078985+00:00"},{"alias_kind":"pith_short_12","alias_value":"PILXBIZWK65M","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"PILXBIZWK65MPAJP","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"PILXBIZW","created_at":"2026-05-18T12:30:39.010887+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/PILXBIZWK65MPAJPRCBAA3GVBU","json":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU.json","graph_json":"https://pith.science/api/pith-number/PILXBIZWK65MPAJPRCBAA3GVBU/graph.json","events_json":"https://pith.science/api/pith-number/PILXBIZWK65MPAJPRCBAA3GVBU/events.json","paper":"https://pith.science/paper/PILXBIZW"},"agent_actions":{"view_html":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU","download_json":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU.json","view_paper":"https://pith.science/paper/PILXBIZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1607.05822&json=true","fetch_graph":"https://pith.science/api/pith-number/PILXBIZWK65MPAJPRCBAA3GVBU/graph.json","fetch_events":"https://pith.science/api/pith-number/PILXBIZWK65MPAJPRCBAA3GVBU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU/action/storage_attestation","attest_author":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU/action/author_attestation","sign_citation":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU/action/citation_signature","submit_replication":"https://pith.science/pith/PILXBIZWK65MPAJPRCBAA3GVBU/action/replication_record"}},"created_at":"2026-05-18T01:04:01.078985+00:00","updated_at":"2026-05-18T01:04:01.078985+00:00"}