{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PILXBIZWK65MPAJPRCBAA3GVBU","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":"2adc693213a2d9b005782c42c821fa604033bfb4e2b2b66adcee892cd880b687","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:38:01Z","title_canon_sha256":"a815364128b0ee614540a31b3a4bfd86f160878c0fe2e89c5fba461371e8b6db"},"schema_version":"1.0","source":{"id":"1607.05822","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.05822","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"1607.05822v2","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.05822","created_at":"2026-05-18T01:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"PILXBIZWK65M","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PILXBIZWK65MPAJP","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PILXBIZW","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:d70024a5345e53a6baa601d6ec7360d94235caedd23a92d365227b60c65b9e05","target":"graph","created_at":"2026-05-18T01:04:01Z","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":"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","authors_text":"Ruey-Cheng Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:38:01Z","title":"Incremental Learning for Fully Unsupervised Word Segmentation Using Penalized Likelihood and Model Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.05822","kind":"arxiv","version":2},"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:d28a22bcf6cc8d03df49ad1f40622f308958ef151df8d3cabdb6e706c316790e","target":"record","created_at":"2026-05-18T01:04:01Z","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":"2adc693213a2d9b005782c42c821fa604033bfb4e2b2b66adcee892cd880b687","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-07-20T04:38:01Z","title_canon_sha256":"a815364128b0ee614540a31b3a4bfd86f160878c0fe2e89c5fba461371e8b6db"},"schema_version":"1.0","source":{"id":"1607.05822","kind":"arxiv","version":2}},"canonical_sha256":"7a1770a33657bac7812f8882006cd50d371c87bd08ccabb2848a204f8f6dbc36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a1770a33657bac7812f8882006cd50d371c87bd08ccabb2848a204f8f6dbc36","first_computed_at":"2026-05-18T01:04:01.078893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:01.078893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ccZemsI5mGIfD2PFgxLNOYE7B14nvlCCJnArL8uR3PHgxvpSAVZr6RP57xtpTlIfRxUpuRpU2s1/TWLmlMoSCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:01.079502Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.05822","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d28a22bcf6cc8d03df49ad1f40622f308958ef151df8d3cabdb6e706c316790e","sha256:d70024a5345e53a6baa601d6ec7360d94235caedd23a92d365227b60c65b9e05"],"state_sha256":"1cd56f5722bbe4252940e09b861cd9eb4869a23ccb3e4bd75eb766166f45cb4c"}