{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5EOUNUCBA5VKDYHJ4F3OO7ZRIH","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":"3388ae4356dea99520c2a14a2862b5532c2a1fac92d66db5ac3bfdcfffef25f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-10T09:41:46Z","title_canon_sha256":"5298c3bc202c4a0a72c92e01798d075cfac5fb7146dadc3a20eb9330ae8285e9"},"schema_version":"1.0","source":{"id":"1710.03476","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.03476","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"1710.03476v1","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.03476","created_at":"2026-05-18T00:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"5EOUNUCBA5VK","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5EOUNUCBA5VKDYHJ","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5EOUNUCB","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:b5b6de156a26b234a86efdefa93977b4a6fb27d791e4473e7731315bd9ecf37f","target":"graph","created_at":"2026-05-18T00:33:11Z","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 propose MoNoise: a normalization model focused on generalizability and efficiency, it aims at being easily reusable and adaptable. Normalization is the task of translating texts from a non- canonical domain to a more canonical domain, in our case: from social media data to standard language. Our proposed model is based on a modular candidate generation in which each module is responsible for a different type of normalization action. The most important generation modules are a spelling correction system and a word embeddings module. Depending on the definition of the normalization task, a st","authors_text":"Gertjan van Noord, Rob van der Goot","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-10T09:41:46Z","title":"MoNoise: Modeling Noise Using a Modular Normalization System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.03476","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:f5f8db33dee124c0b1f431994a3c206b794a88720c0c226fdad75444b99f5349","target":"record","created_at":"2026-05-18T00:33:11Z","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":"3388ae4356dea99520c2a14a2862b5532c2a1fac92d66db5ac3bfdcfffef25f6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-10T09:41:46Z","title_canon_sha256":"5298c3bc202c4a0a72c92e01798d075cfac5fb7146dadc3a20eb9330ae8285e9"},"schema_version":"1.0","source":{"id":"1710.03476","kind":"arxiv","version":1}},"canonical_sha256":"e91d46d041076aa1e0e9e176e77f3141ceb05fde2076abb5d035fa631bc082ed","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e91d46d041076aa1e0e9e176e77f3141ceb05fde2076abb5d035fa631bc082ed","first_computed_at":"2026-05-18T00:33:11.812047Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:33:11.812047Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"moogmjCbfz9bcnnZrgI8d2I2LqkNxcQLIXmD+KCZNfF2OZqlEI5FQLIRtSgPK9oorXS6DmlRcPYBw/Z66VGXBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:33:11.812529Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.03476","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5f8db33dee124c0b1f431994a3c206b794a88720c0c226fdad75444b99f5349","sha256:b5b6de156a26b234a86efdefa93977b4a6fb27d791e4473e7731315bd9ecf37f"],"state_sha256":"c05f66ebafb8a02eeb55521e39cb0f1ee1075cd961ed6398e53fa878439874df"}